Edit model card

YorkieOH10/granite-8b-code-instruct-Q8_0-GGUF

This model was converted to GGUF format from ibm-granite/granite-8b-code-instruct using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo YorkieOH10/granite-8b-code-instruct-Q8_0-GGUF --model granite-8b-code-instruct.Q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo YorkieOH10/granite-8b-code-instruct-Q8_0-GGUF --model granite-8b-code-instruct.Q8_0.gguf -c 2048

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

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m granite-8b-code-instruct.Q8_0.gguf -n 128
Downloads last month
45
GGUF
Model size
8.05B params
Architecture
llama

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for YorkieOH10/granite-8b-code-instruct-Q8_0-GGUF

Quantized
(21)
this model

Datasets used to train YorkieOH10/granite-8b-code-instruct-Q8_0-GGUF

Evaluation results