Post-transformer inference: 224× compression of Llama-70B with improved accuracy (zenodo.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of zenodo.org: Post-transformer inference: 224× compression of Llama-70B with improved accuracy

First screen, captured 10 months ago.

Looks similar

Screenshot of blog.vllm.ai: vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep

vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep (blog.vllm.ai)

138 points by robertnishihara 9 months ago | 46 comments

Screenshot of llasatts.github.io: Llasa: Llama-Based Speech Synthesis

Llasa: Llama-Based Speech Synthesis (llasatts.github.io)

156 points by CalmStorm 1 year ago | 18 comments

Screenshot of jiachenzhu.github.io: Transformers Without Normalization

Transformers Without Normalization (jiachenzhu.github.io)

247 points by hellollm 1 year ago | 30 comments

Screenshot of vicuna.lmsys.org: Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality

Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality (vicuna.lmsys.org)

245 points by yvbbrjdr 3 years ago | 128 comments

Screenshot of yitay.net: What happened to BERT and T5?

What happened to BERT and T5?(yitay.net)

218 points by fzliu 2 years ago | 63 comments

Screenshot of zenodo.org: CURLoRA: Stable LLM Fine-Tuning and Catastrophic Forgetting Mitigation

CURLoRA: Stable LLM Fine-Tuning and Catastrophic Forgetting Mitigation (zenodo.org)

49 points by mnoorfawi 2 years ago | 8 comments