Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- eu
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- gguf
|
| 7 |
+
- latxa
|
| 8 |
+
- 7b
|
| 9 |
+
- hitz
|
| 10 |
+
- llama
|
| 11 |
+
- quant
|
| 12 |
+
model_name: latxa-7b-v1
|
| 13 |
+
base_model: xezpeleta/latxa-7b-instruct
|
| 14 |
+
---
|
| 15 |
+
# Latxa 7b Instruct GGUF
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Provided files
|
| 19 |
+
|
| 20 |
+
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|
| 21 |
+
| ---- | ---- | ---- | ---- | ---- | ----- |
|
| 22 |
+
| [latxa-7b-v1-instruct-q8_0.gguf](https://huggingface.co/xezpeleta/latxa-7b-v1-gguf/blob/main/latxa-7b-v1.gguf) | |8 bits | 7 GB | 8,2 GB| Fits in a RTX 3060 12Gb |
|