473278e09152c8e043238cb2b2e8569bfc0aea87bf1b6256beb65ba12eb0b360
Browse files- added_tokens.json +5 -0
- config.json +70 -0
- generation_config.json +15 -0
- merges.txt +0 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen1.5-110B-Chat",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaQwenForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 8192,
|
11 |
+
"image_aspect_ratio": "anyres",
|
12 |
+
"image_crop_resolution": null,
|
13 |
+
"image_grid_pinpoints": [
|
14 |
+
[
|
15 |
+
336,
|
16 |
+
672
|
17 |
+
],
|
18 |
+
[
|
19 |
+
672,
|
20 |
+
336
|
21 |
+
],
|
22 |
+
[
|
23 |
+
672,
|
24 |
+
672
|
25 |
+
],
|
26 |
+
[
|
27 |
+
1008,
|
28 |
+
336
|
29 |
+
],
|
30 |
+
[
|
31 |
+
336,
|
32 |
+
1008
|
33 |
+
]
|
34 |
+
],
|
35 |
+
"image_split_resolution": null,
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 49152,
|
38 |
+
"max_position_embeddings": 32768,
|
39 |
+
"max_window_layers": 70,
|
40 |
+
"mm_hidden_size": 1024,
|
41 |
+
"mm_patch_merge_type": "spatial_unpad",
|
42 |
+
"mm_projector_lr": null,
|
43 |
+
"mm_projector_type": "mlp2x_gelu",
|
44 |
+
"mm_resampler_type": null,
|
45 |
+
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
46 |
+
"mm_use_im_patch_token": false,
|
47 |
+
"mm_use_im_start_end": false,
|
48 |
+
"mm_vision_select_feature": "patch",
|
49 |
+
"mm_vision_select_layer": -2,
|
50 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
51 |
+
"mm_vision_tower_lr": 2e-06,
|
52 |
+
"model_type": "llava_qwen",
|
53 |
+
"num_attention_heads": 64,
|
54 |
+
"num_hidden_layers": 80,
|
55 |
+
"num_key_value_heads": 8,
|
56 |
+
"rms_norm_eps": 1e-06,
|
57 |
+
"rope_scaling": null,
|
58 |
+
"rope_theta": 1000000.0,
|
59 |
+
"sliding_window": 32768,
|
60 |
+
"tie_word_embeddings": false,
|
61 |
+
"tokenizer_model_max_length": 32768,
|
62 |
+
"tokenizer_padding_side": "right",
|
63 |
+
"torch_dtype": "bfloat16",
|
64 |
+
"transformers_version": "4.40.0.dev0",
|
65 |
+
"use_cache": true,
|
66 |
+
"use_mm_proj": true,
|
67 |
+
"use_sliding_window": false,
|
68 |
+
"vision_tower_pretrained": null,
|
69 |
+
"vocab_size": 152064
|
70 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attn_implementation": "flash_attention_2",
|
3 |
+
"bos_token_id": 151643,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": [
|
6 |
+
151645,
|
7 |
+
151643
|
8 |
+
],
|
9 |
+
"pad_token_id": 151643,
|
10 |
+
"repetition_penalty": 1.05,
|
11 |
+
"temperature": 0.7,
|
12 |
+
"top_k": 20,
|
13 |
+
"top_p": 0.8,
|
14 |
+
"transformers_version": "4.40.0.dev0"
|
15 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"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 %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "right",
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
44 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2087078af028aa2233d6020a300508662d2ee97d8cddb35c1b6c70d8e12891c
|
3 |
+
size 8248
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|