Hugging Face's logo

sumo43
/
zephyr-7b-sft-full

Text Generation
Transformers
TensorBoard
Safetensors
bit_llama
trl
sft
Generated from Trainer
conversational
Inference Endpoints
Model card Files Metrics Community
sumo43 commited on
Commit
c1efe65
•
1 Parent(s): 2fb7919

Training in progress, step 5000

Browse files
Files changed (5) hide show
  1. config.json +9 -9
  2. model.safetensors +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +4 -43
  5. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "lectura/TinyLlama-120M-news",
3
  "architectures": [
4
  "BitLlamaForCausalLM"
5
  ],
@@ -9,21 +9,21 @@
9
  "bos_token_id": 1,
10
  "eos_token_id": 2,
11
  "hidden_act": "silu",
12
- "hidden_size": 768,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 2048,
15
- "max_position_embeddings": 1024,
16
  "model_type": "bit_llama",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "num_key_value_heads": 12,
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-05,
22
  "rope_scaling": null,
23
  "rope_theta": 10000.0,
24
- "tie_word_embeddings": true,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.39.0.dev0",
27
  "use_cache": false,
28
- "vocab_size": 46338
29
  }
 
1
  {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
  "architectures": [
4
  "BitLlamaForCausalLM"
5
  ],
 
9
  "bos_token_id": 1,
10
  "eos_token_id": 2,
11
  "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 5632,
15
+ "max_position_embeddings": 2048,
16
  "model_type": "bit_llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-05,
22
  "rope_scaling": null,
23
  "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.39.0.dev0",
27
  "use_cache": false,
28
+ "vocab_size": 32002
29
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a8f0f0d2a37ac00149a44fdf13b6cc34e6cc0095696ae6a755be8558ffa5aea
3
- size 241437456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46cb5af63882895c9a1a0eb69aa5e49a8b31c6fec67537f408060dc78992a7d
3
+ size 2201749928
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -26,47 +26,7 @@
26
  "single_word": false,
27
  "special": true
28
  },
29
- "46331": {
30
- "content": "<|sep|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "46332": {
38
- "content": "<|endoftext|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "46333": {
46
- "content": "<|acc|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "46334": {
54
- "content": "<|rrn|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "46335": {
62
- "content": "<|tel|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "46336": {
70
  "content": "<|im_start|>",
71
  "lstrip": false,
72
  "normalized": false,
@@ -74,7 +34,7 @@
74
  "single_word": false,
75
  "special": true
76
  },
77
- "46337": {
78
  "content": "<|im_end|>",
79
  "lstrip": false,
80
  "normalized": false,
@@ -94,8 +54,9 @@
94
  "legacy": false,
95
  "model_max_length": 2048,
96
  "pad_token": "<|im_end|>",
 
97
  "sp_model_kwargs": {},
98
  "tokenizer_class": "LlamaTokenizer",
99
  "unk_token": "<unk>",
100
- "use_default_system_prompt": true
101
  }
 
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "32000": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "content": "<|im_start|>",
31
  "lstrip": false,
32
  "normalized": false,
 
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "32001": {
38
  "content": "<|im_end|>",
39
  "lstrip": false,
40
  "normalized": false,
 
54
  "legacy": false,
55
  "model_max_length": 2048,
56
  "pad_token": "<|im_end|>",
57
+ "padding_side": "right",
58
  "sp_model_kwargs": {},
59
  "tokenizer_class": "LlamaTokenizer",
60
  "unk_token": "<unk>",
61
+ "use_default_system_prompt": false
62
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:835feb71d544b963e5d2bc0c5bc229d8fdfc8cb508e797df572da8dba67d19f9
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07cc40c5a6d24066e3c9c9dc23db4ba29b9036550b49d4e3f00420e402d9f406
3
  size 4984