Hugging Face's logo

mango-sciences
/
Mistral_7B_0.2_Chat_finetuned_DS_v1_RL

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files Community
Anshulmango commited on
Commit
4d1b05c
•
1 Parent(s): cbf45b0

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "k_proj",
23
  "q_proj",
24
- "v_proj",
25
- "o_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "q_proj",
23
+ "o_proj",
24
+ "k_proj",
25
+ "v_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50f3455820ef1327e69484e6706c26e456a23b591c621b13749aa83a24206478
3
  size 218138576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e4a3199e790ca5fca4b66712f064eba08e8c981844723ade268602eeb35222
3
  size 218138576
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8c68627fdd367f0676dedc072970ef22640242ce298e2f9d2343f2542d9ae42
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4b665f60a77b0b1a2fb974c27e1b72cc98798f9c294d15290f4c9b3b81df76
3
  size 4792