From 1d4cc089d432883c7f4fe3829005e2de84dde8e2 Mon Sep 17 00:00:00 2001 From: Shaun Prince Date: Thu, 18 Apr 2024 17:46:53 +0000 Subject: [PATCH] Update README.md --- README.md | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 20515b6..0649a1e 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,7 @@ --- +license: other +license_name: llama3 +license_link: LICENSE library_name: transformers tags: - 4-bit @@ -6,10 +9,29 @@ tags: - text-generation - autotrain_compatible - endpoints_compatible +- facebook +- meta +- pytorch +- llama +- llama-3 pipeline_tag: text-generation inference: false quantized_by: Suparious --- -# +# Undi95/Meta-Llama-3-8B-hf AWQ -**UPLOAD IN PROGRESS** +- Original model: [Meta-Llama-3-8B-instruct-hf](Undi95/Meta-Llama-3-8B-instruct-hf) + +## Model Summary + +Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. + +**Model developers** Meta + +**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants. + +**Input** Models input text only. + +**Output** Models generate text and code only. + +**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.