bullerwins
/

Meta-Llama-3.1-70B-Instruct-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

bullerwins commited on Jul 23

Commit

cd04975

•

1 Parent(s): 70e7369

Update README.md

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -21,6 +21,9 @@ license: llama3.1
 GGUF quantized version using llama.cpp
 ## Model Information
 The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

 GGUF quantized version using llama.cpp
+While it works, it still need proper [RoPE suppport](https://github.com/ggerganov/llama.cpp/issues/8650)
+I will requant once merged
 ## Model Information
 The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.