tachan881 commited on
Commit
99b6f66
·
verified ·
1 Parent(s): 02067fc

Upload LoRA adapter (README written by author)

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -34,7 +34,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
34
  - Base model: Qwen/Qwen3-4B-Instruct-2507
35
  - Method: QLoRA (4-bit)
36
  - Max sequence length: 512
37
- - Epochs: 3
38
  - Learning rate: 1e-06
39
  - LoRA: r=128, alpha=256
40
 
 
34
  - Base model: Qwen/Qwen3-4B-Instruct-2507
35
  - Method: QLoRA (4-bit)
36
  - Max sequence length: 512
37
+ - Epochs: 2
38
  - Learning rate: 1e-06
39
  - LoRA: r=128, alpha=256
40
 
adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "q_proj",
37
- "v_proj",
38
- "gate_proj",
39
  "o_proj",
 
 
40
  "k_proj",
41
- "up_proj",
42
- "down_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "down_proj",
 
 
37
  "o_proj",
38
+ "gate_proj",
39
+ "v_proj",
40
  "k_proj",
41
+ "q_proj",
42
+ "up_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aef0ffda479e65edde8f7b79e14f7a95a95746a525b98be39f50906d22e8e20
3
  size 1057033224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b440a680c3e32352941e183f885bc23740ab04d9f0acd1f765dbaf6d006b46
3
  size 1057033224