Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
jsfs11/MixtureofMerges-MoE-4x7b-v5 - GGUF
This repo contains GGUF format model files for jsfs11/MixtureofMerges-MoE-4x7b-v5.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
Model file specification
Filename | Quant type | File Size | Description |
---|---|---|---|
MixtureofMerges-MoE-4x7b-v5-Q2_K.gguf | Q2_K | 8.236 GB | smallest, significant quality loss - not recommended for most purposes |
MixtureofMerges-MoE-4x7b-v5-Q3_K_S.gguf | Q3_K_S | 9.717 GB | very small, high quality loss |
MixtureofMerges-MoE-4x7b-v5-Q3_K_M.gguf | Q3_K_M | 10.785 GB | very small, high quality loss |
MixtureofMerges-MoE-4x7b-v5-Q3_K_L.gguf | Q3_K_L | 11.683 GB | small, substantial quality loss |
MixtureofMerges-MoE-4x7b-v5-Q4_0.gguf | Q4_0 | 12.688 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
MixtureofMerges-MoE-4x7b-v5-Q4_K_S.gguf | Q4_K_S | 12.799 GB | small, greater quality loss |
MixtureofMerges-MoE-4x7b-v5-Q4_K_M.gguf | Q4_K_M | 13.607 GB | medium, balanced quality - recommended |
MixtureofMerges-MoE-4x7b-v5-Q5_0.gguf | Q5_0 | 15.485 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
MixtureofMerges-MoE-4x7b-v5-Q5_K_S.gguf | Q5_K_S | 15.485 GB | large, low quality loss - recommended |
MixtureofMerges-MoE-4x7b-v5-Q5_K_M.gguf | Q5_K_M | 15.958 GB | large, very low quality loss - recommended |
MixtureofMerges-MoE-4x7b-v5-Q6_K.gguf | Q6_K | 18.456 GB | very large, extremely low quality loss |
MixtureofMerges-MoE-4x7b-v5-Q8_0.gguf | Q8_0 | 23.904 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/MixtureofMerges-MoE-4x7b-v5-GGUF --include "MixtureofMerges-MoE-4x7b-v5-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf
), you can try:
huggingface-cli download tensorblock/MixtureofMerges-MoE-4x7b-v5-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 212
Model tree for tensorblock/MixtureofMerges-MoE-4x7b-v5-GGUF
Base model
jsfs11/MixtureofMerges-MoE-4x7b-v5Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard73.890
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard89.000
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.690
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard73.730
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard85.080
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard69.750