Hugging Face's logo

Cognitive Computations

community
https://erichartford.com
erhartford
ehartford
Activity Feed

AI & ML interests

Supervised Fine Tuning, DPO, and unalignment

Recent Activity

v2ray  new activity about 3 hours ago
cognitivecomputations/DeepSeek-V3-0324-AWQ:why tokenizer_config.json changed for AWQ model.
v2ray  new activity about 20 hours ago
cognitivecomputations/DeepSeek-V3-0324-AWQ:Does FlashMLA support kv cache fp8 dtype and how to enable FlashMLA ?
v2ray  new activity 2 days ago
cognitivecomputations/DeepSeek-R1-AWQ:AMD Instinct MI210 + vllm fail to run this model, any solutions please? Is there any other deepseek-r1-671b models that can run succesfully on AMD Instinct MI210 + vllm? Thanks!
View all activity

Organization Card
Community About org cards

Cognitive Computations is a group founded by Eric Hartford

Join Our Discord! Discord

Our core values:

  1. Integrity
  2. Curiosity
  3. Freedom
  4. Democratizing AI
  5. Helping Each Other and the Community
  6. Edge is the Future
  7. The Right to Keep and Bear Computations
  8. AI is a Confusing Space, May as Well Embrace Confusion(AICSMWEC)
  9. There are No Dumb Questions in AI

Collections 2

Dolphin 3.0
Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model.
DolphinLabeled Datasets
Eric Hartford has added labels to help you filter datasets, for your pleasure.