Hugging Face's logo

xezpeleta
/
latxa-7b-v1-gguf

Text Generation
GGUF
Basque
latxa
7b
hitz
llama
Inference Endpoints
Model card Files Community
xezpeleta commited on
Commit
22b8c6e
•
1 Parent(s): 492d30a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -6,7 +6,19 @@ tags:
6
  - gguf
7
  - latxa
8
  - 7b
 
 
 
 
9
  ---
10
 
11
  # Latxa 7b GGUF
12
 
 
 
 
 
 
 
 
 
 
6
  - gguf
7
  - latxa
8
  - 7b
9
+ - hitz
10
+ - llama
11
+ model_name: latxa-7b-v1
12
+ base_model: HiTZ/latxa-7b-v1
13
  ---
14
 
15
  # Latxa 7b GGUF
16
 
17
+
18
+ ## Provided files
19
+
20
+ | Name | Quant method | Bits | Size | Max RAM required | Use case |
21
+ | ---- | ---- | ---- | ---- | ---- | ----- |
22
+ | [latxa-7b-v1.gguf](https://huggingface.co/xezpeleta/latxa-7b-v1-gguf/blob/main/latxa-7b-v1.gguf) | | | 26 GB| | |
23
+ | [latxa-7b-v1-f16.gguf](https://huggingface.co/xezpeleta/latxa-7b-v1-gguf/blob/main/latxa-7b-v1-f16.gguf) | | | 13 GB| | |
24
+ | [latxa-7b-v1-q8_0.gguf](https://huggingface.co/xezpeleta/latxa-7b-v1-gguf/blob/main/latxa-7b-v1-q8_0.gguf) | Q8_0 | | 6,7 GB| | |