Hugging Face's logo

AXERA-TECH
/
Qwen3-VL-4B-Instruct-GPTQ-Int4

Image-Text-to-Text
Transformers
English
Chinese
Qwen3-VL
Qwen3-VL-2B-Instruct
Qwen3-VL-4B-Instruct
Int4
VLM
GPTQ
Model card Files
xet
Community
1
lihongjie commited on
Commit
20aa145
·
1 Parent(s): 691362f

first commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +56 -35
  2. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/Qwen3-VL-4B-Instruct_vision.axmodel +3 -0
  3. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/model.embed_tokens.weight.bfloat16.bin +3 -0
  4. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l0_together.axmodel +3 -0
  5. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l10_together.axmodel +3 -0
  6. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l11_together.axmodel +3 -0
  7. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l12_together.axmodel +3 -0
  8. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l13_together.axmodel +3 -0
  9. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l14_together.axmodel +3 -0
  10. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l15_together.axmodel +3 -0
  11. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l16_together.axmodel +3 -0
  12. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l17_together.axmodel +3 -0
  13. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l18_together.axmodel +3 -0
  14. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l19_together.axmodel +3 -0
  15. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l1_together.axmodel +3 -0
  16. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l20_together.axmodel +3 -0
  17. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l21_together.axmodel +3 -0
  18. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l22_together.axmodel +3 -0
  19. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l23_together.axmodel +3 -0
  20. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l24_together.axmodel +3 -0
  21. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l25_together.axmodel +3 -0
  22. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l26_together.axmodel +3 -0
  23. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l27_together.axmodel +3 -0
  24. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l28_together.axmodel +3 -0
  25. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l29_together.axmodel +3 -0
  26. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l2_together.axmodel +3 -0
  27. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l30_together.axmodel +3 -0
  28. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l31_together.axmodel +3 -0
  29. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l32_together.axmodel +3 -0
  30. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l33_together.axmodel +3 -0
  31. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l34_together.axmodel +3 -0
  32. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l35_together.axmodel +3 -0
  33. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l3_together.axmodel +3 -0
  34. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l4_together.axmodel +3 -0
  35. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l5_together.axmodel +3 -0
  36. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l6_together.axmodel +3 -0
  37. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l7_together.axmodel +3 -0
  38. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l8_together.axmodel +3 -0
  39. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l9_together.axmodel +3 -0
  40. Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_post.axmodel +3 -0
  41. README.md +257 -3
  42. config.json +0 -0
  43. images/demo.jpg +3 -0
  44. images/demo1.jpg +3 -0
  45. images/recoAll_attractions_1.jpg +3 -0
  46. images/recoAll_attractions_2.jpg +3 -0
  47. images/recoAll_attractions_3.jpg +3 -0
  48. images/recoAll_attractions_4.jpg +3 -0
  49. images/ssd_car.jpg +3 -0
  50. images/ssd_horse.jpg +3 -0
.gitattributes CHANGED
@@ -1,35 +1,56 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz 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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l29_together.axmodel filter=lfs diff=lfs merge=lfs -text
2
+ images/ssd_horse.jpg filter=lfs diff=lfs merge=lfs -text
3
+ video/frame_0008.jpg filter=lfs diff=lfs merge=lfs -text
4
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l13_together.axmodel filter=lfs diff=lfs merge=lfs -text
5
+ images/recoAll_attractions_2.jpg filter=lfs diff=lfs merge=lfs -text
6
+ video/frame_0024.jpg filter=lfs diff=lfs merge=lfs -text
7
+ images/recoAll_attractions_3.jpg filter=lfs diff=lfs merge=lfs -text
8
+ video/frame_0032.jpg filter=lfs diff=lfs merge=lfs -text
9
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l0_together.axmodel filter=lfs diff=lfs merge=lfs -text
10
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l11_together.axmodel filter=lfs diff=lfs merge=lfs -text
11
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l15_together.axmodel filter=lfs diff=lfs merge=lfs -text
12
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l20_together.axmodel filter=lfs diff=lfs merge=lfs -text
13
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l14_together.axmodel filter=lfs diff=lfs merge=lfs -text
14
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l4_together.axmodel filter=lfs diff=lfs merge=lfs -text
15
+ images/recoAll_attractions_4.jpg filter=lfs diff=lfs merge=lfs -text
16
+ video/frame_0040.jpg filter=lfs diff=lfs merge=lfs -text
17
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l22_together.axmodel filter=lfs diff=lfs merge=lfs -text
18
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l33_together.axmodel filter=lfs diff=lfs merge=lfs -text
19
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l7_together.axmodel filter=lfs diff=lfs merge=lfs -text
20
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l19_together.axmodel filter=lfs diff=lfs merge=lfs -text
21
+ images/demo.jpg filter=lfs diff=lfs merge=lfs -text
22
+ video/frame_0048.jpg filter=lfs diff=lfs merge=lfs -text
23
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l26_together.axmodel filter=lfs diff=lfs merge=lfs -text
24
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l27_together.axmodel filter=lfs diff=lfs merge=lfs -text
25
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l2_together.axmodel filter=lfs diff=lfs merge=lfs -text
26
+ images/recoAll_attractions_1.jpg filter=lfs diff=lfs merge=lfs -text
27
+ video/frame_0056.jpg filter=lfs diff=lfs merge=lfs -text
28
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/model.embed_tokens.weight.bfloat16.bin filter=lfs diff=lfs merge=lfs -text
29
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l12_together.axmodel filter=lfs diff=lfs merge=lfs -text
30
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l17_together.axmodel filter=lfs diff=lfs merge=lfs -text
31
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/Qwen3-VL-4B-Instruct_vision.axmodel filter=lfs diff=lfs merge=lfs -text
32
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l16_together.axmodel filter=lfs diff=lfs merge=lfs -text
33
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l31_together.axmodel filter=lfs diff=lfs merge=lfs -text
34
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l32_together.axmodel filter=lfs diff=lfs merge=lfs -text
35
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l8_together.axmodel filter=lfs diff=lfs merge=lfs -text
36
+ images/ssd_car.jpg filter=lfs diff=lfs merge=lfs -text
37
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l10_together.axmodel filter=lfs diff=lfs merge=lfs -text
38
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l18_together.axmodel filter=lfs diff=lfs merge=lfs -text
39
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l35_together.axmodel filter=lfs diff=lfs merge=lfs -text
40
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l3_together.axmodel filter=lfs diff=lfs merge=lfs -text
41
+ images/demo1.jpg filter=lfs diff=lfs merge=lfs -text
42
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l6_together.axmodel filter=lfs diff=lfs merge=lfs -text
43
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l9_together.axmodel filter=lfs diff=lfs merge=lfs -text
44
+ video/frame_0016.jpg filter=lfs diff=lfs merge=lfs -text
45
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l25_together.axmodel filter=lfs diff=lfs merge=lfs -text
46
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l30_together.axmodel filter=lfs diff=lfs merge=lfs -text
47
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_post.axmodel filter=lfs diff=lfs merge=lfs -text
48
+ video/frame_0000.jpg filter=lfs diff=lfs merge=lfs -text
49
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l1_together.axmodel filter=lfs diff=lfs merge=lfs -text
50
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l23_together.axmodel filter=lfs diff=lfs merge=lfs -text
51
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l5_together.axmodel filter=lfs diff=lfs merge=lfs -text
52
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l24_together.axmodel filter=lfs diff=lfs merge=lfs -text
53
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l34_together.axmodel filter=lfs diff=lfs merge=lfs -text
54
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l21_together.axmodel filter=lfs diff=lfs merge=lfs -text
55
+ Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l28_together.axmodel filter=lfs diff=lfs merge=lfs -text
56
+ main_ax650 filter=lfs diff=lfs merge=lfs -text
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/Qwen3-VL-4B-Instruct_vision.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5e5ce705711ae0660a0fa849c154219eb97288c4fc3fa9e55f6a2c5d1bd099
3
+ size 461423557
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/model.embed_tokens.weight.bfloat16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2942e869a0df443edd3158b7f6c4f735f79faea563354b3a077db81f5f21edaa
3
+ size 777912320
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l0_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf8e61aa220a80ac61ab393b2b05474dd9ae9c7c9031befd16443dc026e2b52
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l10_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb9dc29dc284981482280f3a43847d7b5d9f99f307f2f219a2dafe12644f21e
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l11_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3fee27aa23f0c7f0b7d25ba9ab36ec1dfef777505cecfb8fd52e9caa58e5da
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l12_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5be834d391633438dd4b7149453492118c575f53bba68f02edb1ca856b4af577
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l13_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06041b232d361727bb6511320ce7407fa6b5c3551a99d6bb19a996322923d7bf
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l14_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f55f6bd73ac57840a97426036e45deaaa24d44ef985f2a3c0ea38d702d329a
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l15_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337384b91fa8f6aee83136d25a259fa360e119feb33680e770a0babe6b776e89
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l16_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3baadd9f5230cb92fb4207bc88d2d254d82a6c9719714369ff638113b907ce06
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l17_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77906277d424a85572156865134b9b92d6a03c38cdbb0fc59db09a440e435269
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l18_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ff17fc2fcee8c1eaa599e61696d4a09021b760569462c23d1b34a88e741eff
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l19_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5ae0e6d4cf3d637baae8c3094632b41507e58359c0e0232ba641246d27c358
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l1_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e8fa5562a601dffca0453340796431c005c60ef3574adb4b23cc0b09fc0f98a
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l20_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3880c7a57b7ffa2e6f628bcf9885a8cc919b104e931f8d06c485063b3ad5398c
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l21_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95a838b55b5da19dc8f69bd144dc427a9550fc9b96dcda452d85dc8586ce69d
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l22_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aaa8d79bc1db8c2fba7ff9578e87c2201b73f3250cfbd53d106e4d5ca6e9d4a
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l23_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f183a6e553ed7b82d8ead8d29bd1e8d2260aff6f865ada242c0ec939afb1e99e
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l24_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27623f138c3f994f9c6d2d666d83d08b0ddab6c276402963a763c057ab57041a
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l25_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d3eedb056d987f3c555940dd0277c29ebe86b2b7fee5151559b40184b312e23
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l26_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377c0ba1d595d1d53a92fdbc31866ae012a6431f6579a62a4e9cf4fe9ed0c599
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l27_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:501e10ba64d76c09d12d3470dd042f4153c220a685514ffcada6d7bd0e4d447a
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l28_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48eda5a7a8b376f3c2a1e8762c8a764dd370257c9e751a66d62dbea40c939f8
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l29_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500191aecf1ee95bd3350bf72b0795bfa787d04dda1f2ed041bbfc2e512a95c2
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l2_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d165dbdcb653eacafac3bb44462a0511891033fe2a0149d17540188810085ae
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l30_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0cb3ea07659d0a2a2b285d9839fdfa234455d97933eebf3664a0dd7258149bd
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l31_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:028f8dad6a872d949b4c505c76ceb794e9d9956131b6dfc2d6086389904a145a
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l32_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcf18e785121375dab0d7d5bca441e356aed46efc978eed1ba5b7458f34d55b
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l33_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5534a4b1e6612071447e4f0615ec45997d0142f61eaffd6731fdcfd5ed0acc9
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l34_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715ef73de0a8f14c2f8ea71f7e84435a90a96d3e78cace5f02309ad3b84cab75
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l35_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472afb7ee42c754ec8cd39c7c0a99648c64330008db2be23b5f5b1cb082cdd54
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l3_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06cc06a36a0f9a9ea3845cb19c5e37765658ca53c54e9dd303c816300de647c4
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l4_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47bb93d82cdfe96116b246b472a296f452c23047cbadae7dba02aaaa56e81cc
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l5_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd00bf513f2f6e689aaa0d984f743852af909b4de068f584bb1d66200330156
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l6_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef4c75d495d046b4838d1417e6db830bf9532b43f445bd2bccd2136504e7c0b
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l7_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb8e8a08fbca9b92127b390ca60473334d90f5b03558a73fc216b7dd9a2a648
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l8_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6f8130116558ae18fae8946ee00c8095bde8a040e1e44e31f5ea8846d76f81
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_p128_l9_together.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6021c3fbee01675a758d26fbfd4c4a33d37fbc74664aa523c67bafc4e98ad803
3
+ size 82215119
Qwen3-VL-4B-Instruct-AX650-c128_p1152-int4/qwen3_vl_text_post.axmodel ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b97d6f2daab1ff9d0e6ed2f2a77203c500556273409cb4acd0e5fecbbdf5315
3
+ size 424045076
README.md CHANGED
@@ -1,3 +1,257 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ - zh
6
+ base_model:
7
+ - Qwen/Qwen3-VL-2B-Instruct
8
+ - Qwen/Qwen3-VL-4B-Instruct
9
+ pipeline_tag: image-text-to-text
10
+ library_name: transformers
11
+ tags:
12
+ - Qwen3-VL
13
+ - Qwen3-VL-2B-Instruct
14
+ - Qwen3-VL-4B-Instruct
15
+ - Int4
16
+ - VLM
17
+ - GPTQ
18
+ ---
19
+
20
+ # Qwen3-VL-2B-Instruct-GPTQ-Int4
21
+
22
+ This version of Qwen3-VL-4B-Instruct have been converted to run on the Axera NPU using **w4a16** quantization.
23
+
24
+ Compatible with Pulsar2 version: 5.0
25
+
26
+ ## Convert tools links:
27
+
28
+ For those who are interested in model conversion, you can try to export axmodel through the original repo :
29
+
30
+ - https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct
31
+ - https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct
32
+
33
+ [Pulsar2 Link, How to Convert LLM from Huggingface to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/appendix/build_llm.html)
34
+
35
+ [AXera NPU HOST LLM Runtime](https://github.com/AXERA-TECH/Qwen3-VL.AXERA)
36
+
37
+
38
+ ## Support Platform
39
+
40
+ - AX650
41
+ - AX650N DEMO Board
42
+ - [M4N-Dock(爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html)
43
+ - [M.2 Accelerator card](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html)
44
+
45
+ **Image Process**
46
+ |Chips| input size | image num | image encoder | ttft(320 tokens) | w4a16 | CMM | Flash |
47
+ |--|--|--|--|--|--|--|--|
48
+ |AX650| 384*384 | 1 | 222 ms | 678 ms | 7.0 tokens/sec| 5.6GiB | 5.6GiB |
49
+
50
+ **Video Process**
51
+ |Chips| input size | image num | image encoder |ttft(600 tokens) | w4a16 | CMM | Flash |
52
+ |--|--|--|--|--|--|--|--|
53
+ |AX650| 384*384 | 8 | 773 ms | 1887 ms | 7.1 tokens/sec| 5.6GiB | 5.6GiB |
54
+
55
+ The DDR capacity refers to the CMM memory that needs to be consumed. Ensure that the CMM memory allocation on the development board is greater than this value.
56
+
57
+ ## How to use
58
+
59
+ Download all files from this repository to the device
60
+
61
+ **If you using AX650 Board**
62
+
63
+ ### Prepare tokenizer server
64
+
65
+ #### Install transformer
66
+
67
+ ```
68
+ pip install -r requirements.txt
69
+ ```
70
+
71
+ ### Demo Run
72
+
73
+ #### Image understand demo
74
+
75
+ ##### start tokenizer server for image understand demo
76
+
77
+ ```
78
+ python3 tokenizer_images.py --port 8080
79
+ ```
80
+
81
+ ##### run image understand demo
82
+
83
+ - input text
84
+
85
+ ```
86
+ 描述这张图片
87
+ ```
88
+
89
+ - input image
90
+
91
+ ![](./images/recoAll_attractions_1.jpg)
92
+
93
+ ```
94
+ root@ax650 ~/Qwen3-VL-4B-Instruct-GPTQ-Int4 # bash run_image_ax650.sh
95
+ [I][ Init][ 156]: LLM init start
96
+ [I][ Init][ 158]: Total CMM:7884 MB
97
+ [I][ Init][ 34]: connect http://127.0.0.1:8080 ok
98
+ bos_id: -1, eos_id: 151645
99
+ img_start_token: 151652
100
+ img_context_token: 151655
101
+ 2% | █ | 1 / 39 [0.01s<0.58s, 66.67 count/s] tokenizer init ok[I][ Init][ 26]: LLaMaEmbedSelector use mmap
102
+ 5% | ██ | 2 / 39 [0.02s<0.37s, 105.26 count/s] embed_selector init ok[I][ Init][ 201]: attr.axmodel_num:36
103
+ 102% | █████████████████████████████████ | 40 / 39 [11.33s<11.05s, 3.53 count/s] init vpm axmodel ok,remain_cmm(2199 MB)[I][ Init][ 266]: IMAGE_CONTEXT_TOKEN: 151655, IMAGE_START_TOKEN: 151652
104
+ [I][ Init][ 309]: image encoder output float32
105
+
106
+ [I][ Init][ 339]: max_token_len : 2047
107
+ [I][ Init][ 344]: kv_cache_size : 1024, kv_cache_num: 2047
108
+ [I][ Init][ 352]: prefill_token_num : 128
109
+ [I][ Init][ 356]: grp: 1, prefill_max_token_num : 1
110
+ [I][ Init][ 356]: grp: 2, prefill_max_token_num : 128
111
+ [I][ Init][ 356]: grp: 3, prefill_max_token_num : 256
112
+ [I][ Init][ 356]: grp: 4, prefill_max_token_num : 384
113
+ [I][ Init][ 356]: grp: 5, prefill_max_token_num : 512
114
+ [I][ Init][ 356]: grp: 6, prefill_max_token_num : 640
115
+ [I][ Init][ 356]: grp: 7, prefill_max_token_num : 768
116
+ [I][ Init][ 356]: grp: 8, prefill_max_token_num : 896
117
+ [I][ Init][ 356]: grp: 9, prefill_max_token_num : 1024
118
+ [I][ Init][ 356]: grp: 10, prefill_max_token_num : 1152
119
+ [I][ Init][ 360]: prefill_max_token_num : 1152
120
+ [I][ Init][ 372]: LLM init ok
121
+ [I][ Init][ 374]: Left CMM:2199 MB
122
+ Type "q" to exit, Ctrl+c to stop current running
123
+ prompt >> 描述这张图片
124
+ image >> images/recoAll_attractions_1.jpg
125
+ [I][ EncodeImage][ 440]: pixel_values size 1
126
+ [I][ EncodeImage][ 441]: grid_h 24 grid_w 24
127
+ [I][ EncodeImage][ 489]: image encode time : 222.440994 ms, size : 1
128
+ [I][ Encode][ 532]: input_ids size:168
129
+ [I][ Encode][ 540]: offset 15
130
+ [I][ Encode][ 569]: img_embed.size:1, 368640
131
+ [I][ Encode][ 583]: out_embed size:430080
132
+ [I][ Encode][ 584]: input_ids size 168
133
+ [I][ Encode][ 586]: position_ids size:168
134
+ [I][ Run][ 607]: input token num : 168, prefill_split_num : 2
135
+ [I][ Run][ 641]: input_num_token:128
136
+ [I][ Run][ 641]: input_num_token:40
137
+ [I][ Run][ 865]: ttft: 676.16 ms
138
+ 这张图片展示了埃及吉萨的金字塔群，背景是晴朗的蓝天，前景是广阔的沙漠。
139
+
140
+ 画面中主要可见三座金字塔：
141
+ - 最大的一座是著名的**胡夫金字塔**，它位于画面中央偏左，是三座金字塔中最高、最显眼的。
142
+ - 在其右侧，是稍小一些的**卡纳克金字塔**（或称“卡纳克金字塔”）。
143
+ - 在画面最左侧，可以看到一座更小的金字塔，可能是**门卡乌金字塔**或**哈夫拉金字塔**。
144
+
145
+ 这三座金字塔都是古埃及法老的陵墓，是古代世界七大奇迹中唯一现存的。它们的结构和规模令人惊叹，体现了古埃及人在建筑、数学和天文学方面的卓越成就。
146
+
147
+ 整个场景在阳光下显得庄严而神秘，是埃及最具代表性的历史遗迹之一。
148
+
149
+ [N][ Run][ 992]: hit eos,avg 7.12 token/s
150
+ ```
151
+
152
+ #### Video understand demo
153
+
154
+ ##### start tokenizer server for image understand demo
155
+
156
+ ```
157
+ python tokenizer_video.py --port 8080
158
+ ```
159
+
160
+ ##### run video understand demo
161
+ - input text
162
+
163
+ ```
164
+ 描述这个视频
165
+ ```
166
+
167
+ - input video
168
+
169
+ ./video
170
+
171
+ ```
172
+ root@ax650 ~/Qwen3-VL-4B-Instruct-GPTQ-Int4 # bash run_video_ax650.sh
173
+ [I][ Init][ 156]: LLM init start
174
+ [I][ Init][ 158]: Total CMM:7884 MB
175
+ [I][ Init][ 34]: connect http://127.0.0.1:8080 ok
176
+ bos_id: -1, eos_id: 151645
177
+ img_start_token: 151652
178
+ img_context_token: 151656
179
+ 2% | █ | 1 / 39 [0.02s<0.62s, 62.50 count/s] tokenizer init ok[I][ Init][ 26]: LLaMaEmbedSelector use mmap
180
+ 5% | ██ | 2 / 39 [0.02s<0.39s, 100.00 count/s] embed_selector init ok[I][ Init][ 201]: attr.axmodel_num:36
181
+ 102% | █████████████████████████████████ | 40 / 39 [44.70s<43.58s, 0.89 count/s] init vpm axmodel ok,remain_cmm(2199 MB)[I][ Init][ 266]: IMAGE_CONTEXT_TOKEN: 151656, IMAGE_START_TOKEN: 151652
182
+ [I][ Init][ 309]: image encoder output float32
183
+
184
+ [I][ Init][ 339]: max_token_len : 2047
185
+ [I][ Init][ 344]: kv_cache_size : 1024, kv_cache_num: 2047
186
+ [I][ Init][ 352]: prefill_token_num : 128
187
+ [I][ Init][ 356]: grp: 1, prefill_max_token_num : 1
188
+ [I][ Init][ 356]: grp: 2, prefill_max_token_num : 128
189
+ [I][ Init][ 356]: grp: 3, prefill_max_token_num : 256
190
+ [I][ Init][ 356]: grp: 4, prefill_max_token_num : 384
191
+ [I][ Init][ 356]: grp: 5, prefill_max_token_num : 512
192
+ [I][ Init][ 356]: grp: 6, prefill_max_token_num : 640
193
+ [I][ Init][ 356]: grp: 7, prefill_max_token_num : 768
194
+ [I][ Init][ 356]: grp: 8, prefill_max_token_num : 896
195
+ [I][ Init][ 356]: grp: 9, prefill_max_token_num : 1024
196
+ [I][ Init][ 356]: grp: 10, prefill_max_token_num : 1152
197
+ [I][ Init][ 360]: prefill_max_token_num : 1152
198
+ [I][ Init][ 372]: LLM init ok
199
+ [I][ Init][ 374]: Left CMM:2199 MB
200
+ Type "q" to exit, Ctrl+c to stop current running
201
+ prompt >> 描述这个视频
202
+ video >> video
203
+ video/frame_0000.jpg
204
+ video/frame_0008.jpg
205
+ video/frame_0016.jpg
206
+ video/frame_0024.jpg
207
+ video/frame_0032.jpg
208
+ video/frame_0040.jpg
209
+ video/frame_0048.jpg
210
+ video/frame_0056.jpg
211
+ [I][ EncodeImage][ 440]: pixel_values size 4
212
+ [I][ EncodeImage][ 441]: grid_h 24 grid_w 24
213
+ [I][ EncodeImage][ 489]: image encode time : 773.406006 ms, size : 4
214
+ [I][ Encode][ 532]: input_ids size:600
215
+ [I][ Encode][ 540]: offset 15
216
+ [I][ Encode][ 569]: img_embed.size:4, 368640
217
+ [I][ Encode][ 574]: offset:159
218
+ [I][ Encode][ 574]: offset:303
219
+ [I][ Encode][ 574]: offset:447
220
+ [I][ Encode][ 583]: out_embed size:1536000
221
+ [I][ Encode][ 584]: input_ids size 600
222
+ [I][ Encode][ 586]: position_ids size:600
223
+ [I][ Run][ 607]: input token num : 600, prefill_split_num : 5
224
+ [I][ Run][ 641]: input_num_token:128
225
+ [I][ Run][ 641]: input_num_token:128
226
+ [I][ Run][ 641]: input_num_token:128
227
+ [I][ Run][ 641]: input_num_token:128
228
+ [I][ Run][ 641]: input_num_token:88
229
+
230
+ [I][ Run][ 865]: ttft: 1886.83 ms
231
+ 这个视频展示了一群**土拨鼠**（或称“旱獭”）在山间草地上嬉戏打斗的场景。
232
+
233
+ **画面细节：**
234
+
235
+ - **主体动物**：画面中有多只土拨鼠，它们毛色以灰、棕、白相间，腹部和四肢颜色较浅，背部较深。它们体型圆润，耳朵短小，表情生动。
236
+ - **动作**：这些土拨鼠似乎在进行一场“打斗”或“嬉戏”。它们互相扑腾、跳跃、用前爪拍打、甚至互相“拥抱”或“推搡”。动作非常活跃，充满动感，有些画面甚至有轻微的运动模糊，增强了动态感。
237
+ - **背景**：背景是连绵起伏的山峦，山坡上覆盖着绿色植被，远处可见裸露的岩石和山体，天空湛蓝，阳光明媚，说明是白天晴朗的天气。
238
+ - **前景**：它们站在一片布满小石子和草的地面，看起来像是山间小径或开阔地。
239
+ - **构图**：画面采用近景特写，聚焦于土拨鼠的互动，背景虚化，突出了主体的动态和表情。整体构图充满活力和趣味性。
240
+
241
+ **风格与氛围：**
242
+
243
+ - ��张图片/视频具有**拟人化和趣味性**，土拨鼠的动作被夸张化，仿佛在“打斗”或“跳舞”，非常可爱。
244
+ - 画面色彩明亮，阳光充足，给人一种**自然、活泼、欢乐**的感觉。
245
+
246
+ **总结：**
247
+
248
+ 这是一段充满趣味和活力的野生动物短片，展现了土拨鼠在自然环境中的社交行为，它们的“打斗”其实可能是玩耍、争夺领地或建立社交关系的自然行为。整体画面生动、可爱，极具观赏性。
249
+
250
+ ---
251
+
252
+ **注意**：虽然土拨鼠（旱獭）在野外确实会互相打斗，但这种“打斗”通常是**玩耍或社交行为**，并非真正的攻击。视频中的“打斗”更像是它们的社交互动，非常可爱。
253
+
254
+ [N][ Run][ 992]: hit eos,avg 7.10 token/s
255
+
256
+ prompt >> q
257
+ ```
config.json ADDED
File without changes
images/demo.jpg ADDED

Git LFS Details

  • SHA256: 344d5f0e43bfd6a4a6ed655dc9c3dc76a2a6ecb1de3afeee998e61722378e8b3
  • Pointer size: 130 Bytes
  • Size of remote file: 64.5 kB
images/demo1.jpg ADDED

Git LFS Details

  • SHA256: 8d6156cbaa86cf0f4a9ebbfc8c2bf307dcf6fc64e32176d69333f6f7c7b294c5
  • Pointer size: 131 Bytes
  • Size of remote file: 101 kB
images/recoAll_attractions_1.jpg ADDED

Git LFS Details

  • SHA256: 0072430513e76580c4134b78e452a1fb729112fe5725d1f8481e697c7b5cd4a1
  • Pointer size: 130 Bytes
  • Size of remote file: 73.3 kB
images/recoAll_attractions_2.jpg ADDED

Git LFS Details

  • SHA256: 28acba6c284d06039ca57c9ce182094baafa8a48b49068dc44482a6d643689cc
  • Pointer size: 131 Bytes
  • Size of remote file: 105 kB
images/recoAll_attractions_3.jpg ADDED

Git LFS Details

  • SHA256: f308b3ebb1855b74768d9a24a256616f683ba59e52c238326501f4008a3ab9a4
  • Pointer size: 130 Bytes
  • Size of remote file: 59.4 kB
images/recoAll_attractions_4.jpg ADDED

Git LFS Details

  • SHA256: e47e13a69c16073e221b143a43263fcbe956bcfeb8ad47fddbdbc03a2b6f7261
  • Pointer size: 131 Bytes
  • Size of remote file: 115 kB
images/ssd_car.jpg ADDED

Git LFS Details

  • SHA256: 92d459a39a9eef03956257cf9fec84114d9e5df8fb9c0662fb257488cdd4f365
  • Pointer size: 130 Bytes
  • Size of remote file: 50.5 kB
images/ssd_horse.jpg ADDED

Git LFS Details

  • SHA256: ed22f6b4c8c33e50e391e089ede14e8fa9402c623b09dbcf010e804770698fbb
  • Pointer size: 131 Bytes
  • Size of remote file: 123 kB