Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
anthracite-org/magnum-v3-27b-kto - GGUF
This repo contains GGUF format model files for anthracite-org/magnum-v3-27b-kto.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
Filename | Quant type | File Size | Description |
---|---|---|---|
magnum-v3-27b-kto-Q2_K.gguf | Q2_K | 9.732 GB | smallest, significant quality loss - not recommended for most purposes |
magnum-v3-27b-kto-Q3_K_S.gguf | Q3_K_S | 11.333 GB | very small, high quality loss |
magnum-v3-27b-kto-Q3_K_M.gguf | Q3_K_M | 12.503 GB | very small, high quality loss |
magnum-v3-27b-kto-Q3_K_L.gguf | Q3_K_L | 13.522 GB | small, substantial quality loss |
magnum-v3-27b-kto-Q4_0.gguf | Q4_0 | 14.555 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
magnum-v3-27b-kto-Q4_K_S.gguf | Q4_K_S | 14.658 GB | small, greater quality loss |
magnum-v3-27b-kto-Q4_K_M.gguf | Q4_K_M | 15.502 GB | medium, balanced quality - recommended |
magnum-v3-27b-kto-Q5_0.gguf | Q5_0 | 17.587 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
magnum-v3-27b-kto-Q5_K_S.gguf | Q5_K_S | 17.587 GB | large, low quality loss - recommended |
magnum-v3-27b-kto-Q5_K_M.gguf | Q5_K_M | 18.075 GB | large, very low quality loss - recommended |
magnum-v3-27b-kto-Q6_K.gguf | Q6_K | 20.809 GB | very large, extremely low quality loss |
magnum-v3-27b-kto-Q8_0.gguf | Q8_0 | 26.950 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/magnum-v3-27b-kto-GGUF --include "magnum-v3-27b-kto-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/magnum-v3-27b-kto-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 347
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 tensorblock/magnum-v3-27b-kto-GGUF
Base model
IntervitensInc/gemma-2-27b-chatml
Finetuned
anthracite-org/magnum-v3-27b-kto
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard56.750
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard41.160
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard15.480
- acc_norm on GPQA (0-shot)Open LLM Leaderboard14.090
- acc_norm on MuSR (0-shot)Open LLM Leaderboard9.920
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard35.980