Hugging Face's logo

PanzerBread
/
PromptCoT

Text Generation
PEFT
Safetensors
Transformers
lora
promptcot
chain-of-thought
mathematical-reasoning
unsloth
Model card Files
xet
 Community
PanzerBread commited on
Commit
7dc29fe
·
verified ·
1 Parent(s): 9f11147

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. coding-0.2/p/latest/README.md +3 -3
  2. coding-0.2/p/latest/adapter_config.json +4 -4
  3. coding-0.2/p/latest/base_adapter/adapter_config.json +5 -8
  4. coding-0.2/p/latest/base_adapter/adapter_model.safetensors +2 -2
  5. coding-0.2/p/latest/checkpoint-28/adapter_config.json +4 -4
  6. coding-0.2/p/latest/checkpoint-28/base_adapter/adapter_config.json +5 -8
  7. coding-0.2/p/latest/checkpoint-28/base_adapter/adapter_model.safetensors +2 -2
  8. coding-0.2/p/latest/checkpoint-28/optimizer.pt +2 -2
  9. coding-0.2/p/latest/checkpoint-28/trainer_state.json +1 -1
  10. coding-0.2/p/latest/checkpoint-28/training_args.bin +1 -1
coding-0.2/p/latest/README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
3
  library_name: peft
4
- model_name: iter-1
5
  tags:
6
  - base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
7
  - lora
@@ -13,7 +13,7 @@ licence: license
13
  pipeline_tag: text-generation
14
  ---
15
 
16
- # Model Card for iter-1
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).
@@ -31,7 +31,7 @@ print(output["generated_text"])
31
 
32
  ## Training procedure
33
 
34
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/kstaron-/huggingface/runs/lrlmlt1t)
35
 
36
 
37
  This model was trained with SFT.
 
1
  ---
2
  base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
3
  library_name: peft
4
+ model_name: iter-2
5
  tags:
6
  - base_model:adapter:unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
7
  - lora
 
13
  pipeline_tag: text-generation
14
  ---
15
 
16
+ # Model Card for iter-2
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).
 
31
 
32
  ## Training procedure
33
 
34
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/kstaron-/promptcot-em/runs/em_training_6iters)
35
 
36
 
37
  This model was trained with SFT.
coding-0.2/p/latest/adapter_config.json CHANGED
@@ -34,12 +34,12 @@
34
  "revision": null,
35
  "target_modules": [
36
  "up_proj",
37
- "down_proj",
38
  "q_proj",
39
- "gate_proj",
40
  "k_proj",
41
- "o_proj",
42
- "v_proj"
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
34
  "revision": null,
35
  "target_modules": [
36
  "up_proj",
 
37
  "q_proj",
 
38
  "k_proj",
39
+ "down_proj",
40
+ "gate_proj",
41
+ "v_proj",
42
+ "o_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
coding-0.2/p/latest/base_adapter/adapter_config.json CHANGED
@@ -25,10 +25,7 @@
25
  "lora_dropout": 0,
26
  "megatron_config": null,
27
  "megatron_core": "megatron.core",
28
- "modules_to_save": [
29
- "lm_head",
30
- "embed_tokens"
31
- ],
32
  "peft_type": "LORA",
33
  "peft_version": "0.18.0",
34
  "qalora_group_size": 16,
@@ -37,12 +34,12 @@
37
  "revision": null,
38
  "target_modules": [
39
  "up_proj",
40
- "down_proj",
41
  "q_proj",
42
- "gate_proj",
43
  "k_proj",
44
- "o_proj",
45
- "v_proj"
 
 
46
  ],
47
  "target_parameters": null,
48
  "task_type": "CAUSAL_LM",
 
25
  "lora_dropout": 0,
26
  "megatron_config": null,
27
  "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
 
 
 
29
  "peft_type": "LORA",
30
  "peft_version": "0.18.0",
31
  "qalora_group_size": 16,
 
34
  "revision": null,
35
  "target_modules": [
36
  "up_proj",
 
37
  "q_proj",
 
38
  "k_proj",
39
+ "down_proj",
40
+ "gate_proj",
41
+ "v_proj",
42
+ "o_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
coding-0.2/p/latest/base_adapter/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c9481dac28ce0d5b8ade418c64f05fd46d073d116917d1a498f4235b9f39c72
3
- size 2825965440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ff04ba632410c1d699ff65581199682b73a2fcf21950113b9de8fd7e27ed4f
3
+ size 645975704
coding-0.2/p/latest/checkpoint-28/adapter_config.json CHANGED
@@ -34,12 +34,12 @@
34
  "revision": null,
35
  "target_modules": [
36
  "up_proj",
37
- "down_proj",
38
  "q_proj",
39
- "gate_proj",
40
  "k_proj",
41
- "o_proj",
42
- "v_proj"
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
34
  "revision": null,
35
  "target_modules": [
36
  "up_proj",
 
37
  "q_proj",
 
38
  "k_proj",
39
+ "down_proj",
40
+ "gate_proj",
41
+ "v_proj",
42
+ "o_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
coding-0.2/p/latest/checkpoint-28/base_adapter/adapter_config.json CHANGED
@@ -25,10 +25,7 @@
25
  "lora_dropout": 0,
26
  "megatron_config": null,
27
  "megatron_core": "megatron.core",
28
- "modules_to_save": [
29
- "lm_head",
30
- "embed_tokens"
31
- ],
32
  "peft_type": "LORA",
33
  "peft_version": "0.18.0",
34
  "qalora_group_size": 16,
@@ -37,12 +34,12 @@
37
  "revision": null,
38
  "target_modules": [
39
  "up_proj",
40
- "down_proj",
41
  "q_proj",
42
- "gate_proj",
43
  "k_proj",
44
- "o_proj",
45
- "v_proj"
 
 
46
  ],
47
  "target_parameters": null,
48
  "task_type": "CAUSAL_LM",
 
25
  "lora_dropout": 0,
26
  "megatron_config": null,
27
  "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
 
 
 
29
  "peft_type": "LORA",
30
  "peft_version": "0.18.0",
31
  "qalora_group_size": 16,
 
34
  "revision": null,
35
  "target_modules": [
36
  "up_proj",
 
37
  "q_proj",
 
38
  "k_proj",
39
+ "down_proj",
40
+ "gate_proj",
41
+ "v_proj",
42
+ "o_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
coding-0.2/p/latest/checkpoint-28/base_adapter/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c9481dac28ce0d5b8ade418c64f05fd46d073d116917d1a498f4235b9f39c72
3
- size 2825965440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ff04ba632410c1d699ff65581199682b73a2fcf21950113b9de8fd7e27ed4f
3
+ size 645975704
coding-0.2/p/latest/checkpoint-28/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f022fdf1d6b23d3fb608c874aedc470a49d88a3add70d804eca3992e867327bc
3
- size 5795494515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb72360b58fa91fe5d6b16b7eb7744a74ae14dce46ee0eabd0f5ffe5887ce58
3
+ size 328468869
coding-0.2/p/latest/checkpoint-28/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 2.438731137024e+17,
30
  "train_batch_size": 90,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 2.2713079431168e+17,
30
  "train_batch_size": 90,
31
  "trial_name": null,
32
  "trial_params": null
coding-0.2/p/latest/checkpoint-28/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d742ad02897ec0aeab7d86e7684e69ab674b7af5a473943467239abd13221e98
3
  size 6225
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc86eb21aff7e7c0abc5483802cd6faeb2970251b815689e19b35ddacc65d918
3
  size 6225