Article
Process Reinforcement through Implicit Rewards
ganqu
• • 31zhongyah
BruceNju
AI & ML interests
RAG, RL, PEFT skills
Recent Activity
liked a model about 2 months ago
deepseek-ai/DeepSeek-V4-Pro liked a model 2 months ago
Qwen/Qwen3-Omni-30B-A3B-Instruct liked a dataset 6 months ago
open-r1/codeforcesOrganizations
upvoted an article 12 months ago
upvoted an article almost 2 years ago
Article
Llama 3.1 - 405B, 70B & 8B with multilinguality and long context
- +6
philschmid, osanseviero, alvarobartt, lvwerra, dvilasuero, reach-vb, marcsun13, pcuenq
• • 241 upvoted an article about 2 years ago
Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
- +3
ybelkada, timdettmers, artidoro, sgugger, smangrul
• • 180