Upload 4 files
Browse files- lit_model.pth +3 -0
- model_config.yaml +42 -0
- tokenizer.json +0 -0
- tokenizer_config.json +40 -0
lit_model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97fbcf5093ffe42f5015b10a70ff383a88e280e66b1c814c78656fb29cd600b6
|
3 |
+
size 2777267002
|
model_config.yaml
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
add_qkv_bias: true
|
2 |
+
asr_adapter: llamamlp
|
3 |
+
attn_dropout: 0.0
|
4 |
+
bias: false
|
5 |
+
block_size: 2048
|
6 |
+
force_align: false
|
7 |
+
gelu_approximate: none
|
8 |
+
head_size: 64
|
9 |
+
hf_config:
|
10 |
+
name: Qwen2-0.5B
|
11 |
+
org: Qwen
|
12 |
+
intermediate_size: 4864
|
13 |
+
lm_head_bias: false
|
14 |
+
mlp_class_name: LLaMAMLP
|
15 |
+
n_embd: 896
|
16 |
+
n_expert: 0
|
17 |
+
n_expert_per_token: 0
|
18 |
+
n_head: 14
|
19 |
+
n_layer: 24
|
20 |
+
n_query_groups: 2
|
21 |
+
name: Qwen2-0.5B
|
22 |
+
norm_class_name: RMSNorm
|
23 |
+
norm_eps: 1.0e-06
|
24 |
+
padded_vocab_size: 181120
|
25 |
+
padding_multiple: 512
|
26 |
+
parallel_residual: false
|
27 |
+
pos_type: rope
|
28 |
+
post_adapter: false
|
29 |
+
post_adapter_layers: 6
|
30 |
+
prompt_vocab_size: null
|
31 |
+
rope_base: 1000000
|
32 |
+
rope_condense_ratio: 1
|
33 |
+
rotary_percentage: 1
|
34 |
+
scale_embeddings: false
|
35 |
+
shared_attention_norm: false
|
36 |
+
tie_word_embeddings: true
|
37 |
+
use_pretrain_phoneme_emb: false
|
38 |
+
vocab_size: 50254
|
39 |
+
text_vocab_size: 152000
|
40 |
+
cat_audio_vocab_size: 29120
|
41 |
+
audio_vocab_size: 4160
|
42 |
+
whisper_adapter_dim: 768
|
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": "<|endoftext|>",
|
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 |
+
}
|