metadata

base_model: balrogbob/open_llama_3b_v2-python-instruct-0.1
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
  - llama-cpp
  - gguf-my-repo

balrogbob/open_llama_3b_v2-python-instruct-0.1-IQ3_XXS-GGUF

This model was converted to GGUF format from balrogbob/open_llama_3b_v2-python-instruct-0.1 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Needs < /s > (minus spaces) as stop tag, some software works automatically, some (like LM Studio) need the stop tag added. Despite the alpaca training it still expects a bert style stop token.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo balrogbob/open_llama_3b_v2-python-instruct-0.1-IQ3_XXS-GGUF --hf-file open_llama_3b_v2-python-instruct-0.1-iq3_xxs-imat.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo balrogbob/open_llama_3b_v2-python-instruct-0.1-IQ3_XXS-GGUF --hf-file open_llama_3b_v2-python-instruct-0.1-iq3_xxs-imat.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo balrogbob/open_llama_3b_v2-python-instruct-0.1-IQ3_XXS-GGUF --hf-file open_llama_3b_v2-python-instruct-0.1-iq3_xxs-imat.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo balrogbob/open_llama_3b_v2-python-instruct-0.1-IQ3_XXS-GGUF --hf-file open_llama_3b_v2-python-instruct-0.1-iq3_xxs-imat.gguf -c 2048