Alfred-40B, an OSS RLHF version of Falcon40B

Any performance benchmarks compared to other LLMs? Also, any performance increases on the orig Falcon model in inference speed?<p>We ditched most of our focus on Falcon 40B after Llama 2 70B came out, both the tokens per sec and quality of results are not even close.

Will every comment here be a question? Will someone break the trend?

What kind of hardware do I need to run this sufficiently well? I.e. say I want 10 tokens&#x2F;s, what specs am I looking at?

Igor, is LightOn still working on optical computing? Or have you fully pivoted to genai without optics?

Will the team be releasing the momentum-internal dataset?

Anyone keeping track of all these LLM releases?

so its open source? Where is the link to the weights?<p>The article was mildly annoying because of many underlines sentences and words that looked like links.