VOOZH about

URL: https://huggingface.co/bartowski/Llama-3.1-8B-Open-SFT-GGUF

⇱ bartowski/Llama-3.1-8B-Open-SFT-GGUF · Hugging Face

Llamacpp imatrix Quantizations of Llama-3.1-8B-Open-SFT

Using llama.cpp release b4381 for quantization.

Original model: https://huggingface.co/prithivMLmods/Llama-3.1-8B-Open-SFT

All quants made using imatrix option with dataset from here

Run them in LM Studio

Prompt format 

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Cutting Knowledge Date: December 2023
Today Date: 26 July 2024

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Download a file (not the whole branch) from below:

Filename Quant type File Size Split Description
Llama-3.1-8B-Open-SFT-f16.gguf f16 16.07GB false Full F16 weights.
Llama-3.1-8B-Open-SFT-Q8_0.gguf Q8_0 8.54GB false Extremely high quality, generally unneeded but max available quant.
Llama-3.1-8B-Open-SFT-Q6_K_L.gguf Q6_K_L 6.85GB false Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended.
Llama-3.1-8B-Open-SFT-Q6_K.gguf Q6_K 6.60GB false Very high quality, near perfect, recommended.
Llama-3.1-8B-Open-SFT-Q5_K_L.gguf Q5_K_L 6.06GB false Uses Q8_0 for embed and output weights. High quality, recommended.
Llama-3.1-8B-Open-SFT-Q5_K_M.gguf Q5_K_M 5.73GB false High quality, recommended.
Llama-3.1-8B-Open-SFT-Q5_K_S.gguf Q5_K_S 5.60GB false High quality, recommended.
Llama-3.1-8B-Open-SFT-Q4_K_L.gguf Q4_K_L 5.31GB false Uses Q8_0 for embed and output weights. Good quality, recommended.
Llama-3.1-8B-Open-SFT-Q4_1.gguf Q4_1 5.13GB false Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
Llama-3.1-8B-Open-SFT-Q4_K_M.gguf Q4_K_M 4.92GB false Good quality, default size for most use cases, recommended.
Llama-3.1-8B-Open-SFT-Q3_K_XL.gguf Q3_K_XL 4.78GB false Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
Llama-3.1-8B-Open-SFT-Q4_K_S.gguf Q4_K_S 4.69GB false Slightly lower quality with more space savings, recommended.
Llama-3.1-8B-Open-SFT-Q4_0.gguf Q4_0 4.68GB false Legacy format, offers online repacking for ARM and AVX CPU inference.
Llama-3.1-8B-Open-SFT-IQ4_NL.gguf IQ4_NL 4.68GB false Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference.
Llama-3.1-8B-Open-SFT-IQ4_XS.gguf IQ4_XS 4.45GB false Decent quality, smaller than Q4_K_S with similar performance, recommended.
Llama-3.1-8B-Open-SFT-Q3_K_L.gguf Q3_K_L 4.32GB false Lower quality but usable, good for low RAM availability.
Llama-3.1-8B-Open-SFT-Q3_K_M.gguf Q3_K_M 4.02GB false Low quality.
Llama-3.1-8B-Open-SFT-IQ3_M.gguf IQ3_M 3.78GB false Medium-low quality, new method with decent performance comparable to Q3_K_M.
Llama-3.1-8B-Open-SFT-Q2_K_L.gguf Q2_K_L 3.69GB false Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
Llama-3.1-8B-Open-SFT-Q3_K_S.gguf Q3_K_S 3.66GB false Low quality, not recommended.
Llama-3.1-8B-Open-SFT-IQ3_XS.gguf IQ3_XS 3.52GB false Lower quality, new method with decent performance, slightly better than Q3_K_S.
Llama-3.1-8B-Open-SFT-Q2_K.gguf Q2_K 3.18GB false Very low quality but surprisingly usable.
Llama-3.1-8B-Open-SFT-IQ2_M.gguf IQ2_M 2.95GB false Relatively low quality, uses SOTA techniques to be surprisingly usable.

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Downloading using huggingface-cli

ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

Which file should I choose?

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Downloads last month
1,392
GGUF
Model size
8B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for bartowski/Llama-3.1-8B-Open-SFT-GGUF

Dataset used to train bartowski/Llama-3.1-8B-Open-SFT-GGUF