Upload folder using huggingface_hub
Browse files- README.md +6 -6
- config.json +705 -1
- configuration.json +1 -0
- model-00001-of-00004.safetensors +2 -2
- model-00002-of-00004.safetensors +2 -2
- model-00003-of-00004.safetensors +2 -2
- model-00004-of-00004.safetensors +2 -2
- model.safetensors.index.json +661 -161
- preprocessor_config.json +21 -0
- processor_config.json +50 -0
- tokenizer_config.json +1 -1
- video_preprocessor_config.json +21 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -7,7 +7,7 @@ license: apache-2.0
|
|
| 7 |
base_model: Qwen/Qwen3.6-35B-A3B
|
| 8 |
base_model_relation: quantized
|
| 9 |
library_name: mlx
|
| 10 |
-
pipeline_tag: text-
|
| 11 |
tags:
|
| 12 |
- mlx
|
| 13 |
- qwen3_5_moe
|
|
@@ -46,15 +46,15 @@ Everything below is **measured, not projected** — KL / top-1 flip on a fixed 4
|
|
| 46 |
|
| 47 |
With int8 KV that leaves ~1.5 GiB of cache ≈ **150 K tokens** of context (KV here is tiny — see below). 111 tok/s decode makes this the best speed-per-GB option for 16 GB machines; prefer it over the dense 27B 16 GB build when throughput matters more than per-token quality.
|
| 48 |
|
| 49 |
-
## Multimodal (
|
| 50 |
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
|
| 55 |
```bash
|
| 56 |
pip install mlx-vlm
|
| 57 |
-
python -m mlx_vlm generate --model avlp12/Qwen3.6-35B-A3B-Alis-MLX-Dynamic
|
| 58 |
--image photo.jpg --prompt "이미지의 텍스트를 읽어줘." --max-tokens 300
|
| 59 |
```
|
| 60 |
|
|
|
|
| 7 |
base_model: Qwen/Qwen3.6-35B-A3B
|
| 8 |
base_model_relation: quantized
|
| 9 |
library_name: mlx
|
| 10 |
+
pipeline_tag: image-text-to-text
|
| 11 |
tags:
|
| 12 |
- mlx
|
| 13 |
- qwen3_5_moe
|
|
|
|
| 46 |
|
| 47 |
With int8 KV that leaves ~1.5 GiB of cache ≈ **150 K tokens** of context (KV here is tiny — see below). 111 tok/s decode makes this the best speed-per-GB option for 16 GB machines; prefer it over the dense 27B 16 GB build when throughput matters more than per-token quality.
|
| 48 |
|
| 49 |
+
## Multimodal (default)
|
| 50 |
|
| 51 |
+
`main` carries the full multimodal stack — 4.0bpw text weights + the vision tower at
|
| 52 |
+
8-bit (verified with EN/KO OCR tests). Plain mlx-lm loads `main` fine for text-only use;
|
| 53 |
+
the `text` branch saves 0.60 GB if you never need images.
|
| 54 |
|
| 55 |
```bash
|
| 56 |
pip install mlx-vlm
|
| 57 |
+
python -m mlx_vlm generate --model avlp12/Qwen3.6-35B-A3B-Alis-MLX-Dynamic \
|
| 58 |
--image photo.jpg --prompt "이미지의 텍스트를 읽어줘." --max-tokens 300
|
| 59 |
```
|
| 60 |
|
config.json
CHANGED
|
@@ -2,16 +2,365 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3_5MoeForConditionalGeneration"
|
| 4 |
],
|
|
|
|
| 5 |
"eos_token_id": [
|
| 6 |
248046,
|
| 7 |
248044
|
| 8 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"image_token_id": 248056,
|
| 10 |
"model_type": "qwen3_5_moe",
|
| 11 |
"quantization": {
|
| 12 |
"group_size": 64,
|
| 13 |
"bits": 4,
|
| 14 |
"mode": "affine",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"language_model.model.embed_tokens": {
|
| 16 |
"bits": 4,
|
| 17 |
"group_size": 16,
|
|
@@ -2577,6 +2926,342 @@
|
|
| 2577 |
"group_size": 64,
|
| 2578 |
"bits": 4,
|
| 2579 |
"mode": "affine",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2580 |
"language_model.model.embed_tokens": {
|
| 2581 |
"bits": 4,
|
| 2582 |
"group_size": 16,
|
|
@@ -5138,6 +5823,7 @@
|
|
| 5138 |
"mode": "nvfp4"
|
| 5139 |
}
|
| 5140 |
},
|
|
|
|
| 5141 |
"text_config": {
|
| 5142 |
"attention_bias": false,
|
| 5143 |
"attention_dropout": 0.0,
|
|
@@ -5221,7 +5907,7 @@
|
|
| 5221 |
],
|
| 5222 |
"partial_rotary_factor": 0.25,
|
| 5223 |
"rope_theta": 10000000,
|
| 5224 |
-
"
|
| 5225 |
},
|
| 5226 |
"router_aux_loss_coef": 0.001,
|
| 5227 |
"shared_expert_intermediate_size": 512,
|
|
@@ -5230,8 +5916,26 @@
|
|
| 5230 |
"vocab_size": 248320
|
| 5231 |
},
|
| 5232 |
"tie_word_embeddings": false,
|
|
|
|
|
|
|
| 5233 |
"transformers_version": "4.57.1",
|
| 5234 |
"video_token_id": 248057,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5235 |
"vision_end_token_id": 248054,
|
| 5236 |
"vision_start_token_id": 248053
|
| 5237 |
}
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3_5MoeForConditionalGeneration"
|
| 4 |
],
|
| 5 |
+
"do_sample": true,
|
| 6 |
"eos_token_id": [
|
| 7 |
248046,
|
| 8 |
248044
|
| 9 |
],
|
| 10 |
+
"generation_config": {
|
| 11 |
+
"bos_token_id": 248044,
|
| 12 |
+
"do_sample": true,
|
| 13 |
+
"eos_token_id": [
|
| 14 |
+
248046,
|
| 15 |
+
248044
|
| 16 |
+
],
|
| 17 |
+
"pad_token_id": 248044,
|
| 18 |
+
"temperature": 1.0,
|
| 19 |
+
"top_k": 20,
|
| 20 |
+
"top_p": 0.95
|
| 21 |
+
},
|
| 22 |
"image_token_id": 248056,
|
| 23 |
"model_type": "qwen3_5_moe",
|
| 24 |
"quantization": {
|
| 25 |
"group_size": 64,
|
| 26 |
"bits": 4,
|
| 27 |
"mode": "affine",
|
| 28 |
+
"vision_tower.pos_embed": {
|
| 29 |
+
"group_size": 64,
|
| 30 |
+
"bits": 8
|
| 31 |
+
},
|
| 32 |
+
"vision_tower.blocks.0.attn.qkv": {
|
| 33 |
+
"group_size": 64,
|
| 34 |
+
"bits": 8
|
| 35 |
+
},
|
| 36 |
+
"vision_tower.blocks.0.attn.proj": {
|
| 37 |
+
"group_size": 64,
|
| 38 |
+
"bits": 8
|
| 39 |
+
},
|
| 40 |
+
"vision_tower.blocks.0.mlp.linear_fc1": {
|
| 41 |
+
"group_size": 64,
|
| 42 |
+
"bits": 8
|
| 43 |
+
},
|
| 44 |
+
"vision_tower.blocks.1.attn.qkv": {
|
| 45 |
+
"group_size": 64,
|
| 46 |
+
"bits": 8
|
| 47 |
+
},
|
| 48 |
+
"vision_tower.blocks.1.attn.proj": {
|
| 49 |
+
"group_size": 64,
|
| 50 |
+
"bits": 8
|
| 51 |
+
},
|
| 52 |
+
"vision_tower.blocks.1.mlp.linear_fc1": {
|
| 53 |
+
"group_size": 64,
|
| 54 |
+
"bits": 8
|
| 55 |
+
},
|
| 56 |
+
"vision_tower.blocks.2.attn.qkv": {
|
| 57 |
+
"group_size": 64,
|
| 58 |
+
"bits": 8
|
| 59 |
+
},
|
| 60 |
+
"vision_tower.blocks.2.attn.proj": {
|
| 61 |
+
"group_size": 64,
|
| 62 |
+
"bits": 8
|
| 63 |
+
},
|
| 64 |
+
"vision_tower.blocks.2.mlp.linear_fc1": {
|
| 65 |
+
"group_size": 64,
|
| 66 |
+
"bits": 8
|
| 67 |
+
},
|
| 68 |
+
"vision_tower.blocks.3.attn.qkv": {
|
| 69 |
+
"group_size": 64,
|
| 70 |
+
"bits": 8
|
| 71 |
+
},
|
| 72 |
+
"vision_tower.blocks.3.attn.proj": {
|
| 73 |
+
"group_size": 64,
|
| 74 |
+
"bits": 8
|
| 75 |
+
},
|
| 76 |
+
"vision_tower.blocks.3.mlp.linear_fc1": {
|
| 77 |
+
"group_size": 64,
|
| 78 |
+
"bits": 8
|
| 79 |
+
},
|
| 80 |
+
"vision_tower.blocks.4.attn.qkv": {
|
| 81 |
+
"group_size": 64,
|
| 82 |
+
"bits": 8
|
| 83 |
+
},
|
| 84 |
+
"vision_tower.blocks.4.attn.proj": {
|
| 85 |
+
"group_size": 64,
|
| 86 |
+
"bits": 8
|
| 87 |
+
},
|
| 88 |
+
"vision_tower.blocks.4.mlp.linear_fc1": {
|
| 89 |
+
"group_size": 64,
|
| 90 |
+
"bits": 8
|
| 91 |
+
},
|
| 92 |
+
"vision_tower.blocks.5.attn.qkv": {
|
| 93 |
+
"group_size": 64,
|
| 94 |
+
"bits": 8
|
| 95 |
+
},
|
| 96 |
+
"vision_tower.blocks.5.attn.proj": {
|
| 97 |
+
"group_size": 64,
|
| 98 |
+
"bits": 8
|
| 99 |
+
},
|
| 100 |
+
"vision_tower.blocks.5.mlp.linear_fc1": {
|
| 101 |
+
"group_size": 64,
|
| 102 |
+
"bits": 8
|
| 103 |
+
},
|
| 104 |
+
"vision_tower.blocks.6.attn.qkv": {
|
| 105 |
+
"group_size": 64,
|
| 106 |
+
"bits": 8
|
| 107 |
+
},
|
| 108 |
+
"vision_tower.blocks.6.attn.proj": {
|
| 109 |
+
"group_size": 64,
|
| 110 |
+
"bits": 8
|
| 111 |
+
},
|
| 112 |
+
"vision_tower.blocks.6.mlp.linear_fc1": {
|
| 113 |
+
"group_size": 64,
|
| 114 |
+
"bits": 8
|
| 115 |
+
},
|
| 116 |
+
"vision_tower.blocks.7.attn.qkv": {
|
| 117 |
+
"group_size": 64,
|
| 118 |
+
"bits": 8
|
| 119 |
+
},
|
| 120 |
+
"vision_tower.blocks.7.attn.proj": {
|
| 121 |
+
"group_size": 64,
|
| 122 |
+
"bits": 8
|
| 123 |
+
},
|
| 124 |
+
"vision_tower.blocks.7.mlp.linear_fc1": {
|
| 125 |
+
"group_size": 64,
|
| 126 |
+
"bits": 8
|
| 127 |
+
},
|
| 128 |
+
"vision_tower.blocks.8.attn.qkv": {
|
| 129 |
+
"group_size": 64,
|
| 130 |
+
"bits": 8
|
| 131 |
+
},
|
| 132 |
+
"vision_tower.blocks.8.attn.proj": {
|
| 133 |
+
"group_size": 64,
|
| 134 |
+
"bits": 8
|
| 135 |
+
},
|
| 136 |
+
"vision_tower.blocks.8.mlp.linear_fc1": {
|
| 137 |
+
"group_size": 64,
|
| 138 |
+
"bits": 8
|
| 139 |
+
},
|
| 140 |
+
"vision_tower.blocks.9.attn.qkv": {
|
| 141 |
+
"group_size": 64,
|
| 142 |
+
"bits": 8
|
| 143 |
+
},
|
| 144 |
+
"vision_tower.blocks.9.attn.proj": {
|
| 145 |
+
"group_size": 64,
|
| 146 |
+
"bits": 8
|
| 147 |
+
},
|
| 148 |
+
"vision_tower.blocks.9.mlp.linear_fc1": {
|
| 149 |
+
"group_size": 64,
|
| 150 |
+
"bits": 8
|
| 151 |
+
},
|
| 152 |
+
"vision_tower.blocks.10.attn.qkv": {
|
| 153 |
+
"group_size": 64,
|
| 154 |
+
"bits": 8
|
| 155 |
+
},
|
| 156 |
+
"vision_tower.blocks.10.attn.proj": {
|
| 157 |
+
"group_size": 64,
|
| 158 |
+
"bits": 8
|
| 159 |
+
},
|
| 160 |
+
"vision_tower.blocks.10.mlp.linear_fc1": {
|
| 161 |
+
"group_size": 64,
|
| 162 |
+
"bits": 8
|
| 163 |
+
},
|
| 164 |
+
"vision_tower.blocks.11.attn.qkv": {
|
| 165 |
+
"group_size": 64,
|
| 166 |
+
"bits": 8
|
| 167 |
+
},
|
| 168 |
+
"vision_tower.blocks.11.attn.proj": {
|
| 169 |
+
"group_size": 64,
|
| 170 |
+
"bits": 8
|
| 171 |
+
},
|
| 172 |
+
"vision_tower.blocks.11.mlp.linear_fc1": {
|
| 173 |
+
"group_size": 64,
|
| 174 |
+
"bits": 8
|
| 175 |
+
},
|
| 176 |
+
"vision_tower.blocks.12.attn.qkv": {
|
| 177 |
+
"group_size": 64,
|
| 178 |
+
"bits": 8
|
| 179 |
+
},
|
| 180 |
+
"vision_tower.blocks.12.attn.proj": {
|
| 181 |
+
"group_size": 64,
|
| 182 |
+
"bits": 8
|
| 183 |
+
},
|
| 184 |
+
"vision_tower.blocks.12.mlp.linear_fc1": {
|
| 185 |
+
"group_size": 64,
|
| 186 |
+
"bits": 8
|
| 187 |
+
},
|
| 188 |
+
"vision_tower.blocks.13.attn.qkv": {
|
| 189 |
+
"group_size": 64,
|
| 190 |
+
"bits": 8
|
| 191 |
+
},
|
| 192 |
+
"vision_tower.blocks.13.attn.proj": {
|
| 193 |
+
"group_size": 64,
|
| 194 |
+
"bits": 8
|
| 195 |
+
},
|
| 196 |
+
"vision_tower.blocks.13.mlp.linear_fc1": {
|
| 197 |
+
"group_size": 64,
|
| 198 |
+
"bits": 8
|
| 199 |
+
},
|
| 200 |
+
"vision_tower.blocks.14.attn.qkv": {
|
| 201 |
+
"group_size": 64,
|
| 202 |
+
"bits": 8
|
| 203 |
+
},
|
| 204 |
+
"vision_tower.blocks.14.attn.proj": {
|
| 205 |
+
"group_size": 64,
|
| 206 |
+
"bits": 8
|
| 207 |
+
},
|
| 208 |
+
"vision_tower.blocks.14.mlp.linear_fc1": {
|
| 209 |
+
"group_size": 64,
|
| 210 |
+
"bits": 8
|
| 211 |
+
},
|
| 212 |
+
"vision_tower.blocks.15.attn.qkv": {
|
| 213 |
+
"group_size": 64,
|
| 214 |
+
"bits": 8
|
| 215 |
+
},
|
| 216 |
+
"vision_tower.blocks.15.attn.proj": {
|
| 217 |
+
"group_size": 64,
|
| 218 |
+
"bits": 8
|
| 219 |
+
},
|
| 220 |
+
"vision_tower.blocks.15.mlp.linear_fc1": {
|
| 221 |
+
"group_size": 64,
|
| 222 |
+
"bits": 8
|
| 223 |
+
},
|
| 224 |
+
"vision_tower.blocks.16.attn.qkv": {
|
| 225 |
+
"group_size": 64,
|
| 226 |
+
"bits": 8
|
| 227 |
+
},
|
| 228 |
+
"vision_tower.blocks.16.attn.proj": {
|
| 229 |
+
"group_size": 64,
|
| 230 |
+
"bits": 8
|
| 231 |
+
},
|
| 232 |
+
"vision_tower.blocks.16.mlp.linear_fc1": {
|
| 233 |
+
"group_size": 64,
|
| 234 |
+
"bits": 8
|
| 235 |
+
},
|
| 236 |
+
"vision_tower.blocks.17.attn.qkv": {
|
| 237 |
+
"group_size": 64,
|
| 238 |
+
"bits": 8
|
| 239 |
+
},
|
| 240 |
+
"vision_tower.blocks.17.attn.proj": {
|
| 241 |
+
"group_size": 64,
|
| 242 |
+
"bits": 8
|
| 243 |
+
},
|
| 244 |
+
"vision_tower.blocks.17.mlp.linear_fc1": {
|
| 245 |
+
"group_size": 64,
|
| 246 |
+
"bits": 8
|
| 247 |
+
},
|
| 248 |
+
"vision_tower.blocks.18.attn.qkv": {
|
| 249 |
+
"group_size": 64,
|
| 250 |
+
"bits": 8
|
| 251 |
+
},
|
| 252 |
+
"vision_tower.blocks.18.attn.proj": {
|
| 253 |
+
"group_size": 64,
|
| 254 |
+
"bits": 8
|
| 255 |
+
},
|
| 256 |
+
"vision_tower.blocks.18.mlp.linear_fc1": {
|
| 257 |
+
"group_size": 64,
|
| 258 |
+
"bits": 8
|
| 259 |
+
},
|
| 260 |
+
"vision_tower.blocks.19.attn.qkv": {
|
| 261 |
+
"group_size": 64,
|
| 262 |
+
"bits": 8
|
| 263 |
+
},
|
| 264 |
+
"vision_tower.blocks.19.attn.proj": {
|
| 265 |
+
"group_size": 64,
|
| 266 |
+
"bits": 8
|
| 267 |
+
},
|
| 268 |
+
"vision_tower.blocks.19.mlp.linear_fc1": {
|
| 269 |
+
"group_size": 64,
|
| 270 |
+
"bits": 8
|
| 271 |
+
},
|
| 272 |
+
"vision_tower.blocks.20.attn.qkv": {
|
| 273 |
+
"group_size": 64,
|
| 274 |
+
"bits": 8
|
| 275 |
+
},
|
| 276 |
+
"vision_tower.blocks.20.attn.proj": {
|
| 277 |
+
"group_size": 64,
|
| 278 |
+
"bits": 8
|
| 279 |
+
},
|
| 280 |
+
"vision_tower.blocks.20.mlp.linear_fc1": {
|
| 281 |
+
"group_size": 64,
|
| 282 |
+
"bits": 8
|
| 283 |
+
},
|
| 284 |
+
"vision_tower.blocks.21.attn.qkv": {
|
| 285 |
+
"group_size": 64,
|
| 286 |
+
"bits": 8
|
| 287 |
+
},
|
| 288 |
+
"vision_tower.blocks.21.attn.proj": {
|
| 289 |
+
"group_size": 64,
|
| 290 |
+
"bits": 8
|
| 291 |
+
},
|
| 292 |
+
"vision_tower.blocks.21.mlp.linear_fc1": {
|
| 293 |
+
"group_size": 64,
|
| 294 |
+
"bits": 8
|
| 295 |
+
},
|
| 296 |
+
"vision_tower.blocks.22.attn.qkv": {
|
| 297 |
+
"group_size": 64,
|
| 298 |
+
"bits": 8
|
| 299 |
+
},
|
| 300 |
+
"vision_tower.blocks.22.attn.proj": {
|
| 301 |
+
"group_size": 64,
|
| 302 |
+
"bits": 8
|
| 303 |
+
},
|
| 304 |
+
"vision_tower.blocks.22.mlp.linear_fc1": {
|
| 305 |
+
"group_size": 64,
|
| 306 |
+
"bits": 8
|
| 307 |
+
},
|
| 308 |
+
"vision_tower.blocks.23.attn.qkv": {
|
| 309 |
+
"group_size": 64,
|
| 310 |
+
"bits": 8
|
| 311 |
+
},
|
| 312 |
+
"vision_tower.blocks.23.attn.proj": {
|
| 313 |
+
"group_size": 64,
|
| 314 |
+
"bits": 8
|
| 315 |
+
},
|
| 316 |
+
"vision_tower.blocks.23.mlp.linear_fc1": {
|
| 317 |
+
"group_size": 64,
|
| 318 |
+
"bits": 8
|
| 319 |
+
},
|
| 320 |
+
"vision_tower.blocks.24.attn.qkv": {
|
| 321 |
+
"group_size": 64,
|
| 322 |
+
"bits": 8
|
| 323 |
+
},
|
| 324 |
+
"vision_tower.blocks.24.attn.proj": {
|
| 325 |
+
"group_size": 64,
|
| 326 |
+
"bits": 8
|
| 327 |
+
},
|
| 328 |
+
"vision_tower.blocks.24.mlp.linear_fc1": {
|
| 329 |
+
"group_size": 64,
|
| 330 |
+
"bits": 8
|
| 331 |
+
},
|
| 332 |
+
"vision_tower.blocks.25.attn.qkv": {
|
| 333 |
+
"group_size": 64,
|
| 334 |
+
"bits": 8
|
| 335 |
+
},
|
| 336 |
+
"vision_tower.blocks.25.attn.proj": {
|
| 337 |
+
"group_size": 64,
|
| 338 |
+
"bits": 8
|
| 339 |
+
},
|
| 340 |
+
"vision_tower.blocks.25.mlp.linear_fc1": {
|
| 341 |
+
"group_size": 64,
|
| 342 |
+
"bits": 8
|
| 343 |
+
},
|
| 344 |
+
"vision_tower.blocks.26.attn.qkv": {
|
| 345 |
+
"group_size": 64,
|
| 346 |
+
"bits": 8
|
| 347 |
+
},
|
| 348 |
+
"vision_tower.blocks.26.attn.proj": {
|
| 349 |
+
"group_size": 64,
|
| 350 |
+
"bits": 8
|
| 351 |
+
},
|
| 352 |
+
"vision_tower.blocks.26.mlp.linear_fc1": {
|
| 353 |
+
"group_size": 64,
|
| 354 |
+
"bits": 8
|
| 355 |
+
},
|
| 356 |
+
"vision_tower.merger.linear_fc1": {
|
| 357 |
+
"group_size": 64,
|
| 358 |
+
"bits": 8
|
| 359 |
+
},
|
| 360 |
+
"vision_tower.merger.linear_fc2": {
|
| 361 |
+
"group_size": 64,
|
| 362 |
+
"bits": 8
|
| 363 |
+
},
|
| 364 |
"language_model.model.embed_tokens": {
|
| 365 |
"bits": 4,
|
| 366 |
"group_size": 16,
|
|
|
|
| 2926 |
"group_size": 64,
|
| 2927 |
"bits": 4,
|
| 2928 |
"mode": "affine",
|
| 2929 |
+
"vision_tower.pos_embed": {
|
| 2930 |
+
"group_size": 64,
|
| 2931 |
+
"bits": 8
|
| 2932 |
+
},
|
| 2933 |
+
"vision_tower.blocks.0.attn.qkv": {
|
| 2934 |
+
"group_size": 64,
|
| 2935 |
+
"bits": 8
|
| 2936 |
+
},
|
| 2937 |
+
"vision_tower.blocks.0.attn.proj": {
|
| 2938 |
+
"group_size": 64,
|
| 2939 |
+
"bits": 8
|
| 2940 |
+
},
|
| 2941 |
+
"vision_tower.blocks.0.mlp.linear_fc1": {
|
| 2942 |
+
"group_size": 64,
|
| 2943 |
+
"bits": 8
|
| 2944 |
+
},
|
| 2945 |
+
"vision_tower.blocks.1.attn.qkv": {
|
| 2946 |
+
"group_size": 64,
|
| 2947 |
+
"bits": 8
|
| 2948 |
+
},
|
| 2949 |
+
"vision_tower.blocks.1.attn.proj": {
|
| 2950 |
+
"group_size": 64,
|
| 2951 |
+
"bits": 8
|
| 2952 |
+
},
|
| 2953 |
+
"vision_tower.blocks.1.mlp.linear_fc1": {
|
| 2954 |
+
"group_size": 64,
|
| 2955 |
+
"bits": 8
|
| 2956 |
+
},
|
| 2957 |
+
"vision_tower.blocks.2.attn.qkv": {
|
| 2958 |
+
"group_size": 64,
|
| 2959 |
+
"bits": 8
|
| 2960 |
+
},
|
| 2961 |
+
"vision_tower.blocks.2.attn.proj": {
|
| 2962 |
+
"group_size": 64,
|
| 2963 |
+
"bits": 8
|
| 2964 |
+
},
|
| 2965 |
+
"vision_tower.blocks.2.mlp.linear_fc1": {
|
| 2966 |
+
"group_size": 64,
|
| 2967 |
+
"bits": 8
|
| 2968 |
+
},
|
| 2969 |
+
"vision_tower.blocks.3.attn.qkv": {
|
| 2970 |
+
"group_size": 64,
|
| 2971 |
+
"bits": 8
|
| 2972 |
+
},
|
| 2973 |
+
"vision_tower.blocks.3.attn.proj": {
|
| 2974 |
+
"group_size": 64,
|
| 2975 |
+
"bits": 8
|
| 2976 |
+
},
|
| 2977 |
+
"vision_tower.blocks.3.mlp.linear_fc1": {
|
| 2978 |
+
"group_size": 64,
|
| 2979 |
+
"bits": 8
|
| 2980 |
+
},
|
| 2981 |
+
"vision_tower.blocks.4.attn.qkv": {
|
| 2982 |
+
"group_size": 64,
|
| 2983 |
+
"bits": 8
|
| 2984 |
+
},
|
| 2985 |
+
"vision_tower.blocks.4.attn.proj": {
|
| 2986 |
+
"group_size": 64,
|
| 2987 |
+
"bits": 8
|
| 2988 |
+
},
|
| 2989 |
+
"vision_tower.blocks.4.mlp.linear_fc1": {
|
| 2990 |
+
"group_size": 64,
|
| 2991 |
+
"bits": 8
|
| 2992 |
+
},
|
| 2993 |
+
"vision_tower.blocks.5.attn.qkv": {
|
| 2994 |
+
"group_size": 64,
|
| 2995 |
+
"bits": 8
|
| 2996 |
+
},
|
| 2997 |
+
"vision_tower.blocks.5.attn.proj": {
|
| 2998 |
+
"group_size": 64,
|
| 2999 |
+
"bits": 8
|
| 3000 |
+
},
|
| 3001 |
+
"vision_tower.blocks.5.mlp.linear_fc1": {
|
| 3002 |
+
"group_size": 64,
|
| 3003 |
+
"bits": 8
|
| 3004 |
+
},
|
| 3005 |
+
"vision_tower.blocks.6.attn.qkv": {
|
| 3006 |
+
"group_size": 64,
|
| 3007 |
+
"bits": 8
|
| 3008 |
+
},
|
| 3009 |
+
"vision_tower.blocks.6.attn.proj": {
|
| 3010 |
+
"group_size": 64,
|
| 3011 |
+
"bits": 8
|
| 3012 |
+
},
|
| 3013 |
+
"vision_tower.blocks.6.mlp.linear_fc1": {
|
| 3014 |
+
"group_size": 64,
|
| 3015 |
+
"bits": 8
|
| 3016 |
+
},
|
| 3017 |
+
"vision_tower.blocks.7.attn.qkv": {
|
| 3018 |
+
"group_size": 64,
|
| 3019 |
+
"bits": 8
|
| 3020 |
+
},
|
| 3021 |
+
"vision_tower.blocks.7.attn.proj": {
|
| 3022 |
+
"group_size": 64,
|
| 3023 |
+
"bits": 8
|
| 3024 |
+
},
|
| 3025 |
+
"vision_tower.blocks.7.mlp.linear_fc1": {
|
| 3026 |
+
"group_size": 64,
|
| 3027 |
+
"bits": 8
|
| 3028 |
+
},
|
| 3029 |
+
"vision_tower.blocks.8.attn.qkv": {
|
| 3030 |
+
"group_size": 64,
|
| 3031 |
+
"bits": 8
|
| 3032 |
+
},
|
| 3033 |
+
"vision_tower.blocks.8.attn.proj": {
|
| 3034 |
+
"group_size": 64,
|
| 3035 |
+
"bits": 8
|
| 3036 |
+
},
|
| 3037 |
+
"vision_tower.blocks.8.mlp.linear_fc1": {
|
| 3038 |
+
"group_size": 64,
|
| 3039 |
+
"bits": 8
|
| 3040 |
+
},
|
| 3041 |
+
"vision_tower.blocks.9.attn.qkv": {
|
| 3042 |
+
"group_size": 64,
|
| 3043 |
+
"bits": 8
|
| 3044 |
+
},
|
| 3045 |
+
"vision_tower.blocks.9.attn.proj": {
|
| 3046 |
+
"group_size": 64,
|
| 3047 |
+
"bits": 8
|
| 3048 |
+
},
|
| 3049 |
+
"vision_tower.blocks.9.mlp.linear_fc1": {
|
| 3050 |
+
"group_size": 64,
|
| 3051 |
+
"bits": 8
|
| 3052 |
+
},
|
| 3053 |
+
"vision_tower.blocks.10.attn.qkv": {
|
| 3054 |
+
"group_size": 64,
|
| 3055 |
+
"bits": 8
|
| 3056 |
+
},
|
| 3057 |
+
"vision_tower.blocks.10.attn.proj": {
|
| 3058 |
+
"group_size": 64,
|
| 3059 |
+
"bits": 8
|
| 3060 |
+
},
|
| 3061 |
+
"vision_tower.blocks.10.mlp.linear_fc1": {
|
| 3062 |
+
"group_size": 64,
|
| 3063 |
+
"bits": 8
|
| 3064 |
+
},
|
| 3065 |
+
"vision_tower.blocks.11.attn.qkv": {
|
| 3066 |
+
"group_size": 64,
|
| 3067 |
+
"bits": 8
|
| 3068 |
+
},
|
| 3069 |
+
"vision_tower.blocks.11.attn.proj": {
|
| 3070 |
+
"group_size": 64,
|
| 3071 |
+
"bits": 8
|
| 3072 |
+
},
|
| 3073 |
+
"vision_tower.blocks.11.mlp.linear_fc1": {
|
| 3074 |
+
"group_size": 64,
|
| 3075 |
+
"bits": 8
|
| 3076 |
+
},
|
| 3077 |
+
"vision_tower.blocks.12.attn.qkv": {
|
| 3078 |
+
"group_size": 64,
|
| 3079 |
+
"bits": 8
|
| 3080 |
+
},
|
| 3081 |
+
"vision_tower.blocks.12.attn.proj": {
|
| 3082 |
+
"group_size": 64,
|
| 3083 |
+
"bits": 8
|
| 3084 |
+
},
|
| 3085 |
+
"vision_tower.blocks.12.mlp.linear_fc1": {
|
| 3086 |
+
"group_size": 64,
|
| 3087 |
+
"bits": 8
|
| 3088 |
+
},
|
| 3089 |
+
"vision_tower.blocks.13.attn.qkv": {
|
| 3090 |
+
"group_size": 64,
|
| 3091 |
+
"bits": 8
|
| 3092 |
+
},
|
| 3093 |
+
"vision_tower.blocks.13.attn.proj": {
|
| 3094 |
+
"group_size": 64,
|
| 3095 |
+
"bits": 8
|
| 3096 |
+
},
|
| 3097 |
+
"vision_tower.blocks.13.mlp.linear_fc1": {
|
| 3098 |
+
"group_size": 64,
|
| 3099 |
+
"bits": 8
|
| 3100 |
+
},
|
| 3101 |
+
"vision_tower.blocks.14.attn.qkv": {
|
| 3102 |
+
"group_size": 64,
|
| 3103 |
+
"bits": 8
|
| 3104 |
+
},
|
| 3105 |
+
"vision_tower.blocks.14.attn.proj": {
|
| 3106 |
+
"group_size": 64,
|
| 3107 |
+
"bits": 8
|
| 3108 |
+
},
|
| 3109 |
+
"vision_tower.blocks.14.mlp.linear_fc1": {
|
| 3110 |
+
"group_size": 64,
|
| 3111 |
+
"bits": 8
|
| 3112 |
+
},
|
| 3113 |
+
"vision_tower.blocks.15.attn.qkv": {
|
| 3114 |
+
"group_size": 64,
|
| 3115 |
+
"bits": 8
|
| 3116 |
+
},
|
| 3117 |
+
"vision_tower.blocks.15.attn.proj": {
|
| 3118 |
+
"group_size": 64,
|
| 3119 |
+
"bits": 8
|
| 3120 |
+
},
|
| 3121 |
+
"vision_tower.blocks.15.mlp.linear_fc1": {
|
| 3122 |
+
"group_size": 64,
|
| 3123 |
+
"bits": 8
|
| 3124 |
+
},
|
| 3125 |
+
"vision_tower.blocks.16.attn.qkv": {
|
| 3126 |
+
"group_size": 64,
|
| 3127 |
+
"bits": 8
|
| 3128 |
+
},
|
| 3129 |
+
"vision_tower.blocks.16.attn.proj": {
|
| 3130 |
+
"group_size": 64,
|
| 3131 |
+
"bits": 8
|
| 3132 |
+
},
|
| 3133 |
+
"vision_tower.blocks.16.mlp.linear_fc1": {
|
| 3134 |
+
"group_size": 64,
|
| 3135 |
+
"bits": 8
|
| 3136 |
+
},
|
| 3137 |
+
"vision_tower.blocks.17.attn.qkv": {
|
| 3138 |
+
"group_size": 64,
|
| 3139 |
+
"bits": 8
|
| 3140 |
+
},
|
| 3141 |
+
"vision_tower.blocks.17.attn.proj": {
|
| 3142 |
+
"group_size": 64,
|
| 3143 |
+
"bits": 8
|
| 3144 |
+
},
|
| 3145 |
+
"vision_tower.blocks.17.mlp.linear_fc1": {
|
| 3146 |
+
"group_size": 64,
|
| 3147 |
+
"bits": 8
|
| 3148 |
+
},
|
| 3149 |
+
"vision_tower.blocks.18.attn.qkv": {
|
| 3150 |
+
"group_size": 64,
|
| 3151 |
+
"bits": 8
|
| 3152 |
+
},
|
| 3153 |
+
"vision_tower.blocks.18.attn.proj": {
|
| 3154 |
+
"group_size": 64,
|
| 3155 |
+
"bits": 8
|
| 3156 |
+
},
|
| 3157 |
+
"vision_tower.blocks.18.mlp.linear_fc1": {
|
| 3158 |
+
"group_size": 64,
|
| 3159 |
+
"bits": 8
|
| 3160 |
+
},
|
| 3161 |
+
"vision_tower.blocks.19.attn.qkv": {
|
| 3162 |
+
"group_size": 64,
|
| 3163 |
+
"bits": 8
|
| 3164 |
+
},
|
| 3165 |
+
"vision_tower.blocks.19.attn.proj": {
|
| 3166 |
+
"group_size": 64,
|
| 3167 |
+
"bits": 8
|
| 3168 |
+
},
|
| 3169 |
+
"vision_tower.blocks.19.mlp.linear_fc1": {
|
| 3170 |
+
"group_size": 64,
|
| 3171 |
+
"bits": 8
|
| 3172 |
+
},
|
| 3173 |
+
"vision_tower.blocks.20.attn.qkv": {
|
| 3174 |
+
"group_size": 64,
|
| 3175 |
+
"bits": 8
|
| 3176 |
+
},
|
| 3177 |
+
"vision_tower.blocks.20.attn.proj": {
|
| 3178 |
+
"group_size": 64,
|
| 3179 |
+
"bits": 8
|
| 3180 |
+
},
|
| 3181 |
+
"vision_tower.blocks.20.mlp.linear_fc1": {
|
| 3182 |
+
"group_size": 64,
|
| 3183 |
+
"bits": 8
|
| 3184 |
+
},
|
| 3185 |
+
"vision_tower.blocks.21.attn.qkv": {
|
| 3186 |
+
"group_size": 64,
|
| 3187 |
+
"bits": 8
|
| 3188 |
+
},
|
| 3189 |
+
"vision_tower.blocks.21.attn.proj": {
|
| 3190 |
+
"group_size": 64,
|
| 3191 |
+
"bits": 8
|
| 3192 |
+
},
|
| 3193 |
+
"vision_tower.blocks.21.mlp.linear_fc1": {
|
| 3194 |
+
"group_size": 64,
|
| 3195 |
+
"bits": 8
|
| 3196 |
+
},
|
| 3197 |
+
"vision_tower.blocks.22.attn.qkv": {
|
| 3198 |
+
"group_size": 64,
|
| 3199 |
+
"bits": 8
|
| 3200 |
+
},
|
| 3201 |
+
"vision_tower.blocks.22.attn.proj": {
|
| 3202 |
+
"group_size": 64,
|
| 3203 |
+
"bits": 8
|
| 3204 |
+
},
|
| 3205 |
+
"vision_tower.blocks.22.mlp.linear_fc1": {
|
| 3206 |
+
"group_size": 64,
|
| 3207 |
+
"bits": 8
|
| 3208 |
+
},
|
| 3209 |
+
"vision_tower.blocks.23.attn.qkv": {
|
| 3210 |
+
"group_size": 64,
|
| 3211 |
+
"bits": 8
|
| 3212 |
+
},
|
| 3213 |
+
"vision_tower.blocks.23.attn.proj": {
|
| 3214 |
+
"group_size": 64,
|
| 3215 |
+
"bits": 8
|
| 3216 |
+
},
|
| 3217 |
+
"vision_tower.blocks.23.mlp.linear_fc1": {
|
| 3218 |
+
"group_size": 64,
|
| 3219 |
+
"bits": 8
|
| 3220 |
+
},
|
| 3221 |
+
"vision_tower.blocks.24.attn.qkv": {
|
| 3222 |
+
"group_size": 64,
|
| 3223 |
+
"bits": 8
|
| 3224 |
+
},
|
| 3225 |
+
"vision_tower.blocks.24.attn.proj": {
|
| 3226 |
+
"group_size": 64,
|
| 3227 |
+
"bits": 8
|
| 3228 |
+
},
|
| 3229 |
+
"vision_tower.blocks.24.mlp.linear_fc1": {
|
| 3230 |
+
"group_size": 64,
|
| 3231 |
+
"bits": 8
|
| 3232 |
+
},
|
| 3233 |
+
"vision_tower.blocks.25.attn.qkv": {
|
| 3234 |
+
"group_size": 64,
|
| 3235 |
+
"bits": 8
|
| 3236 |
+
},
|
| 3237 |
+
"vision_tower.blocks.25.attn.proj": {
|
| 3238 |
+
"group_size": 64,
|
| 3239 |
+
"bits": 8
|
| 3240 |
+
},
|
| 3241 |
+
"vision_tower.blocks.25.mlp.linear_fc1": {
|
| 3242 |
+
"group_size": 64,
|
| 3243 |
+
"bits": 8
|
| 3244 |
+
},
|
| 3245 |
+
"vision_tower.blocks.26.attn.qkv": {
|
| 3246 |
+
"group_size": 64,
|
| 3247 |
+
"bits": 8
|
| 3248 |
+
},
|
| 3249 |
+
"vision_tower.blocks.26.attn.proj": {
|
| 3250 |
+
"group_size": 64,
|
| 3251 |
+
"bits": 8
|
| 3252 |
+
},
|
| 3253 |
+
"vision_tower.blocks.26.mlp.linear_fc1": {
|
| 3254 |
+
"group_size": 64,
|
| 3255 |
+
"bits": 8
|
| 3256 |
+
},
|
| 3257 |
+
"vision_tower.merger.linear_fc1": {
|
| 3258 |
+
"group_size": 64,
|
| 3259 |
+
"bits": 8
|
| 3260 |
+
},
|
| 3261 |
+
"vision_tower.merger.linear_fc2": {
|
| 3262 |
+
"group_size": 64,
|
| 3263 |
+
"bits": 8
|
| 3264 |
+
},
|
| 3265 |
"language_model.model.embed_tokens": {
|
| 3266 |
"bits": 4,
|
| 3267 |
"group_size": 16,
|
|
|
|
| 5823 |
"mode": "nvfp4"
|
| 5824 |
}
|
| 5825 |
},
|
| 5826 |
+
"temperature": 1.0,
|
| 5827 |
"text_config": {
|
| 5828 |
"attention_bias": false,
|
| 5829 |
"attention_dropout": 0.0,
|
|
|
|
| 5907 |
],
|
| 5908 |
"partial_rotary_factor": 0.25,
|
| 5909 |
"rope_theta": 10000000,
|
| 5910 |
+
"rope_type": "default"
|
| 5911 |
},
|
| 5912 |
"router_aux_loss_coef": 0.001,
|
| 5913 |
"shared_expert_intermediate_size": 512,
|
|
|
|
| 5916 |
"vocab_size": 248320
|
| 5917 |
},
|
| 5918 |
"tie_word_embeddings": false,
|
| 5919 |
+
"top_k": 20,
|
| 5920 |
+
"top_p": 0.95,
|
| 5921 |
"transformers_version": "4.57.1",
|
| 5922 |
"video_token_id": 248057,
|
| 5923 |
+
"vision_config": {
|
| 5924 |
+
"deepstack_visual_indexes": [],
|
| 5925 |
+
"depth": 27,
|
| 5926 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 5927 |
+
"hidden_size": 1152,
|
| 5928 |
+
"in_channels": 3,
|
| 5929 |
+
"initializer_range": 0.02,
|
| 5930 |
+
"intermediate_size": 4304,
|
| 5931 |
+
"model_type": "qwen3_5_moe",
|
| 5932 |
+
"num_heads": 16,
|
| 5933 |
+
"num_position_embeddings": 2304,
|
| 5934 |
+
"out_hidden_size": 2048,
|
| 5935 |
+
"patch_size": 16,
|
| 5936 |
+
"spatial_merge_size": 2,
|
| 5937 |
+
"temporal_patch_size": 2
|
| 5938 |
+
},
|
| 5939 |
"vision_end_token_id": 248054,
|
| 5940 |
"vision_start_token_id": 248053
|
| 5941 |
}
|
configuration.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"framework":"Pytorch","task":"visual-question-answering"}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68f508c37420e3550e8dc1bdc334ac2238c9cb650278e789f0aed51b17b8ac5f
|
| 3 |
+
size 5325419428
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3545ebe3e79898ab324d062284886a2ca379932042bfa9ef2aa6760b2eb3d5a6
|
| 3 |
+
size 5266917803
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca8cf2ff0bc89f809d792e92fb003f1bb29200ffc2b5a4767d80d82c260de0aa
|
| 3 |
+
size 5281968265
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:902a7c7b184238ed3e6adbc8d85e946d0718a8ef0da836e9ca25f26f005c3984
|
| 3 |
+
size 2059965085
|
model.safetensors.index.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
-
"total_parameters": 34660608768
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"language_model.lm_head.scales": "model-00004-of-00004.safetensors",
|
|
@@ -128,24 +127,24 @@
|
|
| 128 |
"language_model.model.layers.11.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 129 |
"language_model.model.layers.11.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 130 |
"language_model.model.layers.11.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 131 |
-
"language_model.model.layers.11.mlp.shared_expert.down_proj.scales": "model-
|
| 132 |
-
"language_model.model.layers.11.mlp.shared_expert.down_proj.weight": "model-
|
| 133 |
-
"language_model.model.layers.11.mlp.shared_expert.gate_proj.scales": "model-
|
| 134 |
-
"language_model.model.layers.11.mlp.shared_expert.gate_proj.weight": "model-
|
| 135 |
-
"language_model.model.layers.11.mlp.shared_expert.up_proj.scales": "model-
|
| 136 |
-
"language_model.model.layers.11.mlp.shared_expert.up_proj.weight": "model-
|
| 137 |
-
"language_model.model.layers.11.mlp.shared_expert_gate.biases": "model-
|
| 138 |
-
"language_model.model.layers.11.mlp.shared_expert_gate.scales": "model-
|
| 139 |
-
"language_model.model.layers.11.mlp.shared_expert_gate.weight": "model-
|
| 140 |
-
"language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model-
|
| 141 |
-
"language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model-
|
| 142 |
-
"language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-
|
| 143 |
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
|
| 144 |
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 145 |
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 146 |
-
"language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model-
|
| 147 |
-
"language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model-
|
| 148 |
-
"language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-
|
| 149 |
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
"language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 151 |
"language_model.model.layers.11.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
|
|
@@ -158,65 +157,65 @@
|
|
| 158 |
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 159 |
"language_model.model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 160 |
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
-
"language_model.model.layers.12.input_layernorm.weight": "model-
|
| 162 |
-
"language_model.model.layers.12.linear_attn.A_log": "model-
|
| 163 |
-
"language_model.model.layers.12.linear_attn.conv1d.weight": "model-
|
| 164 |
-
"language_model.model.layers.12.linear_attn.dt_bias": "model-
|
| 165 |
-
"language_model.model.layers.12.linear_attn.in_proj_a.biases": "model-
|
| 166 |
-
"language_model.model.layers.12.linear_attn.in_proj_a.scales": "model-
|
| 167 |
-
"language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-
|
| 168 |
-
"language_model.model.layers.12.linear_attn.in_proj_b.biases": "model-
|
| 169 |
-
"language_model.model.layers.12.linear_attn.in_proj_b.scales": "model-
|
| 170 |
-
"language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-
|
| 171 |
-
"language_model.model.layers.12.linear_attn.in_proj_qkv.scales": "model-
|
| 172 |
-
"language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-
|
| 173 |
-
"language_model.model.layers.12.linear_attn.in_proj_z.scales": "model-
|
| 174 |
-
"language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-
|
| 175 |
-
"language_model.model.layers.12.linear_attn.norm.weight": "model-
|
| 176 |
-
"language_model.model.layers.12.linear_attn.out_proj.scales": "model-
|
| 177 |
-
"language_model.model.layers.12.linear_attn.out_proj.weight": "model-
|
| 178 |
-
"language_model.model.layers.12.mlp.gate.biases": "model-
|
| 179 |
-
"language_model.model.layers.12.mlp.gate.scales": "model-
|
| 180 |
-
"language_model.model.layers.12.mlp.gate.weight": "model-
|
| 181 |
-
"language_model.model.layers.12.mlp.shared_expert.down_proj.scales": "model-
|
| 182 |
-
"language_model.model.layers.12.mlp.shared_expert.down_proj.weight": "model-
|
| 183 |
-
"language_model.model.layers.12.mlp.shared_expert.gate_proj.scales": "model-
|
| 184 |
-
"language_model.model.layers.12.mlp.shared_expert.gate_proj.weight": "model-
|
| 185 |
-
"language_model.model.layers.12.mlp.shared_expert.up_proj.scales": "model-
|
| 186 |
-
"language_model.model.layers.12.mlp.shared_expert.up_proj.weight": "model-
|
| 187 |
-
"language_model.model.layers.12.mlp.shared_expert_gate.biases": "model-
|
| 188 |
-
"language_model.model.layers.12.mlp.shared_expert_gate.scales": "model-
|
| 189 |
-
"language_model.model.layers.12.mlp.shared_expert_gate.weight": "model-
|
| 190 |
-
"language_model.model.layers.12.mlp.switch_mlp.down_proj.biases": "model-
|
| 191 |
-
"language_model.model.layers.12.mlp.switch_mlp.down_proj.scales": "model-
|
| 192 |
-
"language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-
|
| 193 |
-
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-
|
| 194 |
-
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-
|
| 195 |
-
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-
|
| 196 |
-
"language_model.model.layers.12.mlp.switch_mlp.up_proj.biases": "model-
|
| 197 |
-
"language_model.model.layers.12.mlp.switch_mlp.up_proj.scales": "model-
|
| 198 |
-
"language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-
|
| 199 |
-
"language_model.model.layers.12.post_attention_layernorm.weight": "model-
|
| 200 |
-
"language_model.model.layers.13.input_layernorm.weight": "model-
|
| 201 |
-
"language_model.model.layers.13.linear_attn.A_log": "model-
|
| 202 |
-
"language_model.model.layers.13.linear_attn.conv1d.weight": "model-
|
| 203 |
-
"language_model.model.layers.13.linear_attn.dt_bias": "model-
|
| 204 |
-
"language_model.model.layers.13.linear_attn.in_proj_a.biases": "model-
|
| 205 |
-
"language_model.model.layers.13.linear_attn.in_proj_a.scales": "model-
|
| 206 |
-
"language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-
|
| 207 |
-
"language_model.model.layers.13.linear_attn.in_proj_b.biases": "model-
|
| 208 |
-
"language_model.model.layers.13.linear_attn.in_proj_b.scales": "model-
|
| 209 |
-
"language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-
|
| 210 |
-
"language_model.model.layers.13.linear_attn.in_proj_qkv.scales": "model-
|
| 211 |
-
"language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-
|
| 212 |
-
"language_model.model.layers.13.linear_attn.in_proj_z.scales": "model-
|
| 213 |
-
"language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-
|
| 214 |
-
"language_model.model.layers.13.linear_attn.norm.weight": "model-
|
| 215 |
-
"language_model.model.layers.13.linear_attn.out_proj.scales": "model-
|
| 216 |
-
"language_model.model.layers.13.linear_attn.out_proj.weight": "model-
|
| 217 |
-
"language_model.model.layers.13.mlp.gate.biases": "model-
|
| 218 |
-
"language_model.model.layers.13.mlp.gate.scales": "model-
|
| 219 |
-
"language_model.model.layers.13.mlp.gate.weight": "model-
|
| 220 |
"language_model.model.layers.13.mlp.shared_expert.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 221 |
"language_model.model.layers.13.mlp.shared_expert.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 222 |
"language_model.model.layers.13.mlp.shared_expert.gate_proj.scales": "model-00002-of-00004.safetensors",
|
|
@@ -233,7 +232,7 @@
|
|
| 233 |
"language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 234 |
"language_model.model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 235 |
"language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 236 |
-
"language_model.model.layers.13.post_attention_layernorm.weight": "model-
|
| 237 |
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 238 |
"language_model.model.layers.14.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 239 |
"language_model.model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
|
@@ -659,43 +658,43 @@
|
|
| 659 |
"language_model.model.layers.24.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 660 |
"language_model.model.layers.24.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 661 |
"language_model.model.layers.24.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 662 |
-
"language_model.model.layers.24.mlp.shared_expert.down_proj.scales": "model-
|
| 663 |
-
"language_model.model.layers.24.mlp.shared_expert.down_proj.weight": "model-
|
| 664 |
-
"language_model.model.layers.24.mlp.shared_expert.gate_proj.scales": "model-
|
| 665 |
-
"language_model.model.layers.24.mlp.shared_expert.gate_proj.weight": "model-
|
| 666 |
-
"language_model.model.layers.24.mlp.shared_expert.up_proj.scales": "model-
|
| 667 |
-
"language_model.model.layers.24.mlp.shared_expert.up_proj.weight": "model-
|
| 668 |
-
"language_model.model.layers.24.mlp.shared_expert_gate.biases": "model-
|
| 669 |
-
"language_model.model.layers.24.mlp.shared_expert_gate.scales": "model-
|
| 670 |
-
"language_model.model.layers.24.mlp.shared_expert_gate.weight": "model-
|
| 671 |
-
"language_model.model.layers.24.mlp.switch_mlp.down_proj.biases": "model-
|
| 672 |
-
"language_model.model.layers.24.mlp.switch_mlp.down_proj.scales": "model-
|
| 673 |
-
"language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-
|
| 674 |
-
"language_model.model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-
|
| 675 |
-
"language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-
|
| 676 |
-
"language_model.model.layers.24.mlp.switch_mlp.up_proj.scales": "model-
|
| 677 |
-
"language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-
|
| 678 |
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 679 |
-
"language_model.model.layers.25.input_layernorm.weight": "model-
|
| 680 |
-
"language_model.model.layers.25.linear_attn.A_log": "model-
|
| 681 |
-
"language_model.model.layers.25.linear_attn.conv1d.weight": "model-
|
| 682 |
-
"language_model.model.layers.25.linear_attn.dt_bias": "model-
|
| 683 |
-
"language_model.model.layers.25.linear_attn.in_proj_a.biases": "model-
|
| 684 |
-
"language_model.model.layers.25.linear_attn.in_proj_a.scales": "model-
|
| 685 |
-
"language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-
|
| 686 |
-
"language_model.model.layers.25.linear_attn.in_proj_b.biases": "model-
|
| 687 |
-
"language_model.model.layers.25.linear_attn.in_proj_b.scales": "model-
|
| 688 |
-
"language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-
|
| 689 |
-
"language_model.model.layers.25.linear_attn.in_proj_qkv.scales": "model-
|
| 690 |
-
"language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-
|
| 691 |
-
"language_model.model.layers.25.linear_attn.in_proj_z.scales": "model-
|
| 692 |
-
"language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-
|
| 693 |
-
"language_model.model.layers.25.linear_attn.norm.weight": "model-
|
| 694 |
-
"language_model.model.layers.25.linear_attn.out_proj.scales": "model-
|
| 695 |
-
"language_model.model.layers.25.linear_attn.out_proj.weight": "model-
|
| 696 |
-
"language_model.model.layers.25.mlp.gate.biases": "model-
|
| 697 |
-
"language_model.model.layers.25.mlp.gate.scales": "model-
|
| 698 |
-
"language_model.model.layers.25.mlp.gate.weight": "model-
|
| 699 |
"language_model.model.layers.25.mlp.shared_expert.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 700 |
"language_model.model.layers.25.mlp.shared_expert.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 701 |
"language_model.model.layers.25.mlp.shared_expert.gate_proj.scales": "model-00003-of-00004.safetensors",
|
|
@@ -709,11 +708,11 @@
|
|
| 709 |
"language_model.model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00003-of-00004.safetensors",
|
| 710 |
"language_model.model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 711 |
"language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 712 |
-
"language_model.model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-
|
| 713 |
-
"language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-
|
| 714 |
"language_model.model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 715 |
-
"language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-
|
| 716 |
-
"language_model.model.layers.25.post_attention_layernorm.weight": "model-
|
| 717 |
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 718 |
"language_model.model.layers.26.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 719 |
"language_model.model.layers.26.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
|
@@ -1138,42 +1137,42 @@
|
|
| 1138 |
"language_model.model.layers.36.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 1139 |
"language_model.model.layers.36.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 1140 |
"language_model.model.layers.36.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 1141 |
-
"language_model.model.layers.36.mlp.shared_expert.down_proj.scales": "model-
|
| 1142 |
-
"language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-
|
| 1143 |
-
"language_model.model.layers.36.mlp.shared_expert.gate_proj.scales": "model-
|
| 1144 |
-
"language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-
|
| 1145 |
-
"language_model.model.layers.36.mlp.shared_expert.up_proj.scales": "model-
|
| 1146 |
-
"language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-
|
| 1147 |
-
"language_model.model.layers.36.mlp.shared_expert_gate.biases": "model-
|
| 1148 |
-
"language_model.model.layers.36.mlp.shared_expert_gate.scales": "model-
|
| 1149 |
-
"language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-
|
| 1150 |
-
"language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-
|
| 1151 |
-
"language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-
|
| 1152 |
-
"language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-
|
| 1153 |
-
"language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-
|
| 1154 |
-
"language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-
|
| 1155 |
-
"language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-
|
| 1156 |
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 1157 |
-
"language_model.model.layers.37.input_layernorm.weight": "model-
|
| 1158 |
-
"language_model.model.layers.37.linear_attn.A_log": "model-
|
| 1159 |
-
"language_model.model.layers.37.linear_attn.conv1d.weight": "model-
|
| 1160 |
-
"language_model.model.layers.37.linear_attn.dt_bias": "model-
|
| 1161 |
-
"language_model.model.layers.37.linear_attn.in_proj_a.biases": "model-
|
| 1162 |
-
"language_model.model.layers.37.linear_attn.in_proj_a.scales": "model-
|
| 1163 |
-
"language_model.model.layers.37.linear_attn.in_proj_a.weight": "model-
|
| 1164 |
-
"language_model.model.layers.37.linear_attn.in_proj_b.biases": "model-
|
| 1165 |
-
"language_model.model.layers.37.linear_attn.in_proj_b.scales": "model-
|
| 1166 |
-
"language_model.model.layers.37.linear_attn.in_proj_b.weight": "model-
|
| 1167 |
-
"language_model.model.layers.37.linear_attn.in_proj_qkv.scales": "model-
|
| 1168 |
-
"language_model.model.layers.37.linear_attn.in_proj_qkv.weight": "model-
|
| 1169 |
-
"language_model.model.layers.37.linear_attn.in_proj_z.scales": "model-
|
| 1170 |
-
"language_model.model.layers.37.linear_attn.in_proj_z.weight": "model-
|
| 1171 |
-
"language_model.model.layers.37.linear_attn.norm.weight": "model-
|
| 1172 |
-
"language_model.model.layers.37.linear_attn.out_proj.scales": "model-
|
| 1173 |
-
"language_model.model.layers.37.linear_attn.out_proj.weight": "model-
|
| 1174 |
-
"language_model.model.layers.37.mlp.gate.biases": "model-
|
| 1175 |
-
"language_model.model.layers.37.mlp.gate.scales": "model-
|
| 1176 |
-
"language_model.model.layers.37.mlp.gate.weight": "model-
|
| 1177 |
"language_model.model.layers.37.mlp.shared_expert.down_proj.scales": "model-00004-of-00004.safetensors",
|
| 1178 |
"language_model.model.layers.37.mlp.shared_expert.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 1179 |
"language_model.model.layers.37.mlp.shared_expert.gate_proj.scales": "model-00004-of-00004.safetensors",
|
|
@@ -1185,14 +1184,14 @@
|
|
| 1185 |
"language_model.model.layers.37.mlp.shared_expert_gate.weight": "model-00004-of-00004.safetensors",
|
| 1186 |
"language_model.model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00004-of-00004.safetensors",
|
| 1187 |
"language_model.model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00004-of-00004.safetensors",
|
| 1188 |
-
"language_model.model.layers.37.mlp.switch_mlp.down_proj.weight": "model-
|
| 1189 |
-
"language_model.model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-
|
| 1190 |
-
"language_model.model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-
|
| 1191 |
-
"language_model.model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-
|
| 1192 |
-
"language_model.model.layers.37.mlp.switch_mlp.up_proj.biases": "model-
|
| 1193 |
-
"language_model.model.layers.37.mlp.switch_mlp.up_proj.scales": "model-
|
| 1194 |
-
"language_model.model.layers.37.mlp.switch_mlp.up_proj.weight": "model-
|
| 1195 |
-
"language_model.model.layers.37.post_attention_layernorm.weight": "model-
|
| 1196 |
"language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 1197 |
"language_model.model.layers.38.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 1198 |
"language_model.model.layers.38.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
|
@@ -1486,6 +1485,507 @@
|
|
| 1486 |
"language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 1487 |
"language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 1488 |
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 1489 |
-
"language_model.model.norm.weight": "model-00004-of-00004.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1490 |
}
|
| 1491 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 17934015072
|
|
|
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.lm_head.scales": "model-00004-of-00004.safetensors",
|
|
|
|
| 127 |
"language_model.model.layers.11.mlp.gate.biases": "model-00001-of-00004.safetensors",
|
| 128 |
"language_model.model.layers.11.mlp.gate.scales": "model-00001-of-00004.safetensors",
|
| 129 |
"language_model.model.layers.11.mlp.gate.weight": "model-00001-of-00004.safetensors",
|
| 130 |
+
"language_model.model.layers.11.mlp.shared_expert.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 131 |
+
"language_model.model.layers.11.mlp.shared_expert.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"language_model.model.layers.11.mlp.shared_expert.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 133 |
+
"language_model.model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"language_model.model.layers.11.mlp.shared_expert.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 135 |
+
"language_model.model.layers.11.mlp.shared_expert.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"language_model.model.layers.11.mlp.shared_expert_gate.biases": "model-00002-of-00004.safetensors",
|
| 137 |
+
"language_model.model.layers.11.mlp.shared_expert_gate.scales": "model-00002-of-00004.safetensors",
|
| 138 |
+
"language_model.model.layers.11.mlp.shared_expert_gate.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00002-of-00004.safetensors",
|
| 140 |
+
"language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 141 |
+
"language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 142 |
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
|
| 143 |
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
|
| 144 |
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00002-of-00004.safetensors",
|
| 146 |
+
"language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 147 |
+
"language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 148 |
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 149 |
"language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
"language_model.model.layers.11.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
|
|
|
|
| 157 |
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 158 |
"language_model.model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
|
| 159 |
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"language_model.model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 162 |
+
"language_model.model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"language_model.model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 164 |
+
"language_model.model.layers.12.linear_attn.in_proj_a.biases": "model-00002-of-00004.safetensors",
|
| 165 |
+
"language_model.model.layers.12.linear_attn.in_proj_a.scales": "model-00002-of-00004.safetensors",
|
| 166 |
+
"language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"language_model.model.layers.12.linear_attn.in_proj_b.biases": "model-00002-of-00004.safetensors",
|
| 168 |
+
"language_model.model.layers.12.linear_attn.in_proj_b.scales": "model-00002-of-00004.safetensors",
|
| 169 |
+
"language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"language_model.model.layers.12.linear_attn.in_proj_qkv.scales": "model-00002-of-00004.safetensors",
|
| 171 |
+
"language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"language_model.model.layers.12.linear_attn.in_proj_z.scales": "model-00002-of-00004.safetensors",
|
| 173 |
+
"language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"language_model.model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 175 |
+
"language_model.model.layers.12.linear_attn.out_proj.scales": "model-00002-of-00004.safetensors",
|
| 176 |
+
"language_model.model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 177 |
+
"language_model.model.layers.12.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 178 |
+
"language_model.model.layers.12.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 179 |
+
"language_model.model.layers.12.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"language_model.model.layers.12.mlp.shared_expert.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 181 |
+
"language_model.model.layers.12.mlp.shared_expert.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"language_model.model.layers.12.mlp.shared_expert.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 183 |
+
"language_model.model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"language_model.model.layers.12.mlp.shared_expert.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 185 |
+
"language_model.model.layers.12.mlp.shared_expert.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 186 |
+
"language_model.model.layers.12.mlp.shared_expert_gate.biases": "model-00002-of-00004.safetensors",
|
| 187 |
+
"language_model.model.layers.12.mlp.shared_expert_gate.scales": "model-00002-of-00004.safetensors",
|
| 188 |
+
"language_model.model.layers.12.mlp.shared_expert_gate.weight": "model-00002-of-00004.safetensors",
|
| 189 |
+
"language_model.model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00002-of-00004.safetensors",
|
| 190 |
+
"language_model.model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 191 |
+
"language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 192 |
+
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
|
| 193 |
+
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
|
| 194 |
+
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 195 |
+
"language_model.model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00002-of-00004.safetensors",
|
| 196 |
+
"language_model.model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 197 |
+
"language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 198 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 199 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 200 |
+
"language_model.model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 201 |
+
"language_model.model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 202 |
+
"language_model.model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 203 |
+
"language_model.model.layers.13.linear_attn.in_proj_a.biases": "model-00002-of-00004.safetensors",
|
| 204 |
+
"language_model.model.layers.13.linear_attn.in_proj_a.scales": "model-00002-of-00004.safetensors",
|
| 205 |
+
"language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 206 |
+
"language_model.model.layers.13.linear_attn.in_proj_b.biases": "model-00002-of-00004.safetensors",
|
| 207 |
+
"language_model.model.layers.13.linear_attn.in_proj_b.scales": "model-00002-of-00004.safetensors",
|
| 208 |
+
"language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 209 |
+
"language_model.model.layers.13.linear_attn.in_proj_qkv.scales": "model-00002-of-00004.safetensors",
|
| 210 |
+
"language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 211 |
+
"language_model.model.layers.13.linear_attn.in_proj_z.scales": "model-00002-of-00004.safetensors",
|
| 212 |
+
"language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 213 |
+
"language_model.model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 214 |
+
"language_model.model.layers.13.linear_attn.out_proj.scales": "model-00002-of-00004.safetensors",
|
| 215 |
+
"language_model.model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 216 |
+
"language_model.model.layers.13.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 217 |
+
"language_model.model.layers.13.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 218 |
+
"language_model.model.layers.13.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 219 |
"language_model.model.layers.13.mlp.shared_expert.down_proj.scales": "model-00002-of-00004.safetensors",
|
| 220 |
"language_model.model.layers.13.mlp.shared_expert.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 221 |
"language_model.model.layers.13.mlp.shared_expert.gate_proj.scales": "model-00002-of-00004.safetensors",
|
|
|
|
| 232 |
"language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 233 |
"language_model.model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
|
| 234 |
"language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 235 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 236 |
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 237 |
"language_model.model.layers.14.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 238 |
"language_model.model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 658 |
"language_model.model.layers.24.mlp.gate.biases": "model-00002-of-00004.safetensors",
|
| 659 |
"language_model.model.layers.24.mlp.gate.scales": "model-00002-of-00004.safetensors",
|
| 660 |
"language_model.model.layers.24.mlp.gate.weight": "model-00002-of-00004.safetensors",
|
| 661 |
+
"language_model.model.layers.24.mlp.shared_expert.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 662 |
+
"language_model.model.layers.24.mlp.shared_expert.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 663 |
+
"language_model.model.layers.24.mlp.shared_expert.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 664 |
+
"language_model.model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 665 |
+
"language_model.model.layers.24.mlp.shared_expert.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 666 |
+
"language_model.model.layers.24.mlp.shared_expert.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 667 |
+
"language_model.model.layers.24.mlp.shared_expert_gate.biases": "model-00003-of-00004.safetensors",
|
| 668 |
+
"language_model.model.layers.24.mlp.shared_expert_gate.scales": "model-00003-of-00004.safetensors",
|
| 669 |
+
"language_model.model.layers.24.mlp.shared_expert_gate.weight": "model-00003-of-00004.safetensors",
|
| 670 |
+
"language_model.model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00003-of-00004.safetensors",
|
| 671 |
+
"language_model.model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 672 |
+
"language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 673 |
+
"language_model.model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 674 |
+
"language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 675 |
+
"language_model.model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 676 |
+
"language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 677 |
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 678 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 679 |
+
"language_model.model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 680 |
+
"language_model.model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 681 |
+
"language_model.model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 682 |
+
"language_model.model.layers.25.linear_attn.in_proj_a.biases": "model-00003-of-00004.safetensors",
|
| 683 |
+
"language_model.model.layers.25.linear_attn.in_proj_a.scales": "model-00003-of-00004.safetensors",
|
| 684 |
+
"language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 685 |
+
"language_model.model.layers.25.linear_attn.in_proj_b.biases": "model-00003-of-00004.safetensors",
|
| 686 |
+
"language_model.model.layers.25.linear_attn.in_proj_b.scales": "model-00003-of-00004.safetensors",
|
| 687 |
+
"language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 688 |
+
"language_model.model.layers.25.linear_attn.in_proj_qkv.scales": "model-00003-of-00004.safetensors",
|
| 689 |
+
"language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 690 |
+
"language_model.model.layers.25.linear_attn.in_proj_z.scales": "model-00003-of-00004.safetensors",
|
| 691 |
+
"language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 692 |
+
"language_model.model.layers.25.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 693 |
+
"language_model.model.layers.25.linear_attn.out_proj.scales": "model-00003-of-00004.safetensors",
|
| 694 |
+
"language_model.model.layers.25.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 695 |
+
"language_model.model.layers.25.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 696 |
+
"language_model.model.layers.25.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 697 |
+
"language_model.model.layers.25.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 698 |
"language_model.model.layers.25.mlp.shared_expert.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 699 |
"language_model.model.layers.25.mlp.shared_expert.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 700 |
"language_model.model.layers.25.mlp.shared_expert.gate_proj.scales": "model-00003-of-00004.safetensors",
|
|
|
|
| 708 |
"language_model.model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00003-of-00004.safetensors",
|
| 709 |
"language_model.model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
|
| 710 |
"language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 711 |
+
"language_model.model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
|
| 712 |
+
"language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 713 |
"language_model.model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
|
| 714 |
+
"language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 715 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 716 |
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 717 |
"language_model.model.layers.26.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 718 |
"language_model.model.layers.26.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 1137 |
"language_model.model.layers.36.mlp.gate.biases": "model-00003-of-00004.safetensors",
|
| 1138 |
"language_model.model.layers.36.mlp.gate.scales": "model-00003-of-00004.safetensors",
|
| 1139 |
"language_model.model.layers.36.mlp.gate.weight": "model-00003-of-00004.safetensors",
|
| 1140 |
+
"language_model.model.layers.36.mlp.shared_expert.down_proj.scales": "model-00004-of-00004.safetensors",
|
| 1141 |
+
"language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 1142 |
+
"language_model.model.layers.36.mlp.shared_expert.gate_proj.scales": "model-00004-of-00004.safetensors",
|
| 1143 |
+
"language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 1144 |
+
"language_model.model.layers.36.mlp.shared_expert.up_proj.scales": "model-00004-of-00004.safetensors",
|
| 1145 |
+
"language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 1146 |
+
"language_model.model.layers.36.mlp.shared_expert_gate.biases": "model-00004-of-00004.safetensors",
|
| 1147 |
+
"language_model.model.layers.36.mlp.shared_expert_gate.scales": "model-00004-of-00004.safetensors",
|
| 1148 |
+
"language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-00004-of-00004.safetensors",
|
| 1149 |
+
"language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00004-of-00004.safetensors",
|
| 1150 |
+
"language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 1151 |
+
"language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
|
| 1152 |
+
"language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 1153 |
+
"language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00004-of-00004.safetensors",
|
| 1154 |
+
"language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 1155 |
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 1156 |
+
"language_model.model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 1157 |
+
"language_model.model.layers.37.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 1158 |
+
"language_model.model.layers.37.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 1159 |
+
"language_model.model.layers.37.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 1160 |
+
"language_model.model.layers.37.linear_attn.in_proj_a.biases": "model-00004-of-00004.safetensors",
|
| 1161 |
+
"language_model.model.layers.37.linear_attn.in_proj_a.scales": "model-00004-of-00004.safetensors",
|
| 1162 |
+
"language_model.model.layers.37.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 1163 |
+
"language_model.model.layers.37.linear_attn.in_proj_b.biases": "model-00004-of-00004.safetensors",
|
| 1164 |
+
"language_model.model.layers.37.linear_attn.in_proj_b.scales": "model-00004-of-00004.safetensors",
|
| 1165 |
+
"language_model.model.layers.37.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 1166 |
+
"language_model.model.layers.37.linear_attn.in_proj_qkv.scales": "model-00004-of-00004.safetensors",
|
| 1167 |
+
"language_model.model.layers.37.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 1168 |
+
"language_model.model.layers.37.linear_attn.in_proj_z.scales": "model-00004-of-00004.safetensors",
|
| 1169 |
+
"language_model.model.layers.37.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 1170 |
+
"language_model.model.layers.37.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 1171 |
+
"language_model.model.layers.37.linear_attn.out_proj.scales": "model-00004-of-00004.safetensors",
|
| 1172 |
+
"language_model.model.layers.37.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 1173 |
+
"language_model.model.layers.37.mlp.gate.biases": "model-00004-of-00004.safetensors",
|
| 1174 |
+
"language_model.model.layers.37.mlp.gate.scales": "model-00004-of-00004.safetensors",
|
| 1175 |
+
"language_model.model.layers.37.mlp.gate.weight": "model-00004-of-00004.safetensors",
|
| 1176 |
"language_model.model.layers.37.mlp.shared_expert.down_proj.scales": "model-00004-of-00004.safetensors",
|
| 1177 |
"language_model.model.layers.37.mlp.shared_expert.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 1178 |
"language_model.model.layers.37.mlp.shared_expert.gate_proj.scales": "model-00004-of-00004.safetensors",
|
|
|
|
| 1184 |
"language_model.model.layers.37.mlp.shared_expert_gate.weight": "model-00004-of-00004.safetensors",
|
| 1185 |
"language_model.model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00004-of-00004.safetensors",
|
| 1186 |
"language_model.model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00004-of-00004.safetensors",
|
| 1187 |
+
"language_model.model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 1188 |
+
"language_model.model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
|
| 1189 |
+
"language_model.model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
|
| 1190 |
+
"language_model.model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 1191 |
+
"language_model.model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00004-of-00004.safetensors",
|
| 1192 |
+
"language_model.model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00004-of-00004.safetensors",
|
| 1193 |
+
"language_model.model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 1194 |
+
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 1195 |
"language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 1196 |
"language_model.model.layers.38.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 1197 |
"language_model.model.layers.38.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
|
|
|
| 1485 |
"language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
|
| 1486 |
"language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 1487 |
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 1488 |
+
"language_model.model.norm.weight": "model-00004-of-00004.safetensors",
|
| 1489 |
+
"vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1490 |
+
"vision_tower.blocks.0.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1491 |
+
"vision_tower.blocks.0.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1492 |
+
"vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1493 |
+
"vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1494 |
+
"vision_tower.blocks.0.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1495 |
+
"vision_tower.blocks.0.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1496 |
+
"vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1497 |
+
"vision_tower.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1498 |
+
"vision_tower.blocks.0.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1499 |
+
"vision_tower.blocks.0.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1500 |
+
"vision_tower.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1501 |
+
"vision_tower.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1502 |
+
"vision_tower.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1503 |
+
"vision_tower.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1504 |
+
"vision_tower.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1505 |
+
"vision_tower.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1506 |
+
"vision_tower.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1507 |
+
"vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1508 |
+
"vision_tower.blocks.1.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1509 |
+
"vision_tower.blocks.1.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1510 |
+
"vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1511 |
+
"vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1512 |
+
"vision_tower.blocks.1.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1513 |
+
"vision_tower.blocks.1.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1514 |
+
"vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1515 |
+
"vision_tower.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1516 |
+
"vision_tower.blocks.1.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1517 |
+
"vision_tower.blocks.1.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1518 |
+
"vision_tower.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1519 |
+
"vision_tower.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1520 |
+
"vision_tower.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1521 |
+
"vision_tower.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1522 |
+
"vision_tower.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1523 |
+
"vision_tower.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1524 |
+
"vision_tower.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1525 |
+
"vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1526 |
+
"vision_tower.blocks.10.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1527 |
+
"vision_tower.blocks.10.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1528 |
+
"vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1529 |
+
"vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1530 |
+
"vision_tower.blocks.10.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1531 |
+
"vision_tower.blocks.10.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1532 |
+
"vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1533 |
+
"vision_tower.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1534 |
+
"vision_tower.blocks.10.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1535 |
+
"vision_tower.blocks.10.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1536 |
+
"vision_tower.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1537 |
+
"vision_tower.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1538 |
+
"vision_tower.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1539 |
+
"vision_tower.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1540 |
+
"vision_tower.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1541 |
+
"vision_tower.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1542 |
+
"vision_tower.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1543 |
+
"vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1544 |
+
"vision_tower.blocks.11.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1545 |
+
"vision_tower.blocks.11.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1546 |
+
"vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1547 |
+
"vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1548 |
+
"vision_tower.blocks.11.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1549 |
+
"vision_tower.blocks.11.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1550 |
+
"vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1551 |
+
"vision_tower.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1552 |
+
"vision_tower.blocks.11.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1553 |
+
"vision_tower.blocks.11.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1554 |
+
"vision_tower.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1555 |
+
"vision_tower.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1556 |
+
"vision_tower.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1557 |
+
"vision_tower.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1558 |
+
"vision_tower.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1559 |
+
"vision_tower.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1560 |
+
"vision_tower.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1561 |
+
"vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1562 |
+
"vision_tower.blocks.12.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1563 |
+
"vision_tower.blocks.12.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1564 |
+
"vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1565 |
+
"vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1566 |
+
"vision_tower.blocks.12.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1567 |
+
"vision_tower.blocks.12.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1568 |
+
"vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1569 |
+
"vision_tower.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1570 |
+
"vision_tower.blocks.12.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1571 |
+
"vision_tower.blocks.12.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1572 |
+
"vision_tower.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1573 |
+
"vision_tower.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1574 |
+
"vision_tower.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1575 |
+
"vision_tower.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1576 |
+
"vision_tower.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1577 |
+
"vision_tower.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1578 |
+
"vision_tower.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1579 |
+
"vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1580 |
+
"vision_tower.blocks.13.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1581 |
+
"vision_tower.blocks.13.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1582 |
+
"vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1583 |
+
"vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1584 |
+
"vision_tower.blocks.13.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1585 |
+
"vision_tower.blocks.13.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1586 |
+
"vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1587 |
+
"vision_tower.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1588 |
+
"vision_tower.blocks.13.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1589 |
+
"vision_tower.blocks.13.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1590 |
+
"vision_tower.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1591 |
+
"vision_tower.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1592 |
+
"vision_tower.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1593 |
+
"vision_tower.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1594 |
+
"vision_tower.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1595 |
+
"vision_tower.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1596 |
+
"vision_tower.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1597 |
+
"vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1598 |
+
"vision_tower.blocks.14.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1599 |
+
"vision_tower.blocks.14.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1600 |
+
"vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1601 |
+
"vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1602 |
+
"vision_tower.blocks.14.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1603 |
+
"vision_tower.blocks.14.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1604 |
+
"vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1605 |
+
"vision_tower.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1606 |
+
"vision_tower.blocks.14.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1607 |
+
"vision_tower.blocks.14.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1608 |
+
"vision_tower.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1609 |
+
"vision_tower.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1610 |
+
"vision_tower.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1611 |
+
"vision_tower.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1612 |
+
"vision_tower.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1613 |
+
"vision_tower.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1614 |
+
"vision_tower.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1615 |
+
"vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1616 |
+
"vision_tower.blocks.15.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1617 |
+
"vision_tower.blocks.15.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1618 |
+
"vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1619 |
+
"vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1620 |
+
"vision_tower.blocks.15.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1621 |
+
"vision_tower.blocks.15.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1622 |
+
"vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1623 |
+
"vision_tower.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1624 |
+
"vision_tower.blocks.15.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1625 |
+
"vision_tower.blocks.15.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1626 |
+
"vision_tower.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1627 |
+
"vision_tower.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1628 |
+
"vision_tower.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1629 |
+
"vision_tower.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1630 |
+
"vision_tower.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1631 |
+
"vision_tower.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1632 |
+
"vision_tower.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1633 |
+
"vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1634 |
+
"vision_tower.blocks.16.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1635 |
+
"vision_tower.blocks.16.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1636 |
+
"vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1637 |
+
"vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1638 |
+
"vision_tower.blocks.16.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1639 |
+
"vision_tower.blocks.16.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1640 |
+
"vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1641 |
+
"vision_tower.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1642 |
+
"vision_tower.blocks.16.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1643 |
+
"vision_tower.blocks.16.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1644 |
+
"vision_tower.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1645 |
+
"vision_tower.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1646 |
+
"vision_tower.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1647 |
+
"vision_tower.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1648 |
+
"vision_tower.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1649 |
+
"vision_tower.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1650 |
+
"vision_tower.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1651 |
+
"vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1652 |
+
"vision_tower.blocks.17.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1653 |
+
"vision_tower.blocks.17.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1654 |
+
"vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1655 |
+
"vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1656 |
+
"vision_tower.blocks.17.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1657 |
+
"vision_tower.blocks.17.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1658 |
+
"vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1659 |
+
"vision_tower.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1660 |
+
"vision_tower.blocks.17.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1661 |
+
"vision_tower.blocks.17.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1662 |
+
"vision_tower.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1663 |
+
"vision_tower.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1664 |
+
"vision_tower.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1665 |
+
"vision_tower.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1666 |
+
"vision_tower.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1667 |
+
"vision_tower.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1668 |
+
"vision_tower.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1669 |
+
"vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1670 |
+
"vision_tower.blocks.18.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1671 |
+
"vision_tower.blocks.18.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1672 |
+
"vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1673 |
+
"vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1674 |
+
"vision_tower.blocks.18.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1675 |
+
"vision_tower.blocks.18.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1676 |
+
"vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1677 |
+
"vision_tower.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1678 |
+
"vision_tower.blocks.18.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1679 |
+
"vision_tower.blocks.18.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1680 |
+
"vision_tower.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1681 |
+
"vision_tower.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1682 |
+
"vision_tower.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1683 |
+
"vision_tower.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1684 |
+
"vision_tower.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1685 |
+
"vision_tower.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1686 |
+
"vision_tower.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1687 |
+
"vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1688 |
+
"vision_tower.blocks.19.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1689 |
+
"vision_tower.blocks.19.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1690 |
+
"vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1691 |
+
"vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1692 |
+
"vision_tower.blocks.19.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1693 |
+
"vision_tower.blocks.19.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1694 |
+
"vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1695 |
+
"vision_tower.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1696 |
+
"vision_tower.blocks.19.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1697 |
+
"vision_tower.blocks.19.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1698 |
+
"vision_tower.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1699 |
+
"vision_tower.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1700 |
+
"vision_tower.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1701 |
+
"vision_tower.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1702 |
+
"vision_tower.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1703 |
+
"vision_tower.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1704 |
+
"vision_tower.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1705 |
+
"vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1706 |
+
"vision_tower.blocks.2.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1707 |
+
"vision_tower.blocks.2.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1708 |
+
"vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1709 |
+
"vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1710 |
+
"vision_tower.blocks.2.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1711 |
+
"vision_tower.blocks.2.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1712 |
+
"vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1713 |
+
"vision_tower.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1714 |
+
"vision_tower.blocks.2.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1715 |
+
"vision_tower.blocks.2.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1716 |
+
"vision_tower.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1717 |
+
"vision_tower.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1718 |
+
"vision_tower.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1719 |
+
"vision_tower.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1720 |
+
"vision_tower.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1721 |
+
"vision_tower.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1722 |
+
"vision_tower.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1723 |
+
"vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1724 |
+
"vision_tower.blocks.20.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1725 |
+
"vision_tower.blocks.20.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1726 |
+
"vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1727 |
+
"vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1728 |
+
"vision_tower.blocks.20.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1729 |
+
"vision_tower.blocks.20.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1730 |
+
"vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1731 |
+
"vision_tower.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1732 |
+
"vision_tower.blocks.20.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1733 |
+
"vision_tower.blocks.20.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1734 |
+
"vision_tower.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1735 |
+
"vision_tower.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1736 |
+
"vision_tower.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1737 |
+
"vision_tower.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1738 |
+
"vision_tower.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1739 |
+
"vision_tower.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1740 |
+
"vision_tower.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1741 |
+
"vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1742 |
+
"vision_tower.blocks.21.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1743 |
+
"vision_tower.blocks.21.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1744 |
+
"vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1745 |
+
"vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1746 |
+
"vision_tower.blocks.21.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1747 |
+
"vision_tower.blocks.21.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1748 |
+
"vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1749 |
+
"vision_tower.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1750 |
+
"vision_tower.blocks.21.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1751 |
+
"vision_tower.blocks.21.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1752 |
+
"vision_tower.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1753 |
+
"vision_tower.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1754 |
+
"vision_tower.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1755 |
+
"vision_tower.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1756 |
+
"vision_tower.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1757 |
+
"vision_tower.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1758 |
+
"vision_tower.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1759 |
+
"vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1760 |
+
"vision_tower.blocks.22.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1761 |
+
"vision_tower.blocks.22.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1762 |
+
"vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1763 |
+
"vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1764 |
+
"vision_tower.blocks.22.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1765 |
+
"vision_tower.blocks.22.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1766 |
+
"vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1767 |
+
"vision_tower.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1768 |
+
"vision_tower.blocks.22.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1769 |
+
"vision_tower.blocks.22.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1770 |
+
"vision_tower.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1771 |
+
"vision_tower.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1772 |
+
"vision_tower.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1773 |
+
"vision_tower.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1774 |
+
"vision_tower.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1775 |
+
"vision_tower.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1776 |
+
"vision_tower.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1777 |
+
"vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1778 |
+
"vision_tower.blocks.23.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1779 |
+
"vision_tower.blocks.23.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1780 |
+
"vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1781 |
+
"vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1782 |
+
"vision_tower.blocks.23.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1783 |
+
"vision_tower.blocks.23.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1784 |
+
"vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1785 |
+
"vision_tower.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1786 |
+
"vision_tower.blocks.23.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1787 |
+
"vision_tower.blocks.23.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1788 |
+
"vision_tower.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1789 |
+
"vision_tower.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1790 |
+
"vision_tower.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1791 |
+
"vision_tower.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1792 |
+
"vision_tower.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1793 |
+
"vision_tower.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1794 |
+
"vision_tower.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1795 |
+
"vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1796 |
+
"vision_tower.blocks.24.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1797 |
+
"vision_tower.blocks.24.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1798 |
+
"vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1799 |
+
"vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1800 |
+
"vision_tower.blocks.24.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1801 |
+
"vision_tower.blocks.24.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1802 |
+
"vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1803 |
+
"vision_tower.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1804 |
+
"vision_tower.blocks.24.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1805 |
+
"vision_tower.blocks.24.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1806 |
+
"vision_tower.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1807 |
+
"vision_tower.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1808 |
+
"vision_tower.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1809 |
+
"vision_tower.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1810 |
+
"vision_tower.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1811 |
+
"vision_tower.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1812 |
+
"vision_tower.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1813 |
+
"vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1814 |
+
"vision_tower.blocks.25.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1815 |
+
"vision_tower.blocks.25.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1816 |
+
"vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1817 |
+
"vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1818 |
+
"vision_tower.blocks.25.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1819 |
+
"vision_tower.blocks.25.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1820 |
+
"vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1821 |
+
"vision_tower.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1822 |
+
"vision_tower.blocks.25.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1823 |
+
"vision_tower.blocks.25.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1824 |
+
"vision_tower.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1825 |
+
"vision_tower.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1826 |
+
"vision_tower.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1827 |
+
"vision_tower.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1828 |
+
"vision_tower.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1829 |
+
"vision_tower.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1830 |
+
"vision_tower.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1831 |
+
"vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1832 |
+
"vision_tower.blocks.26.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1833 |
+
"vision_tower.blocks.26.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1834 |
+
"vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1835 |
+
"vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1836 |
+
"vision_tower.blocks.26.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1837 |
+
"vision_tower.blocks.26.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1838 |
+
"vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1839 |
+
"vision_tower.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1840 |
+
"vision_tower.blocks.26.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1841 |
+
"vision_tower.blocks.26.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1842 |
+
"vision_tower.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1843 |
+
"vision_tower.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1844 |
+
"vision_tower.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1845 |
+
"vision_tower.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1846 |
+
"vision_tower.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1847 |
+
"vision_tower.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1848 |
+
"vision_tower.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1849 |
+
"vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1850 |
+
"vision_tower.blocks.3.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1851 |
+
"vision_tower.blocks.3.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1852 |
+
"vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1853 |
+
"vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1854 |
+
"vision_tower.blocks.3.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1855 |
+
"vision_tower.blocks.3.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1856 |
+
"vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1857 |
+
"vision_tower.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1858 |
+
"vision_tower.blocks.3.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1859 |
+
"vision_tower.blocks.3.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1860 |
+
"vision_tower.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1861 |
+
"vision_tower.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1862 |
+
"vision_tower.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1863 |
+
"vision_tower.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1864 |
+
"vision_tower.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1865 |
+
"vision_tower.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1866 |
+
"vision_tower.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1867 |
+
"vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1868 |
+
"vision_tower.blocks.4.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1869 |
+
"vision_tower.blocks.4.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1870 |
+
"vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1871 |
+
"vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1872 |
+
"vision_tower.blocks.4.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1873 |
+
"vision_tower.blocks.4.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1874 |
+
"vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1875 |
+
"vision_tower.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1876 |
+
"vision_tower.blocks.4.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1877 |
+
"vision_tower.blocks.4.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1878 |
+
"vision_tower.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1879 |
+
"vision_tower.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1880 |
+
"vision_tower.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1881 |
+
"vision_tower.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1882 |
+
"vision_tower.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1883 |
+
"vision_tower.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1884 |
+
"vision_tower.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1885 |
+
"vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1886 |
+
"vision_tower.blocks.5.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1887 |
+
"vision_tower.blocks.5.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1888 |
+
"vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1889 |
+
"vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1890 |
+
"vision_tower.blocks.5.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1891 |
+
"vision_tower.blocks.5.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1892 |
+
"vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1893 |
+
"vision_tower.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1894 |
+
"vision_tower.blocks.5.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1895 |
+
"vision_tower.blocks.5.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1896 |
+
"vision_tower.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1897 |
+
"vision_tower.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1898 |
+
"vision_tower.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1899 |
+
"vision_tower.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1900 |
+
"vision_tower.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1901 |
+
"vision_tower.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1902 |
+
"vision_tower.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1903 |
+
"vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1904 |
+
"vision_tower.blocks.6.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1905 |
+
"vision_tower.blocks.6.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1906 |
+
"vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1907 |
+
"vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1908 |
+
"vision_tower.blocks.6.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1909 |
+
"vision_tower.blocks.6.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1910 |
+
"vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1911 |
+
"vision_tower.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1912 |
+
"vision_tower.blocks.6.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1913 |
+
"vision_tower.blocks.6.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1914 |
+
"vision_tower.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1915 |
+
"vision_tower.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1916 |
+
"vision_tower.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1917 |
+
"vision_tower.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1918 |
+
"vision_tower.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1919 |
+
"vision_tower.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1920 |
+
"vision_tower.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1921 |
+
"vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1922 |
+
"vision_tower.blocks.7.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1923 |
+
"vision_tower.blocks.7.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1924 |
+
"vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1925 |
+
"vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1926 |
+
"vision_tower.blocks.7.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1927 |
+
"vision_tower.blocks.7.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1928 |
+
"vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1929 |
+
"vision_tower.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1930 |
+
"vision_tower.blocks.7.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1931 |
+
"vision_tower.blocks.7.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1932 |
+
"vision_tower.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1933 |
+
"vision_tower.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1934 |
+
"vision_tower.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1935 |
+
"vision_tower.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1936 |
+
"vision_tower.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1937 |
+
"vision_tower.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1938 |
+
"vision_tower.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1939 |
+
"vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1940 |
+
"vision_tower.blocks.8.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1941 |
+
"vision_tower.blocks.8.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1942 |
+
"vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1943 |
+
"vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1944 |
+
"vision_tower.blocks.8.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1945 |
+
"vision_tower.blocks.8.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1946 |
+
"vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1947 |
+
"vision_tower.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1948 |
+
"vision_tower.blocks.8.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1949 |
+
"vision_tower.blocks.8.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1950 |
+
"vision_tower.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1951 |
+
"vision_tower.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1952 |
+
"vision_tower.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1953 |
+
"vision_tower.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1954 |
+
"vision_tower.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1955 |
+
"vision_tower.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1956 |
+
"vision_tower.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1957 |
+
"vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 1958 |
+
"vision_tower.blocks.9.attn.proj.biases": "model-00001-of-00004.safetensors",
|
| 1959 |
+
"vision_tower.blocks.9.attn.proj.scales": "model-00001-of-00004.safetensors",
|
| 1960 |
+
"vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 1961 |
+
"vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 1962 |
+
"vision_tower.blocks.9.attn.qkv.biases": "model-00001-of-00004.safetensors",
|
| 1963 |
+
"vision_tower.blocks.9.attn.qkv.scales": "model-00001-of-00004.safetensors",
|
| 1964 |
+
"vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 1965 |
+
"vision_tower.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1966 |
+
"vision_tower.blocks.9.mlp.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1967 |
+
"vision_tower.blocks.9.mlp.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1968 |
+
"vision_tower.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1969 |
+
"vision_tower.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1970 |
+
"vision_tower.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1971 |
+
"vision_tower.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 1972 |
+
"vision_tower.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 1973 |
+
"vision_tower.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
| 1974 |
+
"vision_tower.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 1975 |
+
"vision_tower.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 1976 |
+
"vision_tower.merger.linear_fc1.biases": "model-00001-of-00004.safetensors",
|
| 1977 |
+
"vision_tower.merger.linear_fc1.scales": "model-00001-of-00004.safetensors",
|
| 1978 |
+
"vision_tower.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 1979 |
+
"vision_tower.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 1980 |
+
"vision_tower.merger.linear_fc2.biases": "model-00001-of-00004.safetensors",
|
| 1981 |
+
"vision_tower.merger.linear_fc2.scales": "model-00001-of-00004.safetensors",
|
| 1982 |
+
"vision_tower.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 1983 |
+
"vision_tower.merger.norm.bias": "model-00001-of-00004.safetensors",
|
| 1984 |
+
"vision_tower.merger.norm.weight": "model-00001-of-00004.safetensors",
|
| 1985 |
+
"vision_tower.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
|
| 1986 |
+
"vision_tower.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 1987 |
+
"vision_tower.pos_embed.biases": "model-00001-of-00004.safetensors",
|
| 1988 |
+
"vision_tower.pos_embed.scales": "model-00001-of-00004.safetensors",
|
| 1989 |
+
"vision_tower.pos_embed.weight": "model-00001-of-00004.safetensors"
|
| 1990 |
}
|
| 1991 |
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen3VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 16777216,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 65536,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"temporal_patch_size": 2
|
| 23 |
+
},
|
| 24 |
+
"processor_class": "Qwen3VLProcessor",
|
| 25 |
+
"video_processor": {
|
| 26 |
+
"do_convert_rgb": true,
|
| 27 |
+
"do_normalize": true,
|
| 28 |
+
"do_rescale": true,
|
| 29 |
+
"fps": 2.0,
|
| 30 |
+
"image_mean": [
|
| 31 |
+
0.5,
|
| 32 |
+
0.5,
|
| 33 |
+
0.5
|
| 34 |
+
],
|
| 35 |
+
"image_std": [
|
| 36 |
+
0.5,
|
| 37 |
+
0.5,
|
| 38 |
+
0.5
|
| 39 |
+
],
|
| 40 |
+
"max_frames": 768,
|
| 41 |
+
"max_pixels": 25165824,
|
| 42 |
+
"merge_size": 2,
|
| 43 |
+
"min_frames": 4,
|
| 44 |
+
"min_pixels": 4096,
|
| 45 |
+
"patch_size": 16,
|
| 46 |
+
"rescale_factor": 0.00392156862745098,
|
| 47 |
+
"temporal_patch_size": 2,
|
| 48 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 49 |
+
}
|
| 50 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -23,9 +23,9 @@
|
|
| 23 |
},
|
| 24 |
"pad_token": "<|endoftext|>",
|
| 25 |
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
|
|
|
| 26 |
"split_special_tokens": false,
|
| 27 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
-
"tool_parser_type": "qwen3_coder",
|
| 29 |
"unk_token": null,
|
| 30 |
"video_token": "<|video_pad|>",
|
| 31 |
"vision_bos_token": "<|vision_start|>",
|
|
|
|
| 23 |
},
|
| 24 |
"pad_token": "<|endoftext|>",
|
| 25 |
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
"split_special_tokens": false,
|
| 28 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
|
| 29 |
"unk_token": null,
|
| 30 |
"video_token": "<|video_pad|>",
|
| 31 |
"vision_bos_token": "<|vision_start|>",
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|