rinaldow/LogoS-7Bx2-MoE-13B-v0.2-Q4_K_M-GGUF
This model was converted to GGUF format from RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
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 rinaldow/LogoS-7Bx2-MoE-13B-v0.2-Q4_K_M-GGUF --model logos-7bx2-moe-13b-v0.2.Q4_K_M.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo rinaldow/LogoS-7Bx2-MoE-13B-v0.2-Q4_K_M-GGUF --model logos-7bx2-moe-13b-v0.2.Q4_K_M.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 logos-7bx2-moe-13b-v0.2.Q4_K_M.gguf -n 128
- Downloads last month
- 1
Model tree for rinaldow/LogoS-7Bx2-MoE-13B-v0.2-Q4_K_M-GGUF
Merge model
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard74.490
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard89.070
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.740
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard74.570
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard88.320
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard71.650