AI-Engine
/

Meta-Llama-3-8B-Instruct-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

AI-Engine commited on May 1, 2024

Commit

f3dff07

·

verified ·

1 Parent(s): f5e3ca0

Update README.md

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -12,7 +12,11 @@ license: other
 license_name: llama3
 license_link: LICENSE
 ---
-**First Test:**
 GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
 - Original model: [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
 - Model creator: [Meta](https://huggingface.co/meta-llama)

 license_name: llama3
 license_link: LICENSE
 ---
+### Update May, 01 2024
+Re-uploaded the models with the latest fixes (stopping and [pre-tokenization](https://github.com/ggerganov/llama.cpp/pull/6920)) + additional [imatrix](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) versions.
+Just download a quant with imatrix in the name.<br>
+Do not use the old ones (the ones with_temp_token_fix). I'll leave them online for now for comparison.
+---
 GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
 - Original model: [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
 - Model creator: [Meta](https://huggingface.co/meta-llama)