http://
github.com/explosion/spac
y-llm
…
OPEN SOURCE
-
Lemur: New Code LLM Based on Llama 2
By
–
Oh, and there was also Lemur last week. A code LLM not based on Code Llama but based on LLama 2 directly! https://
xlang.ai/blog/openlemur -
Fine-tuning Llama 2 7B on Single GPU A100 and Google Colab
By
–
You can finetune a 7B Llama 2 model on a single GPU A100 for example, so you could even use Google Colab. But in general, most universities and companies are supportive of open source these days.
-
MoE vs Specialized Models: Questioning Current Practical Utility
By
–
Yeah. But unless you want to have a generalist model for all languages, is it really that useful to have a MoE approach compared to say the CodeLlama-34B-Python version? I mean eventually things might move to MoE but maybe it’s not that big of a deal atm.
-
Hardware Expert Misunderstands ML and Open Source Movements
By
–
one thing that was clear was that it was written by a Semi analyst — with all of the biases and shortcomings and misunderstandings that you'd expect from someone who deeply understands hardware, somewhat misunderstands ML & products and poorly understands open movements.
-
LangChain Twitter Fine-tuning Example Repository
By
–
example of that here: https://
github.com/langchain-ai/t
witter-finetune
… -
Gmail ChatLoader Integration for Email Model Finetuning
By
–
Over the weekend, I added a GMail ChatLoader integration to @langchain
, to help anyone to finetune models on their emails I evaluated it the old fashioned way – the eyeball test Here's how it did responding to various types of inquiries (VC, customer, integration, @swyx
) -
Meta Publishes Research Paper on SeamlessM4T Translation Model
By
–
In the interest of open science and sharing our research, we've published a paper outlining the work on our recently released SeamlessM4T all-in-one multilingual & multimodal translation model. Read the full paper https://
bit.ly/44uzanK -
LLM Finetuning Event Recording Available Now
By
–
Recording for Saturday's LLM Finetuning event is here! https://
youtu.be/S7o_ITTAh8w Grateful to @langchain @brevdev @replicatehq @anyscalecompute @metaphorsystems @_FireworksAI @phindsearch and everyone who came and hacked! (recording turned out bad unfortunately so unlisted fn) -
Code Llama Variants Surpass GPT-4 on HumanEval
By
–
Code Llama was just released 4 days ago. Since then, we already got 1) WizardCoder-34B (
https://
github.com/nlpxucan/Wizar
dLM/tree/main/WizardCoder
…)
2) Phind's finetuned CodeLLama-34B (
https://
phind.com/blog/code-llam
a-beats-gpt4
…) *Both reported to be surpassing GPT-4 on HumanEval. The open source community is amazing!