High Quality / Hard to Find
Collection
Q6 quants of LLM Models. Other Quants - including Q8 - in models listings.
•
72 items
•
Updated
•
5
DavidAU/FuseChat-7B-VaRM-Q6_K-GGUF
This model was converted to GGUF format from FuseAI/FuseChat-7B-VaRM 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 DavidAU/FuseChat-7B-VaRM-Q6_K-GGUF --model fusechat-7b-varm.Q6_K.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo DavidAU/FuseChat-7B-VaRM-Q6_K-GGUF --model fusechat-7b-varm.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 fusechat-7b-varm.Q6_K.gguf -n 128
- Downloads last month
- 13
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.
Model tree for DavidAU/FuseChat-7B-VaRM-Q6_K-GGUF
Base model
openchat/openchat_3.5Dataset used to train DavidAU/FuseChat-7B-VaRM-Q6_K-GGUF
Collection including DavidAU/FuseChat-7B-VaRM-Q6_K-GGUF
Evaluation results
- score on MT-Benchsource8.220
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard62.880
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.250
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.710
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard45.670
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard79.160
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard63.460