mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-02-06 08:30:33 +01:00
0cec062a63
* add glm edge chat model * use config partial_rotary_factor as rope ratio * support for glm edge model * vision model support * remove debug info * fix format * llava.cpp trailing whitespace * remove unused AutoTokenizer * Update src/llama.cpp for not contain <|end|> or </s> Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> * add edge template * fix chat template * fix confict * fix confict * fix ci err * fix format err * fix template err * 9b hf chat support * format * format clip.cpp * fix format * Apply suggestions from code review * Apply suggestions from code review * Update examples/llava/clip.cpp * fix format * minor : style --------- Co-authored-by: liyuhang <yuhang.li@zhipuai.cn> Co-authored-by: piDack <pcdack@hotmail.co> Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com> Co-authored-by: liyuhang <yuhang.li@aminer.cn> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
44 lines
1.6 KiB
Markdown
44 lines
1.6 KiB
Markdown
# GLMV-EDGE
|
|
|
|
Currently this implementation supports [glm-edge-v-2b](https://huggingface.co/THUDM/glm-edge-v-2b) and [glm-edge-v-5b](https://huggingface.co/THUDM/glm-edge-v-5b).
|
|
|
|
## Usage
|
|
Build with cmake or run `make llama-llava-cli` to build it.
|
|
|
|
After building, run: `./llama-llava-cli` to see the usage. For example:
|
|
|
|
```sh
|
|
./llama-llava-cli -m model_path/ggml-model-f16.gguf --mmproj model_path/mmproj-model-f16.gguf --image img_path/image.jpg -p "<|system|>\n system prompt <image><|user|>\n prompt <|assistant|>\n"
|
|
```
|
|
|
|
**note**: A lower temperature like 0.1 is recommended for better quality. add `--temp 0.1` to the command to do so.
|
|
**note**: For GPU offloading ensure to use the `-ngl` flag just like usual
|
|
|
|
## GGUF conversion
|
|
|
|
1. Clone a GLMV-EDGE model ([2B](https://huggingface.co/THUDM/glm-edge-v-2b) or [5B](https://huggingface.co/THUDM/glm-edge-v-5b)). For example:
|
|
|
|
```sh
|
|
git clone https://huggingface.co/THUDM/glm-edge-v-5b or https://huggingface.co/THUDM/glm-edge-v-2b
|
|
```
|
|
|
|
2. Use `glmedge-surgery.py` to split the GLMV-EDGE model to LLM and multimodel projector constituents:
|
|
|
|
```sh
|
|
python ./examples/llava/glmedge-surgery.py -m ../model_path
|
|
```
|
|
|
|
4. Use `glmedge-convert-image-encoder-to-gguf.py` to convert the GLMV-EDGE image encoder to GGUF:
|
|
|
|
```sh
|
|
python ./examples/llava/glmedge-convert-image-encoder-to-gguf.py -m ../model_path --llava-projector ../model_path/glm.projector --output-dir ../model_path
|
|
```
|
|
|
|
5. Use `examples/convert_hf_to_gguf.py` to convert the LLM part of GLMV-EDGE to GGUF:
|
|
|
|
```sh
|
|
python convert_hf_to_gguf.py ../model_path
|
|
```
|
|
|
|
Now both the LLM part and the image encoder are in the `model_path` directory.
|