Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- adapter_config.json +54 -0
- adapter_model.safetensors +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "NemotronHForCausalLM",
|
| 7 |
+
"parent_library": "transformers_modules.unsloth.NVIDIA_hyphen_Nemotron_hyphen_3_hyphen_Nano_hyphen_4B.b604b1379531cfac85a3cb195c387cc698aabdeb.modeling_nemotron_h",
|
| 8 |
+
"unsloth_fixed": true
|
| 9 |
+
},
|
| 10 |
+
"base_model_name_or_path": "unsloth/NVIDIA-Nemotron-3-Nano-4B",
|
| 11 |
+
"bias": "none",
|
| 12 |
+
"corda_config": null,
|
| 13 |
+
"ensure_weight_tying": false,
|
| 14 |
+
"eva_config": null,
|
| 15 |
+
"exclude_modules": null,
|
| 16 |
+
"fan_in_fan_out": false,
|
| 17 |
+
"inference_mode": true,
|
| 18 |
+
"init_lora_weights": true,
|
| 19 |
+
"layer_replication": null,
|
| 20 |
+
"layers_pattern": null,
|
| 21 |
+
"layers_to_transform": null,
|
| 22 |
+
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 16,
|
| 24 |
+
"lora_bias": false,
|
| 25 |
+
"lora_dropout": 0,
|
| 26 |
+
"lora_ga_config": null,
|
| 27 |
+
"megatron_config": null,
|
| 28 |
+
"megatron_core": "megatron.core",
|
| 29 |
+
"modules_to_save": null,
|
| 30 |
+
"peft_type": "LORA",
|
| 31 |
+
"peft_version": "0.19.1",
|
| 32 |
+
"qalora_group_size": 16,
|
| 33 |
+
"r": 16,
|
| 34 |
+
"rank_pattern": {},
|
| 35 |
+
"revision": null,
|
| 36 |
+
"target_modules": [
|
| 37 |
+
"k_proj",
|
| 38 |
+
"down_proj",
|
| 39 |
+
"q_proj",
|
| 40 |
+
"out_proj",
|
| 41 |
+
"up_proj",
|
| 42 |
+
"in_proj",
|
| 43 |
+
"v_proj",
|
| 44 |
+
"o_proj",
|
| 45 |
+
"gate_proj"
|
| 46 |
+
],
|
| 47 |
+
"target_parameters": null,
|
| 48 |
+
"task_type": "CAUSAL_LM",
|
| 49 |
+
"trainable_token_indices": null,
|
| 50 |
+
"use_bdlora": null,
|
| 51 |
+
"use_dora": false,
|
| 52 |
+
"use_qalora": false,
|
| 53 |
+
"use_rslora": false
|
| 54 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a64901468646c2d5ed5b1c3eff2efec9e5858138c13b057b2e0a1881188a5e52
|
| 3 |
+
size 82778456
|