Upload folder using huggingface_hub
Browse files- README.md +49 -0
- WEIGHTS.md +7 -0
- chat_template.jinja +64 -0
- config.json +72 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- model.safetensors.index.json +342 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
README.md
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: lfm-open-license
|
| 4 |
+
base_model: LiquidAI/LFM2.5-350M
|
| 5 |
+
tags:
|
| 6 |
+
- mlx
|
| 7 |
+
- dictation
|
| 8 |
+
- speech-to-text
|
| 9 |
+
- cleanup
|
| 10 |
+
- polish
|
| 11 |
+
- apple-silicon
|
| 12 |
+
- lfm
|
| 13 |
+
- lc-350m
|
| 14 |
+
language:
|
| 15 |
+
- en
|
| 16 |
+
library_name: mlx
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
# LC-350M-light (Lint Clean)
|
| 21 |
+
|
| 22 |
+
Light on-device **dictation transcript cleanup** for Apple Silicon (MLX).
|
| 23 |
+
|
| 24 |
+
Fine-tuned from [LiquidAI/LFM2.5-350M](https://huggingface.co/LiquidAI/LFM2.5-350M) for MacWispr-style polish:
|
| 25 |
+
|
| 26 |
+
- Remove stutters / exact word repeats
|
| 27 |
+
- Light grammar, punctuation, capitalization
|
| 28 |
+
- **Keep meaning and almost all wording** (no heavy rewrite)
|
| 29 |
+
|
| 30 |
+
For spoken self-corrections (“bag no not bag, my phone”), use **[LC-350M-smart](https://huggingface.co/vasanth009/LC-350M-smart)** instead.
|
| 31 |
+
|
| 32 |
+
## Usage (MLX)
|
| 33 |
+
|
| 34 |
+
```bash
|
| 35 |
+
pip install mlx-lm
|
| 36 |
+
mlx_lm.generate --model vasanth009/LC-350M-light \
|
| 37 |
+
--max-tokens 256 \
|
| 38 |
+
--prompt "Clean this voice dictation lightly. Keep every idea.\n\nTranscript:\nsee we can improve the UI because currently it's it's glitching"
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
## Related
|
| 42 |
+
|
| 43 |
+
- Training repo: [github.com/vasanthsreeram/lc-350m](https://github.com/vasanthsreeram/lc-350m)
|
| 44 |
+
- App: [github.com/vasanthsreeram/macwispr](https://github.com/vasanthsreeram/macwispr)
|
| 45 |
+
- Smart variant: [LC-350M-smart](https://huggingface.co/vasanth009/LC-350M-smart)
|
| 46 |
+
|
| 47 |
+
## License
|
| 48 |
+
|
| 49 |
+
Inherits Liquid LFM base model terms. Training code in the GitHub repo is Apache-2.0.
|
WEIGHTS.md
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Weights
|
| 2 |
+
|
| 3 |
+
Full fused MLX weights are published on Hugging Face:
|
| 4 |
+
|
| 5 |
+
**https://huggingface.co/vasanth009/LC-350M-light**
|
| 6 |
+
|
| 7 |
+
Local build path (after fuse): `models/LC-350M-light/model.safetensors` (gitignored).
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token -}}
|
| 2 |
+
{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
|
| 3 |
+
{%- set ns = namespace(system_prompt="") -%}
|
| 4 |
+
{%- if messages[0]["role"] == "system" -%}
|
| 5 |
+
{%- set sys_content = messages[0]["content"] -%}
|
| 6 |
+
{%- if sys_content is not string -%}
|
| 7 |
+
{%- for item in sys_content -%}
|
| 8 |
+
{%- if item["type"] == "text" -%}
|
| 9 |
+
{%- set ns.system_prompt = ns.system_prompt + item["text"] -%}
|
| 10 |
+
{%- endif -%}
|
| 11 |
+
{%- endfor -%}
|
| 12 |
+
{%- else -%}
|
| 13 |
+
{%- set ns.system_prompt = sys_content -%}
|
| 14 |
+
{%- endif -%}
|
| 15 |
+
{%- set messages = messages[1:] -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- if tools -%}
|
| 18 |
+
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
|
| 19 |
+
{%- for tool in tools -%}
|
| 20 |
+
{%- if tool is not string -%}
|
| 21 |
+
{%- set tool = tool | tojson -%}
|
| 22 |
+
{%- endif -%}
|
| 23 |
+
{%- set ns.system_prompt = ns.system_prompt + tool -%}
|
| 24 |
+
{%- if not loop.last -%}
|
| 25 |
+
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
|
| 26 |
+
{%- endif -%}
|
| 27 |
+
{%- endfor -%}
|
| 28 |
+
{%- set ns.system_prompt = ns.system_prompt + "]" -%}
|
| 29 |
+
{%- endif -%}
|
| 30 |
+
{%- if ns.system_prompt -%}
|
| 31 |
+
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
|
| 32 |
+
{%- endif -%}
|
| 33 |
+
{%- set ns.last_assistant_index = -1 -%}
|
| 34 |
+
{%- for message in messages -%}
|
| 35 |
+
{%- if message["role"] == "assistant" -%}
|
| 36 |
+
{%- set ns.last_assistant_index = loop.index0 -%}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- endfor -%}
|
| 39 |
+
{%- for message in messages -%}
|
| 40 |
+
{{- "<|im_start|>" + message["role"] + "\n" -}}
|
| 41 |
+
{%- set content = message["content"] -%}
|
| 42 |
+
{%- if content is not string -%}
|
| 43 |
+
{%- set ns.content = "" -%}
|
| 44 |
+
{%- for item in content -%}
|
| 45 |
+
{%- if item["type"] == "image" -%}
|
| 46 |
+
{%- set ns.content = ns.content + "<image>" -%}
|
| 47 |
+
{%- elif item["type"] == "text" -%}
|
| 48 |
+
{%- set ns.content = ns.content + item["text"] -%}
|
| 49 |
+
{%- else -%}
|
| 50 |
+
{%- set ns.content = ns.content + item | tojson -%}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{%- endfor -%}
|
| 53 |
+
{%- set content = ns.content -%}
|
| 54 |
+
{%- endif -%}
|
| 55 |
+
{%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
|
| 56 |
+
{%- if "</think>" in content -%}
|
| 57 |
+
{%- set content = content.split("</think>")[-1] | trim -%}
|
| 58 |
+
{%- endif -%}
|
| 59 |
+
{%- endif -%}
|
| 60 |
+
{{- content + "<|im_end|>\n" -}}
|
| 61 |
+
{%- endfor -%}
|
| 62 |
+
{%- if add_generation_prompt -%}
|
| 63 |
+
{{- "<|im_start|>assistant\n" -}}
|
| 64 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Lfm2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attn_implementation": "flash_attention_2",
|
| 6 |
+
"block_auto_adjust_ff_dim": true,
|
| 7 |
+
"block_dim": 1024,
|
| 8 |
+
"block_ff_dim": 6656,
|
| 9 |
+
"block_ffn_dim_multiplier": 1.0,
|
| 10 |
+
"block_mlp_init_scale": 1.0,
|
| 11 |
+
"block_multiple_of": 256,
|
| 12 |
+
"block_norm_eps": 1e-05,
|
| 13 |
+
"block_out_init_scale": 1.0,
|
| 14 |
+
"block_use_swiglu": true,
|
| 15 |
+
"block_use_xavier_init": true,
|
| 16 |
+
"bos_token_id": 1,
|
| 17 |
+
"conv_L_cache": 3,
|
| 18 |
+
"conv_bias": false,
|
| 19 |
+
"conv_dim": 1024,
|
| 20 |
+
"conv_use_xavier_init": true,
|
| 21 |
+
"dtype": "bfloat16",
|
| 22 |
+
"eos_token_id": 7,
|
| 23 |
+
"hidden_size": 1024,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 6656,
|
| 26 |
+
"layer_types": [
|
| 27 |
+
"conv",
|
| 28 |
+
"conv",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"conv",
|
| 31 |
+
"conv",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"conv",
|
| 34 |
+
"conv",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"conv",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"conv",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"conv",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"conv"
|
| 43 |
+
],
|
| 44 |
+
"max_position_embeddings": 128000,
|
| 45 |
+
"model_type": "lfm2",
|
| 46 |
+
"norm_eps": 1e-05,
|
| 47 |
+
"num_attention_heads": 16,
|
| 48 |
+
"num_heads": 16,
|
| 49 |
+
"num_hidden_layers": 16,
|
| 50 |
+
"num_key_value_heads": 8,
|
| 51 |
+
"pad_token_id": 0,
|
| 52 |
+
"quantization": {
|
| 53 |
+
"group_size": 64,
|
| 54 |
+
"bits": 4,
|
| 55 |
+
"mode": "affine"
|
| 56 |
+
},
|
| 57 |
+
"quantization_config": {
|
| 58 |
+
"group_size": 64,
|
| 59 |
+
"bits": 4,
|
| 60 |
+
"mode": "affine"
|
| 61 |
+
},
|
| 62 |
+
"rope_parameters": {
|
| 63 |
+
"rope_theta": 1000000.0,
|
| 64 |
+
"rope_type": "default"
|
| 65 |
+
},
|
| 66 |
+
"rope_theta": 1000000.0,
|
| 67 |
+
"tie_embedding": true,
|
| 68 |
+
"transformers_version": "4.57.1",
|
| 69 |
+
"use_cache": true,
|
| 70 |
+
"use_pos_enc": true,
|
| 71 |
+
"vocab_size": 65536
|
| 72 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 7,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.57.1"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9feecbb18cdf96bf4fbbb6a2c0a7f27b8ea4e413f365776de804d59a89c8834d
|
| 3 |
+
size 221809325
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,342 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 221772800,
|
| 4 |
+
"total_parameters": 354483968
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.embed_tokens.biases": "model.safetensors",
|
| 8 |
+
"model.embed_tokens.scales": "model.safetensors",
|
| 9 |
+
"model.embed_tokens.weight": "model.safetensors",
|
| 10 |
+
"model.embedding_norm.weight": "model.safetensors",
|
| 11 |
+
"model.layers.0.conv.conv.weight": "model.safetensors",
|
| 12 |
+
"model.layers.0.conv.in_proj.biases": "model.safetensors",
|
| 13 |
+
"model.layers.0.conv.in_proj.scales": "model.safetensors",
|
| 14 |
+
"model.layers.0.conv.in_proj.weight": "model.safetensors",
|
| 15 |
+
"model.layers.0.conv.out_proj.biases": "model.safetensors",
|
| 16 |
+
"model.layers.0.conv.out_proj.scales": "model.safetensors",
|
| 17 |
+
"model.layers.0.conv.out_proj.weight": "model.safetensors",
|
| 18 |
+
"model.layers.0.feed_forward.w1.biases": "model.safetensors",
|
| 19 |
+
"model.layers.0.feed_forward.w1.scales": "model.safetensors",
|
| 20 |
+
"model.layers.0.feed_forward.w1.weight": "model.safetensors",
|
| 21 |
+
"model.layers.0.feed_forward.w2.biases": "model.safetensors",
|
| 22 |
+
"model.layers.0.feed_forward.w2.scales": "model.safetensors",
|
| 23 |
+
"model.layers.0.feed_forward.w2.weight": "model.safetensors",
|
| 24 |
+
"model.layers.0.feed_forward.w3.biases": "model.safetensors",
|
| 25 |
+
"model.layers.0.feed_forward.w3.scales": "model.safetensors",
|
| 26 |
+
"model.layers.0.feed_forward.w3.weight": "model.safetensors",
|
| 27 |
+
"model.layers.0.ffn_norm.weight": "model.safetensors",
|
| 28 |
+
"model.layers.0.operator_norm.weight": "model.safetensors",
|
| 29 |
+
"model.layers.1.conv.conv.weight": "model.safetensors",
|
| 30 |
+
"model.layers.1.conv.in_proj.biases": "model.safetensors",
|
| 31 |
+
"model.layers.1.conv.in_proj.scales": "model.safetensors",
|
| 32 |
+
"model.layers.1.conv.in_proj.weight": "model.safetensors",
|
| 33 |
+
"model.layers.1.conv.out_proj.biases": "model.safetensors",
|
| 34 |
+
"model.layers.1.conv.out_proj.scales": "model.safetensors",
|
| 35 |
+
"model.layers.1.conv.out_proj.weight": "model.safetensors",
|
| 36 |
+
"model.layers.1.feed_forward.w1.biases": "model.safetensors",
|
| 37 |
+
"model.layers.1.feed_forward.w1.scales": "model.safetensors",
|
| 38 |
+
"model.layers.1.feed_forward.w1.weight": "model.safetensors",
|
| 39 |
+
"model.layers.1.feed_forward.w2.biases": "model.safetensors",
|
| 40 |
+
"model.layers.1.feed_forward.w2.scales": "model.safetensors",
|
| 41 |
+
"model.layers.1.feed_forward.w2.weight": "model.safetensors",
|
| 42 |
+
"model.layers.1.feed_forward.w3.biases": "model.safetensors",
|
| 43 |
+
"model.layers.1.feed_forward.w3.scales": "model.safetensors",
|
| 44 |
+
"model.layers.1.feed_forward.w3.weight": "model.safetensors",
|
| 45 |
+
"model.layers.1.ffn_norm.weight": "model.safetensors",
|
| 46 |
+
"model.layers.1.operator_norm.weight": "model.safetensors",
|
| 47 |
+
"model.layers.10.feed_forward.w1.biases": "model.safetensors",
|
| 48 |
+
"model.layers.10.feed_forward.w1.scales": "model.safetensors",
|
| 49 |
+
"model.layers.10.feed_forward.w1.weight": "model.safetensors",
|
| 50 |
+
"model.layers.10.feed_forward.w2.biases": "model.safetensors",
|
| 51 |
+
"model.layers.10.feed_forward.w2.scales": "model.safetensors",
|
| 52 |
+
"model.layers.10.feed_forward.w2.weight": "model.safetensors",
|
| 53 |
+
"model.layers.10.feed_forward.w3.biases": "model.safetensors",
|
| 54 |
+
"model.layers.10.feed_forward.w3.scales": "model.safetensors",
|
| 55 |
+
"model.layers.10.feed_forward.w3.weight": "model.safetensors",
|
| 56 |
+
"model.layers.10.ffn_norm.weight": "model.safetensors",
|
| 57 |
+
"model.layers.10.operator_norm.weight": "model.safetensors",
|
| 58 |
+
"model.layers.10.self_attn.k_layernorm.weight": "model.safetensors",
|
| 59 |
+
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 60 |
+
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 61 |
+
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 62 |
+
"model.layers.10.self_attn.out_proj.biases": "model.safetensors",
|
| 63 |
+
"model.layers.10.self_attn.out_proj.scales": "model.safetensors",
|
| 64 |
+
"model.layers.10.self_attn.out_proj.weight": "model.safetensors",
|
| 65 |
+
"model.layers.10.self_attn.q_layernorm.weight": "model.safetensors",
|
| 66 |
+
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 67 |
+
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 68 |
+
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 69 |
+
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 70 |
+
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 71 |
+
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 72 |
+
"model.layers.11.conv.conv.weight": "model.safetensors",
|
| 73 |
+
"model.layers.11.conv.in_proj.biases": "model.safetensors",
|
| 74 |
+
"model.layers.11.conv.in_proj.scales": "model.safetensors",
|
| 75 |
+
"model.layers.11.conv.in_proj.weight": "model.safetensors",
|
| 76 |
+
"model.layers.11.conv.out_proj.biases": "model.safetensors",
|
| 77 |
+
"model.layers.11.conv.out_proj.scales": "model.safetensors",
|
| 78 |
+
"model.layers.11.conv.out_proj.weight": "model.safetensors",
|
| 79 |
+
"model.layers.11.feed_forward.w1.biases": "model.safetensors",
|
| 80 |
+
"model.layers.11.feed_forward.w1.scales": "model.safetensors",
|
| 81 |
+
"model.layers.11.feed_forward.w1.weight": "model.safetensors",
|
| 82 |
+
"model.layers.11.feed_forward.w2.biases": "model.safetensors",
|
| 83 |
+
"model.layers.11.feed_forward.w2.scales": "model.safetensors",
|
| 84 |
+
"model.layers.11.feed_forward.w2.weight": "model.safetensors",
|
| 85 |
+
"model.layers.11.feed_forward.w3.biases": "model.safetensors",
|
| 86 |
+
"model.layers.11.feed_forward.w3.scales": "model.safetensors",
|
| 87 |
+
"model.layers.11.feed_forward.w3.weight": "model.safetensors",
|
| 88 |
+
"model.layers.11.ffn_norm.weight": "model.safetensors",
|
| 89 |
+
"model.layers.11.operator_norm.weight": "model.safetensors",
|
| 90 |
+
"model.layers.12.feed_forward.w1.biases": "model.safetensors",
|
| 91 |
+
"model.layers.12.feed_forward.w1.scales": "model.safetensors",
|
| 92 |
+
"model.layers.12.feed_forward.w1.weight": "model.safetensors",
|
| 93 |
+
"model.layers.12.feed_forward.w2.biases": "model.safetensors",
|
| 94 |
+
"model.layers.12.feed_forward.w2.scales": "model.safetensors",
|
| 95 |
+
"model.layers.12.feed_forward.w2.weight": "model.safetensors",
|
| 96 |
+
"model.layers.12.feed_forward.w3.biases": "model.safetensors",
|
| 97 |
+
"model.layers.12.feed_forward.w3.scales": "model.safetensors",
|
| 98 |
+
"model.layers.12.feed_forward.w3.weight": "model.safetensors",
|
| 99 |
+
"model.layers.12.ffn_norm.weight": "model.safetensors",
|
| 100 |
+
"model.layers.12.operator_norm.weight": "model.safetensors",
|
| 101 |
+
"model.layers.12.self_attn.k_layernorm.weight": "model.safetensors",
|
| 102 |
+
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 103 |
+
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 104 |
+
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 105 |
+
"model.layers.12.self_attn.out_proj.biases": "model.safetensors",
|
| 106 |
+
"model.layers.12.self_attn.out_proj.scales": "model.safetensors",
|
| 107 |
+
"model.layers.12.self_attn.out_proj.weight": "model.safetensors",
|
| 108 |
+
"model.layers.12.self_attn.q_layernorm.weight": "model.safetensors",
|
| 109 |
+
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 110 |
+
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 111 |
+
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 112 |
+
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 113 |
+
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 114 |
+
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 115 |
+
"model.layers.13.conv.conv.weight": "model.safetensors",
|
| 116 |
+
"model.layers.13.conv.in_proj.biases": "model.safetensors",
|
| 117 |
+
"model.layers.13.conv.in_proj.scales": "model.safetensors",
|
| 118 |
+
"model.layers.13.conv.in_proj.weight": "model.safetensors",
|
| 119 |
+
"model.layers.13.conv.out_proj.biases": "model.safetensors",
|
| 120 |
+
"model.layers.13.conv.out_proj.scales": "model.safetensors",
|
| 121 |
+
"model.layers.13.conv.out_proj.weight": "model.safetensors",
|
| 122 |
+
"model.layers.13.feed_forward.w1.biases": "model.safetensors",
|
| 123 |
+
"model.layers.13.feed_forward.w1.scales": "model.safetensors",
|
| 124 |
+
"model.layers.13.feed_forward.w1.weight": "model.safetensors",
|
| 125 |
+
"model.layers.13.feed_forward.w2.biases": "model.safetensors",
|
| 126 |
+
"model.layers.13.feed_forward.w2.scales": "model.safetensors",
|
| 127 |
+
"model.layers.13.feed_forward.w2.weight": "model.safetensors",
|
| 128 |
+
"model.layers.13.feed_forward.w3.biases": "model.safetensors",
|
| 129 |
+
"model.layers.13.feed_forward.w3.scales": "model.safetensors",
|
| 130 |
+
"model.layers.13.feed_forward.w3.weight": "model.safetensors",
|
| 131 |
+
"model.layers.13.ffn_norm.weight": "model.safetensors",
|
| 132 |
+
"model.layers.13.operator_norm.weight": "model.safetensors",
|
| 133 |
+
"model.layers.14.feed_forward.w1.biases": "model.safetensors",
|
| 134 |
+
"model.layers.14.feed_forward.w1.scales": "model.safetensors",
|
| 135 |
+
"model.layers.14.feed_forward.w1.weight": "model.safetensors",
|
| 136 |
+
"model.layers.14.feed_forward.w2.biases": "model.safetensors",
|
| 137 |
+
"model.layers.14.feed_forward.w2.scales": "model.safetensors",
|
| 138 |
+
"model.layers.14.feed_forward.w2.weight": "model.safetensors",
|
| 139 |
+
"model.layers.14.feed_forward.w3.biases": "model.safetensors",
|
| 140 |
+
"model.layers.14.feed_forward.w3.scales": "model.safetensors",
|
| 141 |
+
"model.layers.14.feed_forward.w3.weight": "model.safetensors",
|
| 142 |
+
"model.layers.14.ffn_norm.weight": "model.safetensors",
|
| 143 |
+
"model.layers.14.operator_norm.weight": "model.safetensors",
|
| 144 |
+
"model.layers.14.self_attn.k_layernorm.weight": "model.safetensors",
|
| 145 |
+
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 146 |
+
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 147 |
+
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 148 |
+
"model.layers.14.self_attn.out_proj.biases": "model.safetensors",
|
| 149 |
+
"model.layers.14.self_attn.out_proj.scales": "model.safetensors",
|
| 150 |
+
"model.layers.14.self_attn.out_proj.weight": "model.safetensors",
|
| 151 |
+
"model.layers.14.self_attn.q_layernorm.weight": "model.safetensors",
|
| 152 |
+
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 153 |
+
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 154 |
+
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 155 |
+
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 156 |
+
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 157 |
+
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 158 |
+
"model.layers.15.conv.conv.weight": "model.safetensors",
|
| 159 |
+
"model.layers.15.conv.in_proj.biases": "model.safetensors",
|
| 160 |
+
"model.layers.15.conv.in_proj.scales": "model.safetensors",
|
| 161 |
+
"model.layers.15.conv.in_proj.weight": "model.safetensors",
|
| 162 |
+
"model.layers.15.conv.out_proj.biases": "model.safetensors",
|
| 163 |
+
"model.layers.15.conv.out_proj.scales": "model.safetensors",
|
| 164 |
+
"model.layers.15.conv.out_proj.weight": "model.safetensors",
|
| 165 |
+
"model.layers.15.feed_forward.w1.biases": "model.safetensors",
|
| 166 |
+
"model.layers.15.feed_forward.w1.scales": "model.safetensors",
|
| 167 |
+
"model.layers.15.feed_forward.w1.weight": "model.safetensors",
|
| 168 |
+
"model.layers.15.feed_forward.w2.biases": "model.safetensors",
|
| 169 |
+
"model.layers.15.feed_forward.w2.scales": "model.safetensors",
|
| 170 |
+
"model.layers.15.feed_forward.w2.weight": "model.safetensors",
|
| 171 |
+
"model.layers.15.feed_forward.w3.biases": "model.safetensors",
|
| 172 |
+
"model.layers.15.feed_forward.w3.scales": "model.safetensors",
|
| 173 |
+
"model.layers.15.feed_forward.w3.weight": "model.safetensors",
|
| 174 |
+
"model.layers.15.ffn_norm.weight": "model.safetensors",
|
| 175 |
+
"model.layers.15.operator_norm.weight": "model.safetensors",
|
| 176 |
+
"model.layers.2.feed_forward.w1.biases": "model.safetensors",
|
| 177 |
+
"model.layers.2.feed_forward.w1.scales": "model.safetensors",
|
| 178 |
+
"model.layers.2.feed_forward.w1.weight": "model.safetensors",
|
| 179 |
+
"model.layers.2.feed_forward.w2.biases": "model.safetensors",
|
| 180 |
+
"model.layers.2.feed_forward.w2.scales": "model.safetensors",
|
| 181 |
+
"model.layers.2.feed_forward.w2.weight": "model.safetensors",
|
| 182 |
+
"model.layers.2.feed_forward.w3.biases": "model.safetensors",
|
| 183 |
+
"model.layers.2.feed_forward.w3.scales": "model.safetensors",
|
| 184 |
+
"model.layers.2.feed_forward.w3.weight": "model.safetensors",
|
| 185 |
+
"model.layers.2.ffn_norm.weight": "model.safetensors",
|
| 186 |
+
"model.layers.2.operator_norm.weight": "model.safetensors",
|
| 187 |
+
"model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
|
| 188 |
+
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 189 |
+
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 190 |
+
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 191 |
+
"model.layers.2.self_attn.out_proj.biases": "model.safetensors",
|
| 192 |
+
"model.layers.2.self_attn.out_proj.scales": "model.safetensors",
|
| 193 |
+
"model.layers.2.self_attn.out_proj.weight": "model.safetensors",
|
| 194 |
+
"model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
|
| 195 |
+
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 196 |
+
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 197 |
+
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 198 |
+
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 199 |
+
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 200 |
+
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 201 |
+
"model.layers.3.conv.conv.weight": "model.safetensors",
|
| 202 |
+
"model.layers.3.conv.in_proj.biases": "model.safetensors",
|
| 203 |
+
"model.layers.3.conv.in_proj.scales": "model.safetensors",
|
| 204 |
+
"model.layers.3.conv.in_proj.weight": "model.safetensors",
|
| 205 |
+
"model.layers.3.conv.out_proj.biases": "model.safetensors",
|
| 206 |
+
"model.layers.3.conv.out_proj.scales": "model.safetensors",
|
| 207 |
+
"model.layers.3.conv.out_proj.weight": "model.safetensors",
|
| 208 |
+
"model.layers.3.feed_forward.w1.biases": "model.safetensors",
|
| 209 |
+
"model.layers.3.feed_forward.w1.scales": "model.safetensors",
|
| 210 |
+
"model.layers.3.feed_forward.w1.weight": "model.safetensors",
|
| 211 |
+
"model.layers.3.feed_forward.w2.biases": "model.safetensors",
|
| 212 |
+
"model.layers.3.feed_forward.w2.scales": "model.safetensors",
|
| 213 |
+
"model.layers.3.feed_forward.w2.weight": "model.safetensors",
|
| 214 |
+
"model.layers.3.feed_forward.w3.biases": "model.safetensors",
|
| 215 |
+
"model.layers.3.feed_forward.w3.scales": "model.safetensors",
|
| 216 |
+
"model.layers.3.feed_forward.w3.weight": "model.safetensors",
|
| 217 |
+
"model.layers.3.ffn_norm.weight": "model.safetensors",
|
| 218 |
+
"model.layers.3.operator_norm.weight": "model.safetensors",
|
| 219 |
+
"model.layers.4.conv.conv.weight": "model.safetensors",
|
| 220 |
+
"model.layers.4.conv.in_proj.biases": "model.safetensors",
|
| 221 |
+
"model.layers.4.conv.in_proj.scales": "model.safetensors",
|
| 222 |
+
"model.layers.4.conv.in_proj.weight": "model.safetensors",
|
| 223 |
+
"model.layers.4.conv.out_proj.biases": "model.safetensors",
|
| 224 |
+
"model.layers.4.conv.out_proj.scales": "model.safetensors",
|
| 225 |
+
"model.layers.4.conv.out_proj.weight": "model.safetensors",
|
| 226 |
+
"model.layers.4.feed_forward.w1.biases": "model.safetensors",
|
| 227 |
+
"model.layers.4.feed_forward.w1.scales": "model.safetensors",
|
| 228 |
+
"model.layers.4.feed_forward.w1.weight": "model.safetensors",
|
| 229 |
+
"model.layers.4.feed_forward.w2.biases": "model.safetensors",
|
| 230 |
+
"model.layers.4.feed_forward.w2.scales": "model.safetensors",
|
| 231 |
+
"model.layers.4.feed_forward.w2.weight": "model.safetensors",
|
| 232 |
+
"model.layers.4.feed_forward.w3.biases": "model.safetensors",
|
| 233 |
+
"model.layers.4.feed_forward.w3.scales": "model.safetensors",
|
| 234 |
+
"model.layers.4.feed_forward.w3.weight": "model.safetensors",
|
| 235 |
+
"model.layers.4.ffn_norm.weight": "model.safetensors",
|
| 236 |
+
"model.layers.4.operator_norm.weight": "model.safetensors",
|
| 237 |
+
"model.layers.5.feed_forward.w1.biases": "model.safetensors",
|
| 238 |
+
"model.layers.5.feed_forward.w1.scales": "model.safetensors",
|
| 239 |
+
"model.layers.5.feed_forward.w1.weight": "model.safetensors",
|
| 240 |
+
"model.layers.5.feed_forward.w2.biases": "model.safetensors",
|
| 241 |
+
"model.layers.5.feed_forward.w2.scales": "model.safetensors",
|
| 242 |
+
"model.layers.5.feed_forward.w2.weight": "model.safetensors",
|
| 243 |
+
"model.layers.5.feed_forward.w3.biases": "model.safetensors",
|
| 244 |
+
"model.layers.5.feed_forward.w3.scales": "model.safetensors",
|
| 245 |
+
"model.layers.5.feed_forward.w3.weight": "model.safetensors",
|
| 246 |
+
"model.layers.5.ffn_norm.weight": "model.safetensors",
|
| 247 |
+
"model.layers.5.operator_norm.weight": "model.safetensors",
|
| 248 |
+
"model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
|
| 249 |
+
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 250 |
+
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 251 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 252 |
+
"model.layers.5.self_attn.out_proj.biases": "model.safetensors",
|
| 253 |
+
"model.layers.5.self_attn.out_proj.scales": "model.safetensors",
|
| 254 |
+
"model.layers.5.self_attn.out_proj.weight": "model.safetensors",
|
| 255 |
+
"model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 260 |
+
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 261 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 262 |
+
"model.layers.6.conv.conv.weight": "model.safetensors",
|
| 263 |
+
"model.layers.6.conv.in_proj.biases": "model.safetensors",
|
| 264 |
+
"model.layers.6.conv.in_proj.scales": "model.safetensors",
|
| 265 |
+
"model.layers.6.conv.in_proj.weight": "model.safetensors",
|
| 266 |
+
"model.layers.6.conv.out_proj.biases": "model.safetensors",
|
| 267 |
+
"model.layers.6.conv.out_proj.scales": "model.safetensors",
|
| 268 |
+
"model.layers.6.conv.out_proj.weight": "model.safetensors",
|
| 269 |
+
"model.layers.6.feed_forward.w1.biases": "model.safetensors",
|
| 270 |
+
"model.layers.6.feed_forward.w1.scales": "model.safetensors",
|
| 271 |
+
"model.layers.6.feed_forward.w1.weight": "model.safetensors",
|
| 272 |
+
"model.layers.6.feed_forward.w2.biases": "model.safetensors",
|
| 273 |
+
"model.layers.6.feed_forward.w2.scales": "model.safetensors",
|
| 274 |
+
"model.layers.6.feed_forward.w2.weight": "model.safetensors",
|
| 275 |
+
"model.layers.6.feed_forward.w3.biases": "model.safetensors",
|
| 276 |
+
"model.layers.6.feed_forward.w3.scales": "model.safetensors",
|
| 277 |
+
"model.layers.6.feed_forward.w3.weight": "model.safetensors",
|
| 278 |
+
"model.layers.6.ffn_norm.weight": "model.safetensors",
|
| 279 |
+
"model.layers.6.operator_norm.weight": "model.safetensors",
|
| 280 |
+
"model.layers.7.conv.conv.weight": "model.safetensors",
|
| 281 |
+
"model.layers.7.conv.in_proj.biases": "model.safetensors",
|
| 282 |
+
"model.layers.7.conv.in_proj.scales": "model.safetensors",
|
| 283 |
+
"model.layers.7.conv.in_proj.weight": "model.safetensors",
|
| 284 |
+
"model.layers.7.conv.out_proj.biases": "model.safetensors",
|
| 285 |
+
"model.layers.7.conv.out_proj.scales": "model.safetensors",
|
| 286 |
+
"model.layers.7.conv.out_proj.weight": "model.safetensors",
|
| 287 |
+
"model.layers.7.feed_forward.w1.biases": "model.safetensors",
|
| 288 |
+
"model.layers.7.feed_forward.w1.scales": "model.safetensors",
|
| 289 |
+
"model.layers.7.feed_forward.w1.weight": "model.safetensors",
|
| 290 |
+
"model.layers.7.feed_forward.w2.biases": "model.safetensors",
|
| 291 |
+
"model.layers.7.feed_forward.w2.scales": "model.safetensors",
|
| 292 |
+
"model.layers.7.feed_forward.w2.weight": "model.safetensors",
|
| 293 |
+
"model.layers.7.feed_forward.w3.biases": "model.safetensors",
|
| 294 |
+
"model.layers.7.feed_forward.w3.scales": "model.safetensors",
|
| 295 |
+
"model.layers.7.feed_forward.w3.weight": "model.safetensors",
|
| 296 |
+
"model.layers.7.ffn_norm.weight": "model.safetensors",
|
| 297 |
+
"model.layers.7.operator_norm.weight": "model.safetensors",
|
| 298 |
+
"model.layers.8.feed_forward.w1.biases": "model.safetensors",
|
| 299 |
+
"model.layers.8.feed_forward.w1.scales": "model.safetensors",
|
| 300 |
+
"model.layers.8.feed_forward.w1.weight": "model.safetensors",
|
| 301 |
+
"model.layers.8.feed_forward.w2.biases": "model.safetensors",
|
| 302 |
+
"model.layers.8.feed_forward.w2.scales": "model.safetensors",
|
| 303 |
+
"model.layers.8.feed_forward.w2.weight": "model.safetensors",
|
| 304 |
+
"model.layers.8.feed_forward.w3.biases": "model.safetensors",
|
| 305 |
+
"model.layers.8.feed_forward.w3.scales": "model.safetensors",
|
| 306 |
+
"model.layers.8.feed_forward.w3.weight": "model.safetensors",
|
| 307 |
+
"model.layers.8.ffn_norm.weight": "model.safetensors",
|
| 308 |
+
"model.layers.8.operator_norm.weight": "model.safetensors",
|
| 309 |
+
"model.layers.8.self_attn.k_layernorm.weight": "model.safetensors",
|
| 310 |
+
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 311 |
+
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 312 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 313 |
+
"model.layers.8.self_attn.out_proj.biases": "model.safetensors",
|
| 314 |
+
"model.layers.8.self_attn.out_proj.scales": "model.safetensors",
|
| 315 |
+
"model.layers.8.self_attn.out_proj.weight": "model.safetensors",
|
| 316 |
+
"model.layers.8.self_attn.q_layernorm.weight": "model.safetensors",
|
| 317 |
+
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 318 |
+
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 319 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 320 |
+
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 321 |
+
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 322 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 323 |
+
"model.layers.9.conv.conv.weight": "model.safetensors",
|
| 324 |
+
"model.layers.9.conv.in_proj.biases": "model.safetensors",
|
| 325 |
+
"model.layers.9.conv.in_proj.scales": "model.safetensors",
|
| 326 |
+
"model.layers.9.conv.in_proj.weight": "model.safetensors",
|
| 327 |
+
"model.layers.9.conv.out_proj.biases": "model.safetensors",
|
| 328 |
+
"model.layers.9.conv.out_proj.scales": "model.safetensors",
|
| 329 |
+
"model.layers.9.conv.out_proj.weight": "model.safetensors",
|
| 330 |
+
"model.layers.9.feed_forward.w1.biases": "model.safetensors",
|
| 331 |
+
"model.layers.9.feed_forward.w1.scales": "model.safetensors",
|
| 332 |
+
"model.layers.9.feed_forward.w1.weight": "model.safetensors",
|
| 333 |
+
"model.layers.9.feed_forward.w2.biases": "model.safetensors",
|
| 334 |
+
"model.layers.9.feed_forward.w2.scales": "model.safetensors",
|
| 335 |
+
"model.layers.9.feed_forward.w2.weight": "model.safetensors",
|
| 336 |
+
"model.layers.9.feed_forward.w3.biases": "model.safetensors",
|
| 337 |
+
"model.layers.9.feed_forward.w3.scales": "model.safetensors",
|
| 338 |
+
"model.layers.9.feed_forward.w3.weight": "model.safetensors",
|
| 339 |
+
"model.layers.9.ffn_norm.weight": "model.safetensors",
|
| 340 |
+
"model.layers.9.operator_norm.weight": "model.safetensors"
|
| 341 |
+
}
|
| 342 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|startoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<|im_end|>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"legacy": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_input_names": [
|
| 10 |
+
"input_ids",
|
| 11 |
+
"attention_mask"
|
| 12 |
+
],
|
| 13 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
+
"pad_token": "<|pad|>",
|
| 15 |
+
"sp_model_kwargs": {},
|
| 16 |
+
"spaces_between_special_tokens": false,
|
| 17 |
+
"tokenizer_class": "TokenizersBackend",
|
| 18 |
+
"use_default_system_prompt": false,
|
| 19 |
+
"use_fast": true
|
| 20 |
+
}
|