PanzerBread commited on
Commit
c11b64b
·
verified ·
1 Parent(s): f80ca1f

Upload folder using huggingface_hub

Browse files
coding-0.2/p/latest/README.md CHANGED
@@ -1,19 +1,16 @@
1
  ---
2
  base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
3
- library_name: peft
4
- model_name: iter-3
5
  tags:
6
- - base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
7
- - lora
8
  - sft
9
- - transformers
10
  - trl
11
  - unsloth
12
  licence: license
13
- pipeline_tag: text-generation
14
  ---
15
 
16
- # Model Card for iter-3
17
 
18
  This model is a fine-tuned version of [unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit](https://huggingface.co/unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit).
19
  It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -38,7 +35,6 @@ This model was trained with SFT.
38
 
39
  ### Framework versions
40
 
41
- - PEFT 0.18.0
42
  - TRL: 0.23.0
43
  - Transformers: 4.57.1
44
  - Pytorch: 2.9.0
 
1
  ---
2
  base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
3
+ library_name: transformers
4
+ model_name: iter-4
5
  tags:
6
+ - generated_from_trainer
 
7
  - sft
 
8
  - trl
9
  - unsloth
10
  licence: license
 
11
  ---
12
 
13
+ # Model Card for iter-4
14
 
15
  This model is a fine-tuned version of [unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit](https://huggingface.co/unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit).
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
 
35
 
36
  ### Framework versions
37
 
 
38
  - TRL: 0.23.0
39
  - Transformers: 4.57.1
40
  - Pytorch: 2.9.0
coding-0.2/p/latest/checkpoint-15/adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "v_proj",
37
- "gate_proj",
38
- "o_proj",
39
  "down_proj",
40
- "q_proj",
41
  "k_proj",
42
- "up_proj"
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "up_proj",
 
 
37
  "down_proj",
38
+ "gate_proj",
39
  "k_proj",
40
+ "q_proj",
41
+ "v_proj",
42
+ "o_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
coding-0.2/p/latest/checkpoint-15/base_adapter/adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "v_proj",
37
- "gate_proj",
38
- "o_proj",
39
  "down_proj",
40
- "q_proj",
41
  "k_proj",
42
- "up_proj"
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "up_proj",
 
 
37
  "down_proj",
38
+ "gate_proj",
39
  "k_proj",
40
+ "q_proj",
41
+ "v_proj",
42
+ "o_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
coding-0.2/p/latest/checkpoint-15/base_adapter/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ed431632b77787072077269e1acd80624d41c3005af6ff4cfd5e11da6b8a82b
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e13d77666cde3be5553e4374a99bbb6da79ac806c123c5dc3f2c0728109cd1b6
3
  size 645975704
coding-0.2/p/latest/checkpoint-15/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ca63cea33c4123b091307794be51abf568e54a247962e47dbece4d9e731f844
3
  size 328468869
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554519fec21b50fdaf46aa0fe08d2db8000a8c953da52e227616003a522d61cf
3
  size 328468869
coding-0.2/p/latest/checkpoint-15/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b2622ed24dd5d956df99b153a6cb12f0d8143a931e908cbbcee18a055f5cc67
3
  size 6225
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce87e7ba68f7bae04e1f54d1eaf3eec80d67754740de7a5d4280edd907f4b5db
3
  size 6225