aichannel

- Ran the same prompt on DeepSeek R1 and O1
- DeepSeek gave me a better response and better code

🇨🇳

hey, have you tried the quantized ablated?

Engineer @farcaster. Founder bountycaster.xyz

Ex Phantom, 0x Project engineer.

From Italy originally, currently live in NYC

𝖒𝖆𝖓𝖉𝖆𝖙𝖚𝖒 𝖆𝖉 𝖆𝖘𝖙𝖗𝖆

hey, have you tried the quantized ablated? 
https://huggingface.co/mradermacher/deepseek-r1-qwen-2.5-32B-ablated-GGUF
https://huggingface.co/bartowski/deepseek-r1-qwen-2.5-32B-ablated-GGUF

Building Higher apparel at High Line 🧢 
Host at /clickcast /cpg || Husband to @shiwen

Chat

I love this model because there are plenty of ways to access it:
- Chat (requires Google login, no $$)
- API (very cheap, OpenAI compatible)
- Local (Ollama)

need to finally test out this deepseek chat at a minimum this weekend. are you accessing the reasoning model through chat or api atm?

Multiplying onchain economies. Working on interfaces /comint and intelligence @tenfold
Past: AI and crypto rubinovitz.com

RAG can be used with R1, isn't it mainly a concept around retrieval?

someone on twitter suggested using R1 instead of RAG and now I'm testing it

microsub.

well keep in mind o1 is old as hell wouldn’t sleep on openai