newsletter/CapybaraHermes-2.5-Mistral-7B-Q6_K-GGUF
This model was converted to GGUF format from argilla/CapybaraHermes-2.5-Mistral-7B
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 newsletter/CapybaraHermes-2.5-Mistral-7B-Q6_K-GGUF --hf-file capybarahermes-2.5-mistral-7b-q6_k.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo newsletter/CapybaraHermes-2.5-Mistral-7B-Q6_K-GGUF --hf-file capybarahermes-2.5-mistral-7b-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 newsletter/CapybaraHermes-2.5-Mistral-7B-Q6_K-GGUF --hf-file capybarahermes-2.5-mistral-7b-q6_k.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo newsletter/CapybaraHermes-2.5-Mistral-7B-Q6_K-GGUF --hf-file capybarahermes-2.5-mistral-7b-q6_k.gguf -c 2048
- Downloads last month
- 25
Model tree for newsletter/CapybaraHermes-2.5-Mistral-7B-Q6_K-GGUF
Base model
teknium/OpenHermes-2-coder-Mistral-7B-v2-e4
Finetuned
argilla/CapybaraHermes-2.5-Mistral-7B
Quantized
this model
Dataset used to train newsletter/CapybaraHermes-2.5-Mistral-7B-Q6_K-GGUF
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard65.780
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.450
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.130
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard56.910
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.300
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard59.290