chaoyinshe commited on
Commit
be6c531
·
verified ·
1 Parent(s): f25627b

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/user02/SCY/VLM/my_vlm/checkpoints/Qwen2VL_MOE_stage1",
3
+ "architectures": [
4
+ "Qwen2VLMOEForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "moe_intermediate_size": 1408,
18
+ "norm_topk_prob": false,
19
+ "num_attention_heads": 28,
20
+ "num_experts": 4,
21
+ "num_experts_per_tok": 2,
22
+ "num_hidden_layers": 28,
23
+ "num_key_value_heads": 4,
24
+ "output_router_logits": true,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_scaling": {
27
+ "mrope_section": [
28
+ 16,
29
+ 24,
30
+ 24
31
+ ],
32
+ "rope_type": "default",
33
+ "type": "default"
34
+ },
35
+ "rope_theta": 1000000.0,
36
+ "router_aux_loss_coef": 0.001,
37
+ "shared_expert_intermediate_size": 5632,
38
+ "sliding_window": 32768,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.47.0",
42
+ "use_cache": true,
43
+ "use_sliding_window": false,
44
+ "video_token_id": 151656,
45
+ "vision_config": {
46
+ "in_chans": 3,
47
+ "model_type": "qwen2_vl",
48
+ "spatial_patch_size": 14
49
+ },
50
+ "vision_end_token_id": 151653,
51
+ "vision_start_token_id": 151652,
52
+ "vision_token_id": 151654,
53
+ "vocab_size": 152064
54
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "temperature": 0.01,
11
+ "top_k": 1,
12
+ "top_p": 0.001,
13
+ "transformers_version": "4.47.0"
14
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc884b3225a5ec7403ac3184c538a1d52953ae41c67835a050a489faec769537
3
+ size 6872785360
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06207e4b4bd87d680203b340b1219f79118af18e8bcd0b6d85dfce90b955e59d
3
+ size 4877533760
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:356447f781cc45884462ae2d402899be7f74299d837db083503307b1b1f01603
3
+ size 4991495816
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d41cce20d2d26fe6b9f64779a6982d1630b4ee24153c1e0ed26221dd4ba4b4f6
3
+ size 4932751040
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7873b86c015351c0a55532134cd0960a15ca77d13932bc6fe4d0466e000a8e7e
3
+ size 1691924384
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff