152334H
joined 11/26/22, 4:43 AM has 631 karma
https://github.com/152334H
- Llama 4 Computer Use Agent
by 152334H on 4/7/25, 6:06 PM, with comments
- Calculating the cost of a Google DeepMind paper
by 152334H on 7/30/24, 10:26 AM, with comments
- Knowing Enough About MoE to Explain Dropped Tokens in GPT-4
by 152334H on 8/8/23, 10:25 PM, with comments
- Non-determinism in GPT-4 is caused by Sparse MoE
by 152334H on 8/4/23, 9:37 PM, with comments
- LLaVA: Large Language and Vision Assistant
by 152334H on 4/18/23, 5:37 AM, with comments
- Why can't TorToiSe be fine-tuned?
by 152334H on 2/11/23, 3:04 PM, with comments