AlecKarfonta/mistral-7b-v0.1-layla-v4-Q6_K-GGUF
This model was converted to GGUF format from l3utterfly/mistral-7b-v0.1-layla-v4
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 (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo AlecKarfonta/mistral-7b-v0.1-layla-v4-Q6_K-GGUF --hf-file mistral-7b-v0.1-layla-v4-q6_k.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo AlecKarfonta/mistral-7b-v0.1-layla-v4-Q6_K-GGUF --hf-file mistral-7b-v0.1-layla-v4-q6_k.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 AlecKarfonta/mistral-7b-v0.1-layla-v4-Q6_K-GGUF --hf-file mistral-7b-v0.1-layla-v4-q6_k.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo AlecKarfonta/mistral-7b-v0.1-layla-v4-Q6_K-GGUF --hf-file mistral-7b-v0.1-layla-v4-q6_k.gguf -c 2048
- Downloads last month
- 12
Model tree for AlecKarfonta/mistral-7b-v0.1-layla-v4-Q6_K-GGUF
Base model
l3utterfly/mistral-7b-v0.1-layla-v4
Quantized
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard62.290
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard83.360
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.320
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard43.140
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard79.560
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard55.500