Yuka Takahara commited on
Commit
f091a84
·
verified ·
1 Parent(s): 66cf306

Upload LoRA adapter (README written by author)

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. adapter_config.json +3 -3
  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: 2
38
  - Learning rate: 2e-05
39
  - LoRA: r=32, alpha=32
40
 
 
34
  - Base model: Qwen/Qwen3-4B-Instruct-2507
35
  - Method: QLoRA (4-bit)
36
  - Max sequence length: 512
37
+ - Epochs: 3
38
  - Learning rate: 2e-05
39
  - LoRA: r=32, alpha=32
40
 
adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "gate_proj",
37
- "down_proj",
38
  "up_proj",
39
  "o_proj",
 
40
  "k_proj",
41
  "q_proj",
42
- "v_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "v_proj",
 
37
  "up_proj",
38
  "o_proj",
39
+ "down_proj",
40
  "k_proj",
41
  "q_proj",
42
+ "gate_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 sha256:86b3425f5b869e465506a6b57bec0adfb17a3112e0e51798ccef717c89095dfa
3
  size 264308896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a22937ed32fe6906d7512929c493ef4032ee15be75f389068f607f44e3a1d70
3
  size 264308896