Hugging Face's logo

radm
/
Qwen2.5-32B-simpo-LoRA

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
radm commited on
Commit
dda76c6
·
1 Parent(s): e8a12f2

first model version

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. adapter_config.json +1 -1
README.md CHANGED
@@ -5,7 +5,7 @@ tags:
5
  - llama-factory
6
  - lora
7
  - generated_from_trainer
8
- base_model: ../models/Qwen2.5-32B-Instruct
9
  model-index:
10
  - name: qwen-guten-simpo
11
  results: []
 
5
  - llama-factory
6
  - lora
7
  - generated_from_trainer
8
+ base_model: Qwen/Qwen2.5-32B-Instruct
9
  model-index:
10
  - name: qwen-guten-simpo
11
  results: []
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "../models/Qwen2.5-32B-Instruct",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,