Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
MaziyarPanahi/calme-3.3-instruct-3b - GGUF
This repo contains GGUF format model files for MaziyarPanahi/calme-3.3-instruct-3b.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
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 |
---|---|---|---|
calme-3.3-instruct-3b-Q2_K.gguf | Q2_K | 1.275 GB | smallest, significant quality loss - not recommended for most purposes |
calme-3.3-instruct-3b-Q3_K_S.gguf | Q3_K_S | 1.454 GB | very small, high quality loss |
calme-3.3-instruct-3b-Q3_K_M.gguf | Q3_K_M | 1.590 GB | very small, high quality loss |
calme-3.3-instruct-3b-Q3_K_L.gguf | Q3_K_L | 1.707 GB | small, substantial quality loss |
calme-3.3-instruct-3b-Q4_0.gguf | Q4_0 | 1.823 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
calme-3.3-instruct-3b-Q4_K_S.gguf | Q4_K_S | 1.834 GB | small, greater quality loss |
calme-3.3-instruct-3b-Q4_K_M.gguf | Q4_K_M | 1.930 GB | medium, balanced quality - recommended |
calme-3.3-instruct-3b-Q5_0.gguf | Q5_0 | 2.170 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
calme-3.3-instruct-3b-Q5_K_S.gguf | Q5_K_S | 2.170 GB | large, low quality loss - recommended |
calme-3.3-instruct-3b-Q5_K_M.gguf | Q5_K_M | 2.225 GB | large, very low quality loss - recommended |
calme-3.3-instruct-3b-Q6_K.gguf | Q6_K | 2.538 GB | very large, extremely low quality loss |
calme-3.3-instruct-3b-Q8_0.gguf | Q8_0 | 3.285 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/calme-3.3-instruct-3b-GGUF --include "calme-3.3-instruct-3b-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/calme-3.3-instruct-3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 270
Model tree for tensorblock/calme-3.3-instruct-3b-GGUF
Datasets used to train tensorblock/calme-3.3-instruct-3b-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard64.230
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard25.680
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard4.360
- acc_norm on MuSR (0-shot)Open LLM Leaderboard9.400
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard25.620