Prakhar SaxenaTreading the LLM Labyrinth: A Comprehensive Guide to Open-Source LLMs and BeyondThis article will be a crash course on various open source LLMs, so that next time you come across something like…Feb 291Feb 291
Prakhar SaxenaFine Tuning Mistral (or ANY LLM) using LoRAEdit (1/2/2024): Included the keyword ‘Mistral’ in the title for better SEO.Jan 141Jan 141
Prakhar SaxenaFinetuning Mixtral 7bx8This is a simple tutorial for fine-tuning Mixtral with one A100 (40GB) GPU. We will use qlora to fine-tune our model on this Shakespeare…Jan 33Jan 33
Prakhar SaxenaTesting Mixtral 8x7B (MoE)Recently, after Google announced the Gemini suite of models, the Mistral Team posted a torrent link on X without any explanation. As usual…Dec 22, 20231Dec 22, 20231
Prakhar SaxenaFalcon 180B[New OSS king] vs GPT4[The Legend].Falcon 180B was released by TII (research facility based in UAE) yesterday as open source king. With 180 billion parameters and training of…Sep 7, 20231Sep 7, 20231