upload weights
Browse files- config.json +35 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +40 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 896,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4864,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 21,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 14,
|
16 |
+
"num_hidden_layers": 24,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"quantization_config": {
|
19 |
+
"bits": 4,
|
20 |
+
"group_size": 128,
|
21 |
+
"modules_to_not_convert": null,
|
22 |
+
"quant_method": "awq",
|
23 |
+
"version": "gemm",
|
24 |
+
"zero_point": true
|
25 |
+
},
|
26 |
+
"rms_norm_eps": 1e-06,
|
27 |
+
"rope_theta": 1000000.0,
|
28 |
+
"sliding_window": 32768,
|
29 |
+
"tie_word_embeddings": true,
|
30 |
+
"torch_dtype": "float16",
|
31 |
+
"transformers_version": "4.41.0",
|
32 |
+
"use_cache": true,
|
33 |
+
"use_sliding_window": false,
|
34 |
+
"vocab_size": 151936
|
35 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"top_p": 0.8,
|
11 |
+
"transformers_version": "4.41.0"
|
12 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f45125052aa3458f97c57f06df85604a00df7769b2b60ac808dfd6cf99b1c5cc
|
3 |
+
size 730652248
|
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
|
|