vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

readme : move section [no ci]

Browse source
This commit is contained in:
Georgi Gerganov 2024-11-29 22:12:21 +02:00
parent 4ba28761e7
commit e8338b3b4d
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 13 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

26
README.md
View file

@ -223,7 +223,7 @@ Instructions for adding support for new models: [HOWTO-add-model.md](./docs/deve
| [Vulkan](./docs/build.md#vulkan) | GPU | | [Vulkan](./docs/build.md#vulkan) | GPU |
| [CANN](./docs/build.md#cann) | Ascend NPU | | [CANN](./docs/build.md#cann) | Ascend NPU |
## Building and Usage ## Building and usage
The main product of this project is the `llama` library. It's C-style interface can be found in [include/llama.h](include/llama.h). The main product of this project is the `llama` library. It's C-style interface can be found in [include/llama.h](include/llama.h).
The project also produces several examples and tools that can be used to get started. There are a few ways to obtain the binaries: The project also produces several examples and tools that can be used to get started. There are a few ways to obtain the binaries:
@ -235,6 +235,18 @@ The project also produces several examples and tools that can be used to get sta
For more information, refer to [Build llama.cpp locally](./docs/build.md) For more information, refer to [Build llama.cpp locally](./docs/build.md)
### Obtaining and quantizing models
The [Hugging Face](https://huggingface.co) platform hosts a large amount of LLM models compatible with `llama.cpp`. Search for the [GGUF](https://huggingface.co/models?library=gguf&sort=trending) file format.
The platform provides multiple online tools for converting, quantizing and hosting models with `llama.cpp`:
- Use the [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space to quantize model weights to smaller sizes
- Use the [GGUF-my-LoRA](https://huggingface.co/spaces/ggml-org/gguf-my-lora) space to convert LoRA adapters to GGUF format (more info: https://github.com/ggerganov/llama.cpp/discussions/10123)
- Use the [GGUF editor](https://huggingface.co/spaces/CISCai/gguf-editor) space to edit GGUF meta data in the browser (more info: https://github.com/ggerganov/llama.cpp/discussions/9268)
- Use the [Inference Endpoints](https://ui.endpoints.huggingface.co/) to directly host `llama.cpp` in the cloud (more info: https://github.com/ggerganov/llama.cpp/discussions/9669)
To learn more about model quantization, [read this documentation](./examples/quantize/README.md)
### Using the `llama-cli` tool ### Using the `llama-cli` tool
Run a basic text completion: Run a basic text completion:
@ -307,18 +319,6 @@ For more information, see [https://huggingface.co/docs/transformers/perplexity](
To learn more how to measure perplexity using llama.cpp, [read this documentation](./examples/perplexity/README.md) To learn more how to measure perplexity using llama.cpp, [read this documentation](./examples/perplexity/README.md)
## Obtaining and quantizing models
The [Hugging Face](https://huggingface.co) platform hosts a large amount of LLM models compatible with `llama.cpp`. Search for the [GGUF](https://huggingface.co/models?library=gguf&sort=trending) file format.
The platform provides multiple online tools for converting, quantizing and hosting models with `llama.cpp`:
- Use the [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space to quantize model weights to smaller sizes
- Use the [GGUF-my-LoRA](https://huggingface.co/spaces/ggml-org/gguf-my-lora) space to convert LoRA adapters to GGUF format (more info: https://github.com/ggerganov/llama.cpp/discussions/10123)
- Use the [GGUF editor](https://huggingface.co/spaces/CISCai/gguf-editor) space to edit GGUF meta data in the browser (more info: https://github.com/ggerganov/llama.cpp/discussions/9268)
- Use the [Inference Endpoints](https://ui.endpoints.huggingface.co/) to directly host `llama.cpp` in the cloud (more info: https://github.com/ggerganov/llama.cpp/discussions/9669)
To learn more about model quantization, [read this documentation](./examples/quantize/README.md)
## Contributing ## Contributing
- Contributors can open PRs - Contributors can open PRs