Hugging Face's logo

mlc-ai
/
SmolLM-135M-Instruct-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
CharlieFRuan commited on
Commit
9f11903
•
1 Parent(s): 63a2868

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. merges.txt +0 -0
  2. mlc-chat-config.json +76 -0
  3. ndarray-cache.json +0 -0
  4. params_shard_0.bin +3 -0
  5. params_shard_1.bin +3 -0
  6. params_shard_2.bin +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +154 -0
  9. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
mlc-chat-config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "llama",
4
+ "quantization": "q4f16_1",
5
+ "model_config": {
6
+ "hidden_size": 576,
7
+ "intermediate_size": 1536,
8
+ "num_attention_heads": 9,
9
+ "num_hidden_layers": 30,
10
+ "rms_norm_eps": 1e-05,
11
+ "vocab_size": 49152,
12
+ "tie_word_embeddings": true,
13
+ "position_embedding_base": 10000.0,
14
+ "context_window_size": 2048,
15
+ "prefill_chunk_size": 2048,
16
+ "num_key_value_heads": 3,
17
+ "head_dim": 64,
18
+ "tensor_parallel_shards": 1,
19
+ "max_batch_size": 80
20
+ },
21
+ "vocab_size": 49152,
22
+ "context_window_size": 2048,
23
+ "sliding_window_size": -1,
24
+ "prefill_chunk_size": 2048,
25
+ "attention_sink_size": -1,
26
+ "tensor_parallel_shards": 1,
27
+ "temperature": 0.6,
28
+ "presence_penalty": 0.0,
29
+ "frequency_penalty": 0.0,
30
+ "repetition_penalty": 1.0,
31
+ "top_p": 0.92,
32
+ "tokenizer_files": [
33
+ "tokenizer.json",
34
+ "vocab.json",
35
+ "merges.txt",
36
+ "tokenizer_config.json"
37
+ ],
38
+ "tokenizer_info": {
39
+ "token_postproc_method": "byte_level",
40
+ "prepend_space_in_encode": false,
41
+ "strip_space_in_decode": false
42
+ },
43
+ "conv_template": {
44
+ "name": "chatml_nosystem",
45
+ "system_template": "{system_message}",
46
+ "system_message": "",
47
+ "system_prefix_token_ids": null,
48
+ "add_role_after_system_message": true,
49
+ "roles": {
50
+ "user": "<|im_start|>user",
51
+ "assistant": "<|im_start|>assistant"
52
+ },
53
+ "role_templates": {
54
+ "user": "{user_message}",
55
+ "assistant": "{assistant_message}",
56
+ "tool": "{tool_message}"
57
+ },
58
+ "messages": [],
59
+ "seps": [
60
+ "<|im_end|>\n"
61
+ ],
62
+ "role_content_sep": "\n",
63
+ "role_empty_sep": "\n",
64
+ "stop_str": [
65
+ "<|im_end|>"
66
+ ],
67
+ "stop_token_ids": [
68
+ 2
69
+ ],
70
+ "function_string": "",
71
+ "use_function_calling": false
72
+ },
73
+ "pad_token_id": 2,
74
+ "bos_token_id": 1,
75
+ "eos_token_id": 2
76
+ }
ndarray-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4005a78f0440d44af14b573fbc9189c4d7bdf588b0652ff826ed706dac33f73c
3
+ size 33364224
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:471c71abd8512499c9c73afdf29fd707526c32024c751bc2ca165bb474230348
3
+ size 32883840
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f6f9c1a2174754d4348b81336db3ee08af5742aced7c135e2de4f7086a83a3
3
+ size 9467136
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "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 %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "model_max_length": 2048,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff