|
--- |
|
language: |
|
- en |
|
tags: |
|
- facebook |
|
- meta |
|
- pytorch |
|
- llama |
|
- llama-3 |
|
- llama-cpp |
|
- gguf-my-repo |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# nullt3r/Meta-Llama-3-8B-Instruct-64k-PoSE-Q8_0-GGUF |
|
This model was converted to GGUF format from [`Azma-AI/Meta-Llama-3-8B-Instruct-64k-PoSE`](https://huggingface.co/Azma-AI/Meta-Llama-3-8B-Instruct-64k-PoSE) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. |
|
Refer to the [original model card](https://huggingface.co/Azma-AI/Meta-Llama-3-8B-Instruct-64k-PoSE) for more details on the model. |
|
|
|
**The model works great with LM Studio and standard Llama 3 profile. There is known issue in ollama however, where model does not stop generation.** |
|
|
|
## Use with llama.cpp |
|
|
|
Install llama.cpp through brew. |
|
|
|
```bash |
|
brew install ggerganov/ggerganov/llama.cpp |
|
``` |
|
Invoke the llama.cpp server or the CLI. |
|
|
|
CLI: |
|
|
|
```bash |
|
llama-cli --hf-repo nullt3r/Meta-Llama-3-8B-Instruct-64k-PoSE-Q8_0-GGUF --model meta-llama-3-8b-instruct-64k-pose.Q8_0.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
Server: |
|
|
|
```bash |
|
llama-server --hf-repo nullt3r/Meta-Llama-3-8B-Instruct-64k-PoSE-Q8_0-GGUF --model meta-llama-3-8b-instruct-64k-pose.Q8_0.gguf -c 2048 |
|
``` |
|
|
|
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. |
|
|
|
``` |
|
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m meta-llama-3-8b-instruct-64k-pose.Q8_0.gguf -n 128 |
|
``` |
|
|