cobrakenji/granite-34b-code-base-Q2_K-GGUF
This model was converted to GGUF format from ibm-granite/granite-34b-code-base
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 cobrakenji/granite-34b-code-base-Q2_K-GGUF --model granite-34b-code-base.Q2_K.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo cobrakenji/granite-34b-code-base-Q2_K-GGUF --model granite-34b-code-base.Q2_K.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-34b-code-base.Q2_K.gguf -n 128
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Datasets used to train cobrakenji/granite-34b-code-base-Q2_K-GGUF
Evaluation results
- pass@1 on MBPPself-reported47.200
- pass@1 on MBPP+self-reported53.100
- pass@1 on HumanEvalSynthesis(Python)self-reported48.200
- pass@1 on HumanEvalSynthesis(Python)self-reported54.900
- pass@1 on HumanEvalSynthesis(Python)self-reported61.600
- pass@1 on HumanEvalSynthesis(Python)self-reported40.200
- pass@1 on HumanEvalSynthesis(Python)self-reported50.000
- pass@1 on HumanEvalSynthesis(Python)self-reported39.600
- pass@1 on HumanEvalSynthesis(Python)self-reported42.700
- pass@1 on HumanEvalSynthesis(Python)self-reported26.200