An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
2.7M Pulls 64 Tags Updated 1 year ago
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
277.5K Pulls 7 Tags Updated 1 year ago
1,251 Pulls 1 Tag Updated 4 months ago
This is a brand new Mixture of Export (MoE) model from DeepSeek, specializing in coding instructions. (quantized IQ4_XS)
16.3K Pulls 3 Tags Updated 5 months ago
DeepSeek-Coder-V2-Lite-Instruct.Q6_K
2,153 Pulls 1 Tag Updated 4 months ago
Codex 0.1 Mini is a fast version of Codex 0.1 based on deepseek-coder-v2.
40 Pulls 1 Tag Updated 11 months ago
A strong, economical, and efficient Mixture-of-Experts language model with Tool Calling support.
8,738 Pulls 3 Tags Updated 1 year ago
7,057 Pulls 23 Tags Updated 1 year ago
https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF
6,124 Pulls 22 Tags Updated 1 year ago
This model was converted to GGUF format from deepseek-ai/DeepSeek-Coder-V2-Lite-Base using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
1,120 Pulls 1 Tag Updated 1 year ago
Quantized version of DeepSeek Coder v1.5 and Q8_0_L quantization of v2 model form bartowski/DeepSeek-Coder-V2-Lite-Base-GGUF and bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF
1,218 Pulls 14 Tags Updated 1 year ago
313 Pulls 3 Tags Updated 1 year ago
183 Pulls 1 Tag Updated 1 year ago
109 Pulls 3 Tags Updated 1 year ago
72 Pulls 1 Tag Updated 2 years ago
65 Pulls 1 Tag Updated 1 year 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.
1,390 Pulls 5 Tags Updated 1 year ago
DeepSeek-R1-Pruned-Coder-411B is a pruned version of the DeepSeek-R1 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.
92 Pulls 3 Tags Updated 1 year ago