A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
1.3M Pulls 5 Tags Updated 4 months ago
For job and study
tryTo
fiirst tiime
deepseekV3
DeepSeek-V3 from Huggingface: Your powerful solution for handling complex requests and advanced coding tasks. Enhance your development workflow with state-of-the-art code assistance and intelligent problem-solving capabilities.
17.3K Pulls 1 Tag Updated 4 months ago
7,001 Pulls 2 Tags Updated 3 months ago
(Unsloth Dynamic Quants) A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
1,933 Pulls 3 Tags Updated 3 months ago
deepseek-v3-0324-Quants. - Q2_K is the lowest here - quantized = round((original - zero_point) / scale)
737 Pulls 1 Tag Updated 1 month ago
ollama run deepseek-v3
629 Pulls 1 Tag Updated 3 months ago
619 Pulls 5 Tags Updated 1 month ago
dynamic quants from unsloth, merged
246 Pulls 1 Tag Updated 1 month ago
DeepSeek-V3-Pruned-Coder-411B is a pruned version of the DeepSeek-V3 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.
178 Pulls 5 Tags Updated 1 month ago
101 Pulls 2 Tags Updated 3 months ago
This model has been developed based on DistilQwen2.5-DS3-0324-Series.
82 Pulls 7 Tags Updated 1 week ago
Single file version with (Dynamic Quants) A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
66 Pulls 4 Tags Updated 2 months ago
18 Pulls 1 Tag Updated 3 months ago