newsletter/neural-chat-7b-v3-3-Q6_K-GGUF
This model was converted to GGUF format from Intel/neural-chat-7b-v3-3
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 newsletter/neural-chat-7b-v3-3-Q6_K-GGUF --model neural-chat-7b-v3-3.Q6_K.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo newsletter/neural-chat-7b-v3-3-Q6_K-GGUF --model neural-chat-7b-v3-3.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.
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m neural-chat-7b-v3-3.Q6_K.gguf -n 128
- Downloads last month
- 17
Unable to determine this model's library. Check the
docs
.
Quantized from
Evaluation results
- ARC (25-shot) on meta-math/MetaMathQAself-reported66.890
- HellaSwag (10-shot) on meta-math/MetaMathQAself-reported85.260
- MMLU (5-shot) on meta-math/MetaMathQAself-reported63.070
- TruthfulQA (0-shot) on meta-math/MetaMathQAself-reported63.010
- Winogrande (5-shot) on meta-math/MetaMathQAself-reported79.640
- GSM8K (5-shot) on meta-math/MetaMathQAself-reported61.110
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard66.890
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.260
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.070
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard63.010