Pragades commited on
Commit
8663107
·
verified ·
1 Parent(s): 3818ecc

Provide Your Huggingface Library

Browse files
README.md CHANGED
@@ -1,17 +1,17 @@
1
  ---
2
- base_model: meta-llama/Llama-3.2-1B
3
  library_name: transformers
4
  model_name: JavaFollowUp
5
  tags:
6
  - generated_from_trainer
7
- - sft
8
  - trl
 
9
  licence: license
10
  ---
11
 
12
  # Model Card for JavaFollowUp
13
 
14
- This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<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/vineeshsiva20-axtrlabs/huggingface/runs/9kpodtxc)
31
 
32
 
33
  This model was trained with SFT.
 
1
  ---
2
+ base_model: meta-llama/Meta-Llama-3.1-8B
3
  library_name: transformers
4
  model_name: JavaFollowUp
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
+ - sft
9
  licence: license
10
  ---
11
 
12
  # Model Card for JavaFollowUp
13
 
14
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
27
 
28
  ## Training procedure
29
 
30
+ [<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/ml-developer-nitinnov-technologies-private-limited/uncategorized/runs/gsl8xmih)
31
 
32
 
33
  This model was trained with SFT.
adapter_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
- "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
@@ -29,12 +29,12 @@
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
- "gate_proj",
33
- "up_proj",
34
  "q_proj",
 
 
35
  "down_proj",
36
  "o_proj",
37
- "k_proj",
38
  "v_proj"
39
  ],
40
  "target_parameters": null,
 
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
 
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
+ "k_proj",
 
33
  "q_proj",
34
+ "up_proj",
35
+ "gate_proj",
36
  "down_proj",
37
  "o_proj",
 
38
  "v_proj"
39
  ],
40
  "target_parameters": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a4ff56242dfdd5fdb0389d11b60fab599c638935c62346056b907c77146c3c6
3
- size 90207248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b30b8bab0a11ee0e0b526156c659b4b071c87ff8db07cc1ce9e778b6575af14
3
+ size 335604696
special_tokens_map.json CHANGED
@@ -12,6 +12,5 @@
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
- },
16
- "pad_token": "<|end_of_text|>"
17
  }
 
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
+ }
 
16
  }
tokenizer_config.json CHANGED
@@ -2058,6 +2058,5 @@
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
2061
- "pad_token": "<|end_of_text|>",
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
  }
 
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
 
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cc11c1c2e49eac7c6faa91bf18055dc241df0ef71672968cad7215d789054fa
3
  size 6161
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6819fbfc01189ef2dc408cfdc00551fc1a3110260cae0b6c3adc5f2da324f8
3
  size 6161