Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
abacusai/Smaug-Llama-3-70B-Instruct-32K - GGUF
This repo contains GGUF format model files for abacusai/Smaug-Llama-3-70B-Instruct-32K.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Model file specification
Filename | Quant type | File Size | Description |
---|---|---|---|
Smaug-Llama-3-70B-Instruct-32K-Q2_K.gguf | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
Smaug-Llama-3-70B-Instruct-32K-Q3_K_S.gguf | Q3_K_S | 30.912 GB | very small, high quality loss |
Smaug-Llama-3-70B-Instruct-32K-Q3_K_M.gguf | Q3_K_M | 34.267 GB | very small, high quality loss |
Smaug-Llama-3-70B-Instruct-32K-Q3_K_L.gguf | Q3_K_L | 37.141 GB | small, substantial quality loss |
Smaug-Llama-3-70B-Instruct-32K-Q4_0.gguf | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
Smaug-Llama-3-70B-Instruct-32K-Q4_K_S.gguf | Q4_K_S | 40.347 GB | small, greater quality loss |
Smaug-Llama-3-70B-Instruct-32K-Q4_K_M.gguf | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
Smaug-Llama-3-70B-Instruct-32K-Q5_0.gguf | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
Smaug-Llama-3-70B-Instruct-32K-Q5_K_S.gguf | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
Smaug-Llama-3-70B-Instruct-32K-Q5_K_M.gguf | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
Smaug-Llama-3-70B-Instruct-32K-Q8_0 | Q6_K | 74.975 GB | very large, extremely low quality loss |
Smaug-Llama-3-70B-Instruct-32K-Q6_K | Q8_0 | 57.888 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/Smaug-Llama-3-70B-Instruct-32K-GGUF --include "Smaug-Llama-3-70B-Instruct-32K-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/Smaug-Llama-3-70B-Instruct-32K-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 324
Model tree for tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF
Base model
abacusai/Smaug-Llama-3-70B-Instruct-32KDatasets used to train tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard77.610
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard49.070
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard21.220
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.150
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.430
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard41.830