Hugging Face's logo

AI-Engine
/
Meta-Llama-3.1-8B-Instruct-GGUF

GGUF
Inference Endpoints
conversational
Model card Files Community
AI-Engine commited on
Commit
88d8b89
·
verified ·
1 Parent(s): b289338

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -5,7 +5,9 @@ GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
5
  - Original model: [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
6
  - Model creator: [Meta](https://huggingface.co/meta-llama)
7
  - [License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE)
8
-
 
 
9
  ## Recommended Prompt Format (Llama3)
10
  ```
11
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
 
5
  - Original model: [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
6
  - Model creator: [Meta](https://huggingface.co/meta-llama)
7
  - [License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE)
8
+
9
+ <span style="color: red">Update:</span> Use the -imatrix versions (they use [imatrix](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) and the **bpe-llama tokenizer** which should theoretically improve the output)
10
+
11
  ## Recommended Prompt Format (Llama3)
12
  ```
13
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>