Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
stabilityai/stablelm-3b-4e1t - GGUF
This repo contains GGUF format model files for stabilityai/stablelm-3b-4e1t.
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 |
---|---|---|---|
stablelm-3b-4e1t-Q2_K.gguf | Q2_K | 1.009 GB | smallest, significant quality loss - not recommended for most purposes |
stablelm-3b-4e1t-Q3_K_S.gguf | Q3_K_S | 1.168 GB | very small, high quality loss |
stablelm-3b-4e1t-Q3_K_M.gguf | Q3_K_M | 1.296 GB | very small, high quality loss |
stablelm-3b-4e1t-Q3_K_L.gguf | Q3_K_L | 1.405 GB | small, substantial quality loss |
stablelm-3b-4e1t-Q4_0.gguf | Q4_0 | 1.498 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
stablelm-3b-4e1t-Q4_K_S.gguf | Q4_K_S | 1.509 GB | small, greater quality loss |
stablelm-3b-4e1t-Q4_K_M.gguf | Q4_K_M | 1.591 GB | medium, balanced quality - recommended |
stablelm-3b-4e1t-Q5_0.gguf | Q5_0 | 1.809 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
stablelm-3b-4e1t-Q5_K_S.gguf | Q5_K_S | 1.809 GB | large, low quality loss - recommended |
stablelm-3b-4e1t-Q5_K_M.gguf | Q5_K_M | 1.856 GB | large, very low quality loss - recommended |
stablelm-3b-4e1t-Q6_K.gguf | Q6_K | 2.138 GB | very large, extremely low quality loss |
stablelm-3b-4e1t-Q8_0.gguf | Q8_0 | 2.769 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/stablelm-3b-4e1t-GGUF --include "stablelm-3b-4e1t-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/stablelm-3b-4e1t-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 0
Model tree for tensorblock/stablelm-3b-4e1t-GGUF
Base model
stabilityai/stablelm-3b-4e1tDatasets used to train tensorblock/stablelm-3b-4e1t-GGUF
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard46.590
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard75.940
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard45.230
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard37.200
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard71.190
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard3.340