tensorblock/Llama-3-13B-Instruct-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Morris Zhang
2024-11-16 00:40:12 +00:00
committed by system
parent b8a5c19c92
commit 7280b23887
1 changed files with 20 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
README.md
View File

@@ -26,8 +26,16 @@ This repo contains GGUF format model files for [elinas/Llama-3-13B-Instruct](htt
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
<div style="text-align: left; margin: 20px 0;">
<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
Run them on the TensorBlock client using your local machine ↗
</a>
</div>
## Prompt template
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
@@ -40,18 +48,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Llama-3-13B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q2_K.gguf) | Q2_K | 4.680 GB | smallest, significant quality loss - not recommended for most purposes |
| [Llama-3-13B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q3_K_S.gguf) | Q3_K_S | 5.421 GB | very small, high quality loss |
| [Llama-3-13B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q3_K_M.gguf) | Q3_K_M | 5.985 GB | very small, high quality loss |
| [Llama-3-13B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q3_K_L.gguf) | Q3_K_L | 6.473 GB | small, substantial quality loss |
| [Llama-3-13B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q4_0.gguf) | Q4_0 | 6.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Llama-3-13B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q4_K_S.gguf) | Q4_K_S | 7.013 GB | small, greater quality loss |
| [Llama-3-13B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q4_K_M.gguf) | Q4_K_M | 7.378 GB | medium, balanced quality - recommended |
| [Llama-3-13B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q5_0.gguf) | Q5_0 | 8.427 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [Llama-3-13B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q5_K_S.gguf) | Q5_K_S | 8.427 GB | large, low quality loss - recommended |
| [Llama-3-13B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q5_K_M.gguf) | Q5_K_M | 8.637 GB | large, very low quality loss - recommended |
| [Llama-3-13B-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q6_K.gguf) | Q6_K | 9.976 GB | very large, extremely low quality loss |
| [Llama-3-13B-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/tree/main/Llama-3-13B-Instruct-Q8_0.gguf) | Q8_0 | 12.919 GB | very large, extremely low quality loss - not recommended |
| [Llama-3-13B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q2_K.gguf) | Q2_K | 4.680 GB | smallest, significant quality loss - not recommended for most purposes |
| [Llama-3-13B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q3_K_S.gguf) | Q3_K_S | 5.421 GB | very small, high quality loss |
| [Llama-3-13B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q3_K_M.gguf) | Q3_K_M | 5.985 GB | very small, high quality loss |
| [Llama-3-13B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q3_K_L.gguf) | Q3_K_L | 6.473 GB | small, substantial quality loss |
| [Llama-3-13B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q4_0.gguf) | Q4_0 | 6.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Llama-3-13B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q4_K_S.gguf) | Q4_K_S | 7.013 GB | small, greater quality loss |
| [Llama-3-13B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q4_K_M.gguf) | Q4_K_M | 7.378 GB | medium, balanced quality - recommended |
| [Llama-3-13B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q5_0.gguf) | Q5_0 | 8.427 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [Llama-3-13B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q5_K_S.gguf) | Q5_K_S | 8.427 GB | large, low quality loss - recommended |
| [Llama-3-13B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q5_K_M.gguf) | Q5_K_M | 8.637 GB | large, very low quality loss - recommended |
| [Llama-3-13B-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q6_K.gguf) | Q6_K | 9.976 GB | very large, extremely low quality loss |
| [Llama-3-13B-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-13B-Instruct-GGUF/blob/main/Llama-3-13B-Instruct-Q8_0.gguf) | Q8_0 | 12.919 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction