Initial commit
Browse files- logs.txt +0 -0
- merges.txt +0 -0
- mlc-chat-config.json +81 -0
- ndarray-cache-b16.json +0 -0
- ndarray-cache.json +0 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_4.bin +3 -0
- params_shard_5.bin +3 -0
- params_shard_6.bin +3 -0
- params_shard_7.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +40 -0
- vocab.json +0 -0
logs.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "qwen2",
|
4 |
+
"quantization": "q4f32_1",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_act": "silu",
|
7 |
+
"hidden_size": 896,
|
8 |
+
"intermediate_size": 4864,
|
9 |
+
"num_attention_heads": 14,
|
10 |
+
"num_hidden_layers": 24,
|
11 |
+
"num_key_value_heads": 2,
|
12 |
+
"rms_norm_eps": 1e-06,
|
13 |
+
"rope_theta": 1000000.0,
|
14 |
+
"vocab_size": 151936,
|
15 |
+
"tie_word_embeddings": true,
|
16 |
+
"context_window_size": 32768,
|
17 |
+
"prefill_chunk_size": 2048,
|
18 |
+
"tensor_parallel_shards": 1,
|
19 |
+
"head_dim": 64,
|
20 |
+
"dtype": "float32",
|
21 |
+
"max_batch_size": 80
|
22 |
+
},
|
23 |
+
"vocab_size": 151936,
|
24 |
+
"context_window_size": 32768,
|
25 |
+
"sliding_window_size": -1,
|
26 |
+
"prefill_chunk_size": 2048,
|
27 |
+
"attention_sink_size": -1,
|
28 |
+
"tensor_parallel_shards": 1,
|
29 |
+
"temperature": 0.7,
|
30 |
+
"presence_penalty": 0.0,
|
31 |
+
"frequency_penalty": 0.0,
|
32 |
+
"repetition_penalty": 1.1,
|
33 |
+
"top_p": 0.8,
|
34 |
+
"tokenizer_files": [
|
35 |
+
"tokenizer.json",
|
36 |
+
"vocab.json",
|
37 |
+
"merges.txt",
|
38 |
+
"tokenizer_config.json"
|
39 |
+
],
|
40 |
+
"tokenizer_info": {
|
41 |
+
"token_postproc_method": "byte_level",
|
42 |
+
"prepend_space_in_encode": false,
|
43 |
+
"strip_space_in_decode": false
|
44 |
+
},
|
45 |
+
"conv_template": {
|
46 |
+
"name": "chatml",
|
47 |
+
"system_template": "<|im_start|>system\n{system_message}",
|
48 |
+
"system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
|
49 |
+
"system_prefix_token_ids": null,
|
50 |
+
"add_role_after_system_message": true,
|
51 |
+
"roles": {
|
52 |
+
"user": "<|im_start|>user",
|
53 |
+
"assistant": "<|im_start|>assistant"
|
54 |
+
},
|
55 |
+
"role_templates": {
|
56 |
+
"user": "{user_message}",
|
57 |
+
"assistant": "{assistant_message}",
|
58 |
+
"tool": "{tool_message}"
|
59 |
+
},
|
60 |
+
"messages": [],
|
61 |
+
"seps": [
|
62 |
+
"<|im_end|>\n"
|
63 |
+
],
|
64 |
+
"role_content_sep": "\n",
|
65 |
+
"role_empty_sep": "\n",
|
66 |
+
"stop_str": [
|
67 |
+
"<|im_end|>"
|
68 |
+
],
|
69 |
+
"stop_token_ids": [
|
70 |
+
2
|
71 |
+
],
|
72 |
+
"function_string": "",
|
73 |
+
"use_function_calling": false
|
74 |
+
},
|
75 |
+
"pad_token_id": 151643,
|
76 |
+
"bos_token_id": 151643,
|
77 |
+
"eos_token_id": [
|
78 |
+
151645,
|
79 |
+
151643
|
80 |
+
]
|
81 |
+
}
|
ndarray-cache-b16.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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:fcef4ca2b218e1afe003d72dd81f38b08be3137dae5e28006a5d340588ca4e99
|
3 |
+
size 68067328
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd7df5d90935fcd31e865529a112adcb434b6ac2a14dcac8d0b23cadb98e8fc
|
3 |
+
size 33234176
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f7762563b9de6fce45372b2e7585d2e61ecda069a02c8310e48fbb5b6ceb759
|
3 |
+
size 33505280
|
params_shard_3.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78391bce63b798e2e204a5874116111a6cba76a4e399807ae6de934927bd3676
|
3 |
+
size 33053696
|
params_shard_4.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3773caa2fceac237fd9f8917e08fb6363999dafd9de52e75798d55acbb6ad79c
|
3 |
+
size 33020928
|
params_shard_5.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2dc88af78a0364a5f7e32237746f6a213bb2a6d457f35851629dce271f42d36
|
3 |
+
size 29211648
|
params_shard_6.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9747ccba2c1174e8983a50ccf067f733e4e6dee2045d1d38fbc7b79db1b73e54
|
3 |
+
size 33297408
|
params_shard_7.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b291d01bf87d99cbac6f9a61d07d1da32a5097715247a606b84e5fafa399e538
|
3 |
+
size 14605824
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
|
30 |
+
"bos_token": null,
|
31 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "<|im_end|>",
|
34 |
+
"errors": "replace",
|
35 |
+
"model_max_length": 32768,
|
36 |
+
"pad_token": "<|endoftext|>",
|
37 |
+
"split_special_tokens": false,
|
38 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
39 |
+
"unk_token": null
|
40 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|