Hugging Face's logo

S4nto
/
lora-dpo-finetuned-model-beta-0.4-rate-1e5-stage2-iter40000-sft

Transformers
Safetensors
Inference Endpoints
Model card Files Community
S4nto commited on
Commit
c210633
·
verified ·
1 Parent(s): e40aacb

Upload model

Browse files
Files changed (2) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.safetensors +1 -1
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "GENIAC-Team-Ozaki/lora-sft-excluded-chatbot-arena-finetuned-stage2-iter40000",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
- "o_proj",
25
  "k_proj",
26
  "gate_proj",
27
- "up_proj",
 
28
  "v_proj",
29
- "down_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "GENIAC-Team-Ozaki/lora-sft-finetuned-stage4-iter86000",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "k_proj",
24
  "gate_proj",
25
+ "q_proj",
26
+ "down_proj",
27
  "v_proj",
28
+ "up_proj",
29
+ "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:105c5d0469f9d42d3ed8e6b3a961aead4a354c40f626f87344dff08601d3bc0e
3
  size 57417968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0dc38a9e5614417b0d39d592b88dff89654e5f64893aef4d2bfab92e18880eb
3
  size 57417968