Hugging Face's logo

khongtrunght
/
Qwen2-7B-Instruct-SPPO-Function-call-v2.4

PEFT
Safetensors
qwen2
alignment-handbook
trl
dpo
Generated from Trainer
Model card Files Community
khongtrunght commited on
Commit
b4c302f
·
verified ·
1 Parent(s): 017105e

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. adapter_config.json +4 -4
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "up_proj",
24
  "k_proj",
25
- "gate_proj",
26
  "v_proj",
27
- "o_proj",
28
  "down_proj",
29
- "q_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "k_proj",
 
24
  "v_proj",
25
+ "gate_proj",
26
  "down_proj",
27
+ "up_proj",
28
+ "q_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 sha256:8e0b4413b25acad5a89d0fbcb8fa6466a55bf6f6909a3ead4bfeac8806fbe27a
3
  size 323014168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63501e3ca6662c3a34a84fae58518c2f1ffa15f3676f80431f35adb1c2e366ce
3
  size 323014168
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc11165eeb1bbcfd0cb768ff2ed417be5449736ed83844e67fec001bbcfac8a4
3
  size 6264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745c2fb697b565af128ae973db368f2804bbdef3de8f5f13a0b41bcb19c0e276
3
  size 6264