LZHgrla commited on
Commit
1b4cb55
1 Parent(s): e4a6bde

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -7
README.md CHANGED
@@ -17,7 +17,7 @@ pipeline_tag: image-to-text
17
 
18
  llava-phi-3-mini is a LLaVA model fine-tuned from [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) and [CLIP-ViT-Large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) with [ShareGPT4V-PT](https://huggingface.co/datasets/Lin-Chen/ShareGPT4V) and [InternVL-SFT](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat#prepare-training-datasets) by [XTuner](https://github.com/InternLM/xtuner).
19
 
20
- **Note: This model is in GGUF format.**
21
 
22
  Resources:
23
 
@@ -54,10 +54,12 @@ Resources:
54
 
55
  ### Download models
56
 
57
- ```python
58
- from huggingface_hub import snapshot_download
 
59
 
60
- snapshot_download(repo_id='xtuner/llava-phi-3-mini-gguf', local_dir='./llava-phi-3-mini-gguf', max_workers=5)
 
61
  ```
62
 
63
  ### Build environment
@@ -71,9 +73,6 @@ snapshot_download(repo_id='xtuner/llava-phi-3-mini-gguf', local_dir='./llava-phi
71
  ```bash
72
  cd ./llava-phi-3-mini-gguf
73
 
74
- # fp16
75
- ./llava-cli -m ggml-model-f16.gguf --mmproj mmproj-model-f16.gguf --image YOUR_IMAGE.jpg -c 4096
76
-
77
  # int4
78
  ./llava-cli -m ggml-model-int4.gguf --mmproj mmproj-model-f16.gguf --image YOUR_IMAGE.jpg -c 4096
79
  ```
 
17
 
18
  llava-phi-3-mini is a LLaVA model fine-tuned from [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) and [CLIP-ViT-Large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) with [ShareGPT4V-PT](https://huggingface.co/datasets/Lin-Chen/ShareGPT4V) and [InternVL-SFT](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat#prepare-training-datasets) by [XTuner](https://github.com/InternLM/xtuner).
19
 
20
+ **Note: This model is in GGUF format. LLM in fp16 precision is coming soon.**
21
 
22
  Resources:
23
 
 
54
 
55
  ### Download models
56
 
57
+ ```bash
58
+ # mmproj
59
+ wget https://huggingface.co/xtuner/llava-phi-3-mini-gguf/resolve/main/mmproj-model-f16.gguf
60
 
61
+ # int4 llm
62
+ wget https://huggingface.co/xtuner/llava-phi-3-mini-gguf/resolve/main/ggml-model-int4.gguf
63
  ```
64
 
65
  ### Build environment
 
73
  ```bash
74
  cd ./llava-phi-3-mini-gguf
75
 
 
 
 
76
  # int4
77
  ./llava-cli -m ggml-model-int4.gguf --mmproj mmproj-model-f16.gguf --image YOUR_IMAGE.jpg -c 4096
78
  ```