Uncensored DeepSeek-R1-0528-Qwen3-8B via Heretic: 4/100 refusals (from 89), KL 0.041. Reasoning model, MIT.
182 Pulls 5 Tags Updated 2 days ago
DeepSeek-R1-0528-Qwen3-8B
1,272 Pulls 1 Tag Updated 5 months ago
DeepSeek-R1-0528-Qwen3-8B-IQ4_NL
3,927 Pulls 1 Tag Updated 1 year ago
DeepSeek R1 0528 Qwen3 8B with tool calling/MCP support
3,328 Pulls 1 Tag Updated 1 year ago
DeepSeek R1 0528 Qwen3 8B Q4 with tool calling
2,422 Pulls 1 Tag Updated 1 year ago
DeepSeek-R1-0528-Qwen3-8B,包含2个量化模型:Q5_K_M,Q8_0
1,814 Pulls 2 Tags Updated 1 year ago
DeepSeek-R1-0528 仍然使用 2024 年 12 月所发布的 DeepSeek V3 Base 模型作为基座,但在后训练过程中投入了更多算力,显著提升了模型的思维深度与推理能力。这个8B精馏版本编程能力都爆表!
1,101 Pulls 1 Tag Updated 1 year ago
(251GB) unsloth/DeepSeek-R1-0528-GGUF:Q2_K_XL
254 Pulls 7 Tags Updated 1 year ago
(168GB) unsloth/DeepSeek-R1-0528-GGUF:IQ1_S
247 Pulls 3 Tags Updated 1 year ago