vulcan2506 commited on
Commit
15d3b67
·
verified ·
1 Parent(s): d2afde6

Training in progress, epoch 1

Browse files
README.md CHANGED
@@ -1,18 +1,18 @@
1
  ---
2
- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
3
  library_name: transformers
4
  model_name: Strategic-LLAMA-V1-InstructBase
5
  tags:
6
  - generated_from_trainer
7
- - sft
8
  - unsloth
9
  - trl
 
10
  licence: license
11
  ---
12
 
13
  # Model Card for Strategic-LLAMA-V1-InstructBase
14
 
15
- This model is a fine-tuned version of [unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit).
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
  ## Quick start
 
1
  ---
2
+ base_model: unsloth/llama-3.2-3b-unsloth-bnb-4bit
3
  library_name: transformers
4
  model_name: Strategic-LLAMA-V1-InstructBase
5
  tags:
6
  - generated_from_trainer
 
7
  - unsloth
8
  - trl
9
+ - sft
10
  licence: license
11
  ---
12
 
13
  # Model Card for Strategic-LLAMA-V1-InstructBase
14
 
15
+ This model is a fine-tuned version of [unsloth/llama-3.2-3b-unsloth-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-3b-unsloth-bnb-4bit).
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
  ## Quick start
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
@@ -24,13 +24,13 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "k_proj",
28
  "gate_proj",
29
- "up_proj",
30
- "v_proj",
31
  "q_proj",
32
  "down_proj",
33
- "o_proj"
 
 
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3.2-3b-unsloth-bnb-4bit",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
 
27
  "gate_proj",
28
+ "o_proj",
 
29
  "q_proj",
30
  "down_proj",
31
+ "k_proj",
32
+ "v_proj",
33
+ "up_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:318e30638f3e8381f0adfe31047ce665f13e98c1907b8a32c9402ae3ec4704e6
3
  size 145935536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:860e33f94bbe54c328c0402314fec2efd133e9838bc8b377dd02b732809d96de
3
  size 145935536
special_tokens_map.json CHANGED
@@ -7,7 +7,7 @@
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|eot_id|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|end_of_text|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -2052,7 +2052,7 @@
2052
  },
2053
  "bos_token": "<|begin_of_text|>",
2054
  "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|eot_id|>",
2056
  "extra_special_tokens": {},
2057
  "model_input_names": [
2058
  "input_ids",
 
2052
  },
2053
  "bos_token": "<|begin_of_text|>",
2054
  "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
  "extra_special_tokens": {},
2057
  "model_input_names": [
2058
  "input_ids",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aca339722433d372dde1a4715124185ef13452594bc43989fae38495a761b766
3
  size 6225
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985c6d58f0541f2ba25df2a03d78d91002ef9ec5b987ff84c1fb65dbe2d116d6
3
  size 6225