Skip to content

Commit

Permalink
wip
Browse files Browse the repository at this point in the history
  • Loading branch information
matatonic committed Jul 15, 2024
1 parent 0e5d945 commit 72b248e
Show file tree
Hide file tree
Showing 3 changed files with 15 additions and 20 deletions.
7 changes: 3 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ An OpenAI API compatible vision server, it functions like `gpt-4-vision-preview`
## Model support

- [X] [OpenGVLab](https://huggingface.co/OpenGVLab)
- - [ ] [InternVL2-40B](https://huggingface.co/OpenGVLab/InternVL2-40B) (currently errors)
- - [X] [InternVL2-40B](https://huggingface.co/OpenGVLab/InternVL2-40B)
- - [X] [InternVL2-26B](https://huggingface.co/OpenGVLab/InternVL2-26B)
- - [X] [InternVL2-8B](https://huggingface.co/OpenGVLab/InternVL2-8B)
- - [X] [InternVL2-4B](https://huggingface.co/OpenGVLab/InternVL2-4B) (alternate docker only)
Expand Down Expand Up @@ -49,7 +49,7 @@ An OpenAI API compatible vision server, it functions like `gpt-4-vision-preview`
- - [X] [360VL-8B](https://huggingface.co/qihoo360/360VL-8B)
- - [X] [360VL-70B](https://huggingface.co/qihoo360/360VL-70B) (untested)
- [X] [LlavaNext](https://huggingface.co/llava-hf)
- - [X] [llava-v1.6-34b-hf](https://huggingface.co/llava-hf/llava-v1.6-34b-hf) (currently errors, use an image before 0.26.0)
- - [X] [llava-v1.6-34b-hf](https://huggingface.co/llava-hf/llava-v1.6-34b-hf)
- - [X] [llava-v1.6-vicuna-13b-hf](https://huggingface.co/llava-hf/llava-v1.6-vicuna-13b-hf)
- - [X] [llava-v1.6-vicuna-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-vicuna-7b-hf)
- - [X] [llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf)
Expand Down Expand Up @@ -115,8 +115,7 @@ See: [OpenVLM Leaderboard](https://huggingface.co/spaces/opencompass/open_vlm_le

Version 0.27.0

- new model support: OpenGVLab/InternVL2 series of models (40B still has errors, 4B requires alternate docker image)
-
- new model support: OpenGVLab/InternVL2 series of models (1B, 2B, 4B, 8B*, 26B*, 40B*) - *(current top open source models)

Version 0.26.0

Expand Down
4 changes: 0 additions & 4 deletions model_conf_tests.alt.json
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,5 @@
["YanweiLi/MGM-8x7B", "--use-flash-attn"],
["YanweiLi/MGM-8x7B-HD", "--load-in-4bit", "--use-flash-attn"],
["YanweiLi/MGM-8x7B-HD", "--use-flash-attn"],
["internlm/internlm-xcomposer2-4khd-7b", "--use-flash-attn", "--device-map", "cuda:0", "--load-in-4bit"],
["internlm/internlm-xcomposer2-7b", "--use-flash-attn", "--device-map", "cuda:0", "--load-in-4bit"],
["internlm/internlm-xcomposer2-vl-1_8b", "--use-flash-attn", "--device-map", "cuda:0", "--load-in-4bit"],
["internlm/internlm-xcomposer2-vl-7b", "--use-flash-attn", "--device-map", "cuda:0", "--load-in-4bit"],
["vikhyatk/moondream1"]
]
24 changes: 12 additions & 12 deletions model_conf_tests.json
Original file line number Diff line number Diff line change
Expand Up @@ -25,18 +25,18 @@
["OpenGVLab/InternVL-Chat-V1-5", "--device-map", "cuda:0", "--max-tiles", "40"],
["OpenGVLab/InternVL-Chat-V1-5", "--device-map", "cuda:0"],
["OpenGVLab/InternVL-Chat-V1-5-Int8", "--device-map", "cuda:0"],
["OpenGVLab/InternVL2-1B", "--load-in-4bit"],
["OpenGVLab/InternVL2-1B"],
["OpenGVLab/InternVL2-2B", "--load-in-4bit"],
["OpenGVLab/InternVL2-2B"],
["OpenGVLab/InternVL2-4B", "--load-in-4bit"],
["OpenGVLab/InternVL2-4B"],
["OpenGVLab/InternVL2-8B", "--load-in-4bit"],
["OpenGVLab/InternVL2-8B"],
["OpenGVLab/InternVL2-26B", "--load-in-4bit"],
["OpenGVLab/InternVL2-26B"],
["OpenGVLab/InternVL2-40B", "--load-in-4bit"],
["OpenGVLab/InternVL2-40B"],
["OpenGVLab/InternVL2-1B", "--device-map", "cuda:0", "--load-in-4bit"],
["OpenGVLab/InternVL2-1B", "--device-map", "cuda:0"],
["OpenGVLab/InternVL2-2B", "--device-map", "cuda:0", "--load-in-4bit"],
["OpenGVLab/InternVL2-2B", "--device-map", "cuda:0"],
["OpenGVLab/InternVL2-4B", "--device-map", "cuda:0", "--load-in-4bit"],
["OpenGVLab/InternVL2-4B", "--device-map", "cuda:0"],
["OpenGVLab/InternVL2-8B", "--device-map", "cuda:0", "--load-in-4bit"],
["OpenGVLab/InternVL2-8B", "--device-map", "cuda:0"],
["OpenGVLab/InternVL2-26B", "--device-map", "cuda:0", "--load-in-4bit"],
["OpenGVLab/InternVL2-26B", "--device-map", "cuda:0"],
["OpenGVLab/InternVL2-40B", "--device-map", "cuda:0", "--load-in-4bit"],
["OpenGVLab/InternVL2-40B", "--device-map", "cuda:0"],
["OpenGVLab/Mini-InternVL-Chat-2B-V1-5", "--load-in-4bit"],
["OpenGVLab/Mini-InternVL-Chat-2B-V1-5", "--max-tiles", "40", "--load-in-4bit"],
["OpenGVLab/Mini-InternVL-Chat-2B-V1-5", "--max-tiles", "40"],
Expand Down

0 comments on commit 72b248e

Please sign in to comment.