Upload folder using huggingface_hub
Browse files- mlc-chat-config.json +82 -0
- tokenizer.model +3 -0
- tokenizer_config.json +102 -0
mlc-chat-config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "internlm2",
|
4 |
+
"quantization": "q0f16",
|
5 |
+
"model_config": {
|
6 |
+
"vocab_size": 92544,
|
7 |
+
"hidden_size": 6144,
|
8 |
+
"num_hidden_layers": 48,
|
9 |
+
"num_attention_heads": 48,
|
10 |
+
"num_key_value_heads": 8,
|
11 |
+
"rms_norm_eps": 1e-05,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"bias": false,
|
14 |
+
"use_cache": true,
|
15 |
+
"rope_theta": 50000000,
|
16 |
+
"pad_token_id": 2,
|
17 |
+
"bos_token_id": 1,
|
18 |
+
"eos_token_id": 2,
|
19 |
+
"context_window_size": 32768,
|
20 |
+
"prefill_chunk_size": 8192,
|
21 |
+
"tensor_parallel_shards": 1,
|
22 |
+
"max_batch_size": 128,
|
23 |
+
"head_dim": 128
|
24 |
+
},
|
25 |
+
"vocab_size": 92544,
|
26 |
+
"context_window_size": 32768,
|
27 |
+
"sliding_window_size": -1,
|
28 |
+
"prefill_chunk_size": 8192,
|
29 |
+
"attention_sink_size": -1,
|
30 |
+
"tensor_parallel_shards": 1,
|
31 |
+
"pipeline_parallel_stages": 1,
|
32 |
+
"temperature": 1.0,
|
33 |
+
"presence_penalty": 0.0,
|
34 |
+
"frequency_penalty": 0.0,
|
35 |
+
"repetition_penalty": 1.0,
|
36 |
+
"top_p": 1.0,
|
37 |
+
"tokenizer_files": [
|
38 |
+
"tokenizer.model",
|
39 |
+
"tokenizer_config.json"
|
40 |
+
],
|
41 |
+
"tokenizer_info": {
|
42 |
+
"token_postproc_method": "byte_fallback",
|
43 |
+
"prepend_space_in_encode": false,
|
44 |
+
"strip_space_in_decode": false
|
45 |
+
},
|
46 |
+
"conv_template": {
|
47 |
+
"name": "chatml",
|
48 |
+
"system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
|
49 |
+
"system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
|
50 |
+
"system_prefix_token_ids": null,
|
51 |
+
"add_role_after_system_message": true,
|
52 |
+
"roles": {
|
53 |
+
"user": "<|im_start|>user",
|
54 |
+
"assistant": "<|im_start|>assistant"
|
55 |
+
},
|
56 |
+
"role_templates": {
|
57 |
+
"user": "{user_message}",
|
58 |
+
"assistant": "{assistant_message}",
|
59 |
+
"tool": "{tool_message}"
|
60 |
+
},
|
61 |
+
"messages": [],
|
62 |
+
"seps": [
|
63 |
+
"<|im_end|>\n"
|
64 |
+
],
|
65 |
+
"role_content_sep": "\n",
|
66 |
+
"role_empty_sep": "\n",
|
67 |
+
"stop_str": [
|
68 |
+
"<|im_end|>"
|
69 |
+
],
|
70 |
+
"stop_token_ids": [
|
71 |
+
2
|
72 |
+
],
|
73 |
+
"function_string": "",
|
74 |
+
"use_function_calling": false
|
75 |
+
},
|
76 |
+
"pad_token_id": 2,
|
77 |
+
"bos_token_id": 1,
|
78 |
+
"eos_token_id": [
|
79 |
+
2,
|
80 |
+
92542
|
81 |
+
]
|
82 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
|
3 |
+
size 1477754
|
tokenizer_config.json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"92538": {
|
30 |
+
"content": "<|plugin|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"92539": {
|
38 |
+
"content": "<|interpreter|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"92540": {
|
46 |
+
"content": "<|action_end|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"92541": {
|
54 |
+
"content": "<|action_start|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"92542": {
|
62 |
+
"content": "<|im_end|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"92543": {
|
70 |
+
"content": "<|im_start|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
}
|
77 |
+
},
|
78 |
+
"additional_special_tokens": [
|
79 |
+
"<|im_start|>",
|
80 |
+
"<|im_end|>",
|
81 |
+
"<|action_start|>",
|
82 |
+
"<|action_end|>",
|
83 |
+
"<|interpreter|>",
|
84 |
+
"<|plugin|>"
|
85 |
+
],
|
86 |
+
"auto_map": {
|
87 |
+
"AutoTokenizer": [
|
88 |
+
"tokenization_internlm2.InternLM2Tokenizer",
|
89 |
+
"tokenization_internlm2_fast.InternLM2TokenizerFast"
|
90 |
+
]
|
91 |
+
},
|
92 |
+
"bos_token": "<s>",
|
93 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
94 |
+
"clean_up_tokenization_spaces": false,
|
95 |
+
"decode_with_prefix_space": false,
|
96 |
+
"eos_token": "</s>",
|
97 |
+
"model_max_length": 1000000000000000019884624838656,
|
98 |
+
"pad_token": "</s>",
|
99 |
+
"sp_model_kwargs": null,
|
100 |
+
"tokenizer_class": "InternLM2Tokenizer",
|
101 |
+
"unk_token": "<unk>"
|
102 |
+
}
|