Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- config.json +43 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +27 -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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "qnguyen3/nanoLLaVA",
|
3 |
+
"architectures": [
|
4 |
+
"BunnyQwenForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "qnguyen3/nanoLLaVA--configuration_llava_qwen2.LlavaQwen2Config",
|
9 |
+
"AutoModelForCausalLM": "qnguyen3/nanoLLaVA--modeling_llava_qwen2.LlavaQwen2ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 151645,
|
12 |
+
"eos_token_id": 151645,
|
13 |
+
"freeze_mm_mlp_adapter": false,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 1024,
|
16 |
+
"image_aspect_ratio": "pad",
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 2816,
|
19 |
+
"language_model": "vilm/Quyen-SE-v0.1",
|
20 |
+
"max_position_embeddings": 32768,
|
21 |
+
"max_window_layers": 21,
|
22 |
+
"mm_hidden_size": 1152,
|
23 |
+
"mm_projector_lr": null,
|
24 |
+
"mm_projector_type": "mlp2x_gelu",
|
25 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-384",
|
26 |
+
"model_type": "bunny-qwen",
|
27 |
+
"num_attention_heads": 16,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"num_key_value_heads": 16,
|
30 |
+
"rms_norm_eps": 1e-06,
|
31 |
+
"rope_theta": 1000000.0,
|
32 |
+
"sliding_window": 4096,
|
33 |
+
"tie_word_embeddings": false,
|
34 |
+
"tokenizer_model_max_length": 4096,
|
35 |
+
"tokenizer_padding_side": "right",
|
36 |
+
"torch_dtype": "bfloat16",
|
37 |
+
"transformers_version": "4.41.1",
|
38 |
+
"tune_mm_mlp_adapter": false,
|
39 |
+
"use_cache": true,
|
40 |
+
"use_mm_proj": true,
|
41 |
+
"use_sliding_window": false,
|
42 |
+
"vocab_size": 151936
|
43 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151645,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 151645,
|
5 |
+
"max_length": 4096,
|
6 |
+
"temperature": 0.7,
|
7 |
+
"top_p": 0.8,
|
8 |
+
"transformers_version": "4.41.1"
|
9 |
+
}
|
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:f2aec32e7b3844f1621d27f8ba64baf00c40f93532a0bdc9b6310b964fcd5e39
|
3 |
+
size 2100155752
|
special_tokens_map.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<|endoftext|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
}
|
27 |
+
}
|
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": "<|im_end|>",
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nAnswer the questions.<|im_end|>' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>'}}{% 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": 4096,
|
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:dbd98d8f050d85426115bea4d402fbe5219738b3d39d6f358c330af5098dc0d1
|
3 |
+
size 7160
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|