Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
| 1 |
---
|
| 2 |
license: llama2
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: llama2
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
---
|
| 5 |
+
<!-- description start -->
|
| 6 |
+
## Description
|
| 7 |
+
Converted to f16 using llama_cpp convert.py script, then quantized to q6_K using quantize from the same llama_cpp repository.<br>
|
| 8 |
+
Resulting file was split into 2 parts using split. <br><br>
|
| 9 |
+
**Note**: HF does not support uploading files larger than 50GB.<br>
|
| 10 |
+
<!-- description end -->
|
| 11 |
+
### File require joining
|
| 12 |
+
To join the files, do the following: <br>
|
| 13 |
+
cat codellama-70b-python-q6_K.gguf-split-* > codellama-70b-python-q6_K.gguf && rm codellama-70b-python-6_K.gguf-split-*
|