Instruction LoRA upload — task unknown (cleanup + adapter only + .gitattributes)
Browse files- README.md +2 -2
- adapter_config.json +15 -4
- adapter_model.safetensors +2 -2
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
# LoRA — Instruction SFT
|
| 2 |
-
- **Task ID:**
|
| 3 |
- **Base model:** mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
-
- **SHA256 (adapter):** `
|
| 5 |
- **Repo:** raniero/auto-repo
|
| 6 |
|
| 7 |
Questa repo contiene SOLO gli adapter LoRA richiesti dai validator Subnet 56.
|
|
|
|
| 1 |
# LoRA — Instruction SFT
|
| 2 |
+
- **Task ID:** unknown
|
| 3 |
- **Base model:** mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
- **SHA256 (adapter):** `6f22f6f61d78c4f0334cf2b7bcfe2d92d3a6f90fd8ce2d530827d95e45930afa`
|
| 5 |
- **Repo:** raniero/auto-repo
|
| 6 |
|
| 7 |
Questa repo contiene SOLO gli adapter LoRA richiesti dai validator Subnet 56.
|
adapter_config.json
CHANGED
|
@@ -1,19 +1,21 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"peft_type": "LORA",
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 5 |
"revision": null,
|
| 6 |
-
"task_type": "CAUSAL_LM",
|
| 7 |
"inference_mode": false,
|
| 8 |
-
"r":
|
| 9 |
"target_modules": [
|
| 10 |
"v_proj",
|
| 11 |
"q_proj"
|
| 12 |
],
|
| 13 |
-
"
|
|
|
|
| 14 |
"lora_dropout": 0.05,
|
| 15 |
"fan_in_fan_out": false,
|
| 16 |
"bias": "none",
|
|
|
|
| 17 |
"modules_to_save": null,
|
| 18 |
"init_lora_weights": true,
|
| 19 |
"layers_to_transform": null,
|
|
@@ -22,5 +24,14 @@
|
|
| 22 |
"alpha_pattern": {},
|
| 23 |
"megatron_config": null,
|
| 24 |
"megatron_core": "megatron.core",
|
| 25 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"task_type": "CAUSAL_LM",
|
| 3 |
"peft_type": "LORA",
|
| 4 |
"auto_mapping": null,
|
| 5 |
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 6 |
"revision": null,
|
|
|
|
| 7 |
"inference_mode": false,
|
| 8 |
+
"r": 8,
|
| 9 |
"target_modules": [
|
| 10 |
"v_proj",
|
| 11 |
"q_proj"
|
| 12 |
],
|
| 13 |
+
"exclude_modules": null,
|
| 14 |
+
"lora_alpha": 16,
|
| 15 |
"lora_dropout": 0.05,
|
| 16 |
"fan_in_fan_out": false,
|
| 17 |
"bias": "none",
|
| 18 |
+
"use_rslora": false,
|
| 19 |
"modules_to_save": null,
|
| 20 |
"init_lora_weights": true,
|
| 21 |
"layers_to_transform": null,
|
|
|
|
| 24 |
"alpha_pattern": {},
|
| 25 |
"megatron_config": null,
|
| 26 |
"megatron_core": "megatron.core",
|
| 27 |
+
"trainable_token_indices": null,
|
| 28 |
+
"loftq_config": {},
|
| 29 |
+
"eva_config": null,
|
| 30 |
+
"corda_config": null,
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_qalora": false,
|
| 33 |
+
"qalora_group_size": 16,
|
| 34 |
+
"layer_replication": null,
|
| 35 |
+
"lora_bias": false,
|
| 36 |
+
"target_parameters": null
|
| 37 |
}
|
adapter_model.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 sha256:6f22f6f61d78c4f0334cf2b7bcfe2d92d3a6f90fd8ce2d530827d95e45930afa
|
| 3 |
+
size 13648400
|