Hugging Face's logo

VictorDCh
/
Llama-3-8B-Instruct-MoE-2-spider-3

PEFT
TensorBoard
Safetensors
mixtral
trl
sft
Generated from Trainer
Model card Files Metrics Community
VictorDCh commited on
Commit
df87b92
•
1 Parent(s): 277f480

Training in progress, epoch 0

Browse files
Files changed (7) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.safetensors +1 -1
  3. runs/May27_14-24-36_4dea60b22e47/events.out.tfevents.1716812682.4dea60b22e47.90200.0 +3 -0
  4. runs/May27_14-27-26_4dea60b22e47/events.out.tfevents.1716812853.4dea60b22e47.92284.0 +3 -0
  5. special_tokens_map.json +0 -16
  6. tokenizer_config.json +1 -4
  7. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "k_proj",
23
- "up_proj",
24
  "o_proj",
25
- "v_proj",
 
 
26
  "down_proj",
27
- "gate_proj",
28
- "q_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "o_proj",
23
+ "up_proj",
24
+ "q_proj",
25
+ "k_proj",
26
  "down_proj",
27
+ "v_proj",
28
+ "gate_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35c26c6509bcd03e463e4c02ed566e96c08a8f7f029c78c28952e5781ae88c8d
3
  size 2155941056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a024b082bfefc0455d251bf81000219da4194a948de97947b90185c27761b0c3
3
  size 2155941056
runs/May27_14-24-36_4dea60b22e47/events.out.tfevents.1716812682.4dea60b22e47.90200.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b1787e43e41f6585045de619dbd6f2411b8e87af1ecd9a27c237594c7a694c6
3
+ size 5051
runs/May27_14-27-26_4dea60b22e47/events.out.tfevents.1716812853.4dea60b22e47.92284.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c71bd10c619898dbd877a94c2dd3dfb2295bef214e91f5004bdd501b810e8e0
3
+ size 7725
special_tokens_map.json CHANGED
@@ -1,20 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- {
4
- "content": "<|im_end|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<|im_start|>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
- ],
18
  "bos_token": "<|im_start|>",
19
  "eos_token": "<|im_end|>",
20
  "pad_token": "<|im_end|>"
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<|im_start|>",
3
  "eos_token": "<|im_end|>",
4
  "pad_token": "<|im_end|>"
tokenizer_config.json CHANGED
@@ -2065,10 +2065,7 @@
2065
  "special": true
2066
  }
2067
  },
2068
- "additional_special_tokens": [
2069
- "<|im_end|>",
2070
- "<|im_start|>"
2071
- ],
2072
  "bos_token": "<|im_start|>",
2073
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2074
  "clean_up_tokenization_spaces": true,
 
2065
  "special": true
2066
  }
2067
  },
2068
+ "additional_special_tokens": [],
 
 
 
2069
  "bos_token": "<|im_start|>",
2070
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2071
  "clean_up_tokenization_spaces": true,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a870398daa1c55ecca8f1a006c3819c2ab743f8f37cba9d3101a144ebc572967
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9b2a18f2ff9c0e25b74df05d0f5609dea1af3a95412f71b027fd2c7d4c9db2
3
  size 4792