Hugging Face's logo

chentianqi
/
Qwen2.5-1.5B-Open-R1-Distill-ScaleTuning

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
4-bit precision
gptq
Model card Files Community
chentianqi commited on
Commit
29cc797
·
verified ·
1 Parent(s): 837cf14

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -16,13 +16,13 @@
16
  "peft_type": "STUNE",
17
  "revision": null,
18
  "target_modules": [
19
- "up_proj",
20
- "k_proj",
21
- "down_proj",
22
- "o_proj",
23
  "v_proj",
 
 
 
24
  "q_proj",
25
- "gate_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "trainable_token_indices": null
 
16
  "peft_type": "STUNE",
17
  "revision": null,
18
  "target_modules": [
 
 
 
 
19
  "v_proj",
20
+ "o_proj",
21
+ "gate_proj",
22
+ "k_proj",
23
  "q_proj",
24
+ "up_proj",
25
+ "down_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "trainable_token_indices": null
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d41f45949006dda35784f86e285393efaca36cd602a1f9cf18b39c6fa084c20
3
  size 20497672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f000800415c22a808d33503b2c6ea5757e09ab192140c8675bca57b041ae18
3
  size 20497672
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df80156be6db64186937049ec28c01adab8e5e4096d5a708bc63386abe577661
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fb598e592c43bebac5b471f055d26522f8e30b5bbc56b1aa0953ce44994c260
3
  size 7480