Flying-Lynx
commited on
Commit
•
2e33041
1
Parent(s):
7e2c35f
Upload folder using huggingface_hub
Browse files- config.json +46 -0
- generation_config.json +11 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "lmsys/vicuna-13b-v1.5",
|
3 |
+
"architectures": [
|
4 |
+
"EagleLlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"freeze_mm_mlp_adapter": false,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 5120,
|
13 |
+
"image_aspect_ratio": "pad",
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 13824,
|
16 |
+
"max_length": 4096,
|
17 |
+
"max_position_embeddings": 4096,
|
18 |
+
"mm_hidden_size": 7680,
|
19 |
+
"mm_patch_merge_type": "flat",
|
20 |
+
"mm_projector_lr": null,
|
21 |
+
"mm_projector_query_number": 128,
|
22 |
+
"mm_projector_type": "mlp2x_gelu",
|
23 |
+
"mm_use_im_patch_token": false,
|
24 |
+
"mm_use_im_start_end": false,
|
25 |
+
"mm_vision_select_feature": "patch",
|
26 |
+
"mm_vision_select_layer": -2,
|
27 |
+
"mm_vision_tower": "clip-448;convnext-1024;sam-1024;det-1024;pix2struct-1024",
|
28 |
+
"model_type": "eagle_llama",
|
29 |
+
"num_attention_heads": 40,
|
30 |
+
"num_hidden_layers": 40,
|
31 |
+
"num_key_value_heads": 40,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"pretraining_tp": 1,
|
34 |
+
"rms_norm_eps": 1e-05,
|
35 |
+
"rope_scaling": null,
|
36 |
+
"rope_theta": 10000.0,
|
37 |
+
"tie_word_embeddings": false,
|
38 |
+
"tokenizer_model_max_length": 2048,
|
39 |
+
"tokenizer_padding_side": "right",
|
40 |
+
"torch_dtype": "bfloat16",
|
41 |
+
"transformers_version": "4.37.2",
|
42 |
+
"tune_mm_mlp_adapter": false,
|
43 |
+
"use_cache": true,
|
44 |
+
"use_mm_proj": true,
|
45 |
+
"vocab_size": 32000
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"max_length": 4096,
|
7 |
+
"pad_token_id": 0,
|
8 |
+
"temperature": 0.9,
|
9 |
+
"top_p": 0.6,
|
10 |
+
"transformers_version": "4.37.2"
|
11 |
+
}
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d25bd88d5d5b7afe3beaac65b7fa8efbc4f11556931377bbca3c3f41a4baa3
|
3 |
+
size 4978265800
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77ba674c8a695f55dbcd74663b828630ac81753ea9a6c3a98cc6b76e505389e5
|
3 |
+
size 4970422232
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3783f2cddb767bb7de2e13dbaf712b46b9c6206debe84df9a765e5d5269d168
|
3 |
+
size 4970422256
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cbf34e1be1ecb74d8f56919427739418a8912511e66d5f5903a1065323dc363
|
3 |
+
size 4933701504
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cd43d5673d461970e2abd59030c8453106845df1bc2ff3ff3902658d3d47122
|
3 |
+
size 4933722216
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdf82ca8788a346bc59c67e7a8e7ee536ac437f7b95742f46404c6f265e7178c
|
3 |
+
size 4995933256
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8107724aa2951710813865aa1d2d2460ce3c0f773927bc5208c9b1e58a52429d
|
3 |
+
size 938960672
|
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 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 2048,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
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:a40ff1bf0f407773fd779adca25311120ea0f04ec144f37081f931ee9416888a
|
3 |
+
size 6392
|