Text Generation
PEFT
Safetensors
English
qlora
lora
structured-output
yyano80 commited on
Commit
9e86cbe
·
verified ·
1 Parent(s): 80e7d13

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: 3
38
  - Learning rate: 1e-06
39
  - LoRA: r=128, alpha=128
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=128
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
  "o_proj",
 
39
  "k_proj",
40
  "down_proj",
41
  "up_proj",
42
- "gate_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "gate_proj",
 
37
  "o_proj",
38
+ "v_proj",
39
  "k_proj",
40
  "down_proj",
41
  "up_proj",
42
+ "q_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 sha256:88d4a08645a3e23c3624c9268e8bb315e01122243e3eb6c44bc32607e1508a24
3
  size 1057033224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:910e62f6a86bb228f8e8e1576d759cbb2e7fbf34db381f158efa758dc510c4f2
3
  size 1057033224