Upload Qwen2VLForConditionalGeneration
Browse files- config.json +73 -3
- model.safetensors +1 -1
config.json
CHANGED
@@ -19,15 +19,85 @@
|
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": {
|
21 |
"mrope_section": [
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
],
|
26 |
"rope_type": "default",
|
27 |
"type": "mrope"
|
28 |
},
|
29 |
"rope_theta": 1000000.0,
|
30 |
"sliding_window": 32768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.53.0",
|
33 |
"use_cache": true,
|
|
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": {
|
21 |
"mrope_section": [
|
22 |
+
8,
|
23 |
+
8,
|
24 |
+
16
|
25 |
],
|
26 |
"rope_type": "default",
|
27 |
"type": "mrope"
|
28 |
},
|
29 |
"rope_theta": 1000000.0,
|
30 |
"sliding_window": 32768,
|
31 |
+
"text_config": {
|
32 |
+
"architectures": [
|
33 |
+
"Qwen2VLForConditionalGeneration"
|
34 |
+
],
|
35 |
+
"attention_dropout": 0.0,
|
36 |
+
"bos_token_id": 151643,
|
37 |
+
"eos_token_id": 151645,
|
38 |
+
"hidden_act": "silu",
|
39 |
+
"hidden_size": 64,
|
40 |
+
"image_token_id": null,
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"intermediate_size": 8960,
|
43 |
+
"layer_types": [
|
44 |
+
"full_attention",
|
45 |
+
"full_attention",
|
46 |
+
"full_attention",
|
47 |
+
"full_attention",
|
48 |
+
"full_attention",
|
49 |
+
"full_attention",
|
50 |
+
"full_attention",
|
51 |
+
"full_attention",
|
52 |
+
"full_attention",
|
53 |
+
"full_attention",
|
54 |
+
"full_attention",
|
55 |
+
"full_attention",
|
56 |
+
"full_attention",
|
57 |
+
"full_attention",
|
58 |
+
"full_attention",
|
59 |
+
"full_attention",
|
60 |
+
"full_attention",
|
61 |
+
"full_attention",
|
62 |
+
"full_attention",
|
63 |
+
"full_attention",
|
64 |
+
"full_attention",
|
65 |
+
"full_attention",
|
66 |
+
"full_attention",
|
67 |
+
"full_attention",
|
68 |
+
"full_attention",
|
69 |
+
"full_attention",
|
70 |
+
"full_attention",
|
71 |
+
"full_attention"
|
72 |
+
],
|
73 |
+
"max_position_embeddings": 32768,
|
74 |
+
"max_window_layers": 28,
|
75 |
+
"model_type": "qwen2_vl_text",
|
76 |
+
"num_attention_heads": 1,
|
77 |
+
"num_hidden_layers": 1,
|
78 |
+
"num_key_value_heads": 2,
|
79 |
+
"rms_norm_eps": 1e-06,
|
80 |
+
"rope_scaling": {
|
81 |
+
"mrope_section": [
|
82 |
+
8,
|
83 |
+
8,
|
84 |
+
16
|
85 |
+
],
|
86 |
+
"rope_type": "default",
|
87 |
+
"type": "mrope"
|
88 |
+
},
|
89 |
+
"rope_theta": 1000000.0,
|
90 |
+
"sliding_window": null,
|
91 |
+
"tie_word_embeddings": true,
|
92 |
+
"torch_dtype": "float32",
|
93 |
+
"use_cache": true,
|
94 |
+
"use_sliding_window": false,
|
95 |
+
"video_token_id": null,
|
96 |
+
"vision_end_token_id": 151653,
|
97 |
+
"vision_start_token_id": 151652,
|
98 |
+
"vision_token_id": 151654,
|
99 |
+
"vocab_size": 151936
|
100 |
+
},
|
101 |
"torch_dtype": "float32",
|
102 |
"transformers_version": "4.53.0",
|
103 |
"use_cache": true,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 46711048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:746e651149d0c3fb563f963b92add3dc5c3bb14f46d8129cc8aa0ae1a658384f
|
3 |
size 46711048
|