Hugging Face's logo

gaianet
/
Qwen2-VL-2B-Instruct-GGUF

Image-Text-to-Text
Transformers
GGUF
English
qwen2_vl
multimodal
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
c71aa8e
·
verified ·
1 Parent(s): 9b88468

Update models

Browse files
Files changed (16) hide show
  1. .gitattributes +14 -0
  2. Qwen2-VL-2B-Instruct-Q2_K.gguf +3 -0
  3. Qwen2-VL-2B-Instruct-Q3_K_L.gguf +3 -0
  4. Qwen2-VL-2B-Instruct-Q3_K_M.gguf +3 -0
  5. Qwen2-VL-2B-Instruct-Q3_K_S.gguf +3 -0
  6. Qwen2-VL-2B-Instruct-Q4_0.gguf +3 -0
  7. Qwen2-VL-2B-Instruct-Q4_K_M.gguf +3 -0
  8. Qwen2-VL-2B-Instruct-Q4_K_S.gguf +3 -0
  9. Qwen2-VL-2B-Instruct-Q5_0.gguf +3 -0
  10. Qwen2-VL-2B-Instruct-Q5_K_M.gguf +3 -0
  11. Qwen2-VL-2B-Instruct-Q5_K_S.gguf +3 -0
  12. Qwen2-VL-2B-Instruct-Q6_K.gguf +3 -0
  13. Qwen2-VL-2B-Instruct-Q8_0.gguf +3 -0
  14. Qwen2-VL-2B-Instruct-f16.gguf +3 -0
  15. Qwen2-VL-2B-Instruct-vision-encoder.gguf +3 -0
  16. config.json +52 -0
.gitattributes CHANGED
@@ -33,3 +33,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Qwen2-VL-2B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen2-VL-2B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen2-VL-2B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen2-VL-2B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen2-VL-2B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen2-VL-2B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen2-VL-2B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen2-VL-2B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen2-VL-2B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen2-VL-2B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen2-VL-2B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen2-VL-2B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Qwen2-VL-2B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Qwen2-VL-2B-Instruct-vision-encoder.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2-VL-2B-Instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe52033da710da3727f8aa1f18414254387dbb76689ccd4d45154e2dafbb3fa
3
+ size 676303328
Qwen2-VL-2B-Instruct-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb289177bcb04bec880720eb7a10890148f8a6586d911b921a301f55d632807
3
+ size 880161248
Qwen2-VL-2B-Instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d95410507ceeb499d7cb912764ce7d505968ecbdfa1e707cebf12a50565b4fb7
3
+ size 824177120
Qwen2-VL-2B-Instruct-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea1fa21e51590d13ed794650ebf00be700083c7f699966d415ff482ebc97801
3
+ size 760943072
Qwen2-VL-2B-Instruct-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478f7d105b903c22325c2d4b85e4aa94d1642106dc6488c5775e4f167c09b6b4
3
+ size 934953440
Qwen2-VL-2B-Instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20868587821c6b9f82089daac35918f8150c3568e3c4a2cdd51a24b6dd75ab79
3
+ size 986046944
Qwen2-VL-2B-Instruct-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d87cf355a2e6a802417bc6653edf73e29a7d024e4908231c9c54d6aa5e1460e0
3
+ size 940311008
Qwen2-VL-2B-Instruct-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a384294d51a53b61f75ea9a502ec6ad145c359b9297b1101494db16751dd30d
3
+ size 1098727904
Qwen2-VL-2B-Instruct-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1364671f4b4f1232082d8a523d2363446f963f3ccb2daa029349254617f79e9
3
+ size 1125048800
Qwen2-VL-2B-Instruct-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d982a094757fb549a1bde2af6e8925f55d788d34c103bfff4574028527220d
3
+ size 1098727904
Qwen2-VL-2B-Instruct-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7505e951bbeda59f36e0ff413f5a76fec9281f640613e549e0f4398329cf631
3
+ size 1272738272
Qwen2-VL-2B-Instruct-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11dff3f74b326668600607a04b412c320d9dfe917a77f48ed6abbd962dd4a44
3
+ size 1646571488
Qwen2-VL-2B-Instruct-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a5c76cbd1ccbc7a0ae9886099761aed1af564427fb9687c26a8dfb4066b74b
3
+ size 3093667808
Qwen2-VL-2B-Instruct-vision-encoder.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5a4e3b50652c60f7a027fb113d7e9d8f9411b0702f4de4e0743f71a3355530
3
+ size 2661115392
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "vision_start_token_id": 151652,
9
+ "vision_end_token_id": 151653,
10
+ "vision_token_id": 151654,
11
+ "image_token_id": 151655,
12
+ "video_token_id": 151656,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 1536,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 8960,
17
+ "max_position_embeddings": 32768,
18
+ "max_window_layers": 28,
19
+ "model_type": "qwen2_vl",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 28,
22
+ "num_key_value_heads": 2,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_theta": 1000000.0,
25
+ "sliding_window": 32768,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.41.2",
29
+ "use_cache": true,
30
+ "use_sliding_window": false,
31
+ "vision_config": {
32
+ "depth": 32,
33
+ "embed_dim": 1280,
34
+ "mlp_ratio": 4,
35
+ "num_heads": 16,
36
+ "in_chans": 3,
37
+ "hidden_size": 1536,
38
+ "patch_size": 14,
39
+ "spatial_merge_size": 2,
40
+ "spatial_patch_size": 14,
41
+ "temporal_patch_size": 2
42
+ },
43
+ "rope_scaling": {
44
+ "type": "mrope",
45
+ "mrope_section": [
46
+ 16,
47
+ 24,
48
+ 24
49
+ ]
50
+ },
51
+ "vocab_size": 151936
52
+ }