Text Generation
GGUF
English
shining-valiant
shining-valiant-2
valiant
valiant-labs
llama
llama-3.1
llama-3.1-instruct
llama-3.1-instruct-8b
llama-3
llama-3-instruct
llama-3-instruct-8b
8b
science
physics
biology
chemistry
compsci
computer-science
engineering
technical
conversational
chat
instruct
TensorBlock
GGUF
Eval Results
Inference Endpoints
Update README.md
Browse files
README.md
CHANGED
|
@@ -200,8 +200,16 @@ This repo contains GGUF format model files for [ValiantLabs/Llama3.1-8B-ShiningV
|
|
| 200 |
|
| 201 |
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).
|
| 202 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
## Prompt template
|
| 204 |
|
|
|
|
| 205 |
```
|
| 206 |
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
| 207 |
|
|
@@ -217,18 +225,18 @@ Today Date: 26 Jul 2024
|
|
| 217 |
|
| 218 |
| Filename | Quant type | File Size | Description |
|
| 219 |
| -------- | ---------- | --------- | ----------- |
|
| 220 |
-
| [Llama3.1-8B-ShiningValiant2-Q2_K.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 221 |
-
| [Llama3.1-8B-ShiningValiant2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 222 |
-
| [Llama3.1-8B-ShiningValiant2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 223 |
-
| [Llama3.1-8B-ShiningValiant2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 224 |
-
| [Llama3.1-8B-ShiningValiant2-Q4_0.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 225 |
-
| [Llama3.1-8B-ShiningValiant2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 226 |
-
| [Llama3.1-8B-ShiningValiant2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 227 |
-
| [Llama3.1-8B-ShiningValiant2-Q5_0.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 228 |
-
| [Llama3.1-8B-ShiningValiant2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 229 |
-
| [Llama3.1-8B-ShiningValiant2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 230 |
-
| [Llama3.1-8B-ShiningValiant2-Q6_K.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 231 |
-
| [Llama3.1-8B-ShiningValiant2-Q8_0.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/
|
| 232 |
|
| 233 |
|
| 234 |
## Downloading instruction
|
|
|
|
| 200 |
|
| 201 |
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).
|
| 202 |
|
| 203 |
+
|
| 204 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 205 |
+
<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;">
|
| 206 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 207 |
+
</a>
|
| 208 |
+
</div>
|
| 209 |
+
|
| 210 |
## Prompt template
|
| 211 |
|
| 212 |
+
|
| 213 |
```
|
| 214 |
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
| 215 |
|
|
|
|
| 225 |
|
| 226 |
| Filename | Quant type | File Size | Description |
|
| 227 |
| -------- | ---------- | --------- | ----------- |
|
| 228 |
+
| [Llama3.1-8B-ShiningValiant2-Q2_K.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 229 |
+
| [Llama3.1-8B-ShiningValiant2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
| 230 |
+
| [Llama3.1-8B-ShiningValiant2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
| 231 |
+
| [Llama3.1-8B-ShiningValiant2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
| 232 |
+
| [Llama3.1-8B-ShiningValiant2-Q4_0.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 233 |
+
| [Llama3.1-8B-ShiningValiant2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
| 234 |
+
| [Llama3.1-8B-ShiningValiant2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
| 235 |
+
| [Llama3.1-8B-ShiningValiant2-Q5_0.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 236 |
+
| [Llama3.1-8B-ShiningValiant2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
| 237 |
+
| [Llama3.1-8B-ShiningValiant2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
| 238 |
+
| [Llama3.1-8B-ShiningValiant2-Q6_K.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
| 239 |
+
| [Llama3.1-8B-ShiningValiant2-Q8_0.gguf](https://huggingface.co/tensorblock/Llama3.1-8B-ShiningValiant2-GGUF/blob/main/Llama3.1-8B-ShiningValiant2-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
| 240 |
|
| 241 |
|
| 242 |
## Downloading instruction
|