Upload README.md
Browse files
README.md
CHANGED
|
@@ -318,6 +318,11 @@ And thank you again to a16z for their generous grant.
|
|
| 318 |
|
| 319 |
<p><h1> speechless-codellama-34b-v2.0 </h1></p>
|
| 320 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 321 |
Use the following datasets to fine-tune codellama/CodeLlama-34B in order to improve the model's inference and planning capabilities.
|
| 322 |
|
| 323 |
Total 153,013 samples.
|
|
|
|
| 318 |
|
| 319 |
<p><h1> speechless-codellama-34b-v2.0 </h1></p>
|
| 320 |
|
| 321 |
+
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-AWQ)
|
| 322 |
+
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ)
|
| 323 |
+
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GGUF)
|
| 324 |
+
|
| 325 |
+
|
| 326 |
Use the following datasets to fine-tune codellama/CodeLlama-34B in order to improve the model's inference and planning capabilities.
|
| 327 |
|
| 328 |
Total 153,013 samples.
|