Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge - GGUF
This repo contains GGUF format model files for grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
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 |
---|---|---|---|
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q2_K.gguf | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q3_K_S.gguf | Q3_K_S | 3.413 GB | very small, high quality loss |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q3_K_M.gguf | Q3_K_M | 3.743 GB | very small, high quality loss |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q3_K_L.gguf | Q3_K_L | 4.025 GB | small, substantial quality loss |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q4_0.gguf | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q4_K_S.gguf | Q4_K_S | 4.370 GB | small, greater quality loss |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q4_K_M.gguf | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q5_0.gguf | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q5_K_S.gguf | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q5_K_M.gguf | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q6_K.gguf | Q6_K | 6.143 GB | very large, extremely low quality loss |
Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-Q8_0.gguf | Q8_0 | 7.954 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/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-GGUF --include "Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-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/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 5
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/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard68.060
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard29.070
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard6.190
- acc_norm on GPQA (0-shot)Open LLM Leaderboard1.680
- acc_norm on MuSR (0-shot)Open LLM Leaderboard6.700
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard29.830