DeepSeek-V3-FP8 Files

• LICENSE-CODE (1.0 KB)
• LICENSE-MODEL (13.4 KB)
• README.md (22.1 KB)
• README_WEIGHTS.md (3.6 KB)
• config.json (1.7 KB)
• configuration.json (73.0 B)
• configuration_deepseek.py (10.3 KB)
• figures/benchmark.png (179.3 KB)
• figures/niah.png (105.9 KB)
• inference/__pycache__/kernel.cpython-310.pyc (4.3 KB)
• inference/configs/config_16B.json (417.0 B)
• inference/configs/config_236B.json (455.0 B)
• inference/configs/config_671B.json (503.0 B)
• inference/convert.py (3.2 KB)
• inference/fp8_cast_bf16.py (3.2 KB)
• inference/generate.py (5.3 KB)
• inference/kernel.py (4.2 KB)
• inference/model.py (17.1 KB)
• inference/nohup.out (540.0 B)
• inference/requirements.txt (66.0 B)
• model-00001-of-000163.safetensors (4.9 GB)
• model-00002-of-000163.safetensors (4.0 GB)
• model-00003-of-000163.safetensors (4.0 GB)
• model-00004-of-000163.safetensors (4.0 GB)
• model-00005-of-000163.safetensors (4.0 GB)
• model-00006-of-000163.safetensors (4.1 GB)
• model-00007-of-000163.safetensors (4.0 GB)
• model-00008-of-000163.safetensors (4.0 GB)
• model-00009-of-000163.safetensors (4.0 GB)
• model-00010-of-000163.safetensors (4.0 GB)
• model-00011-of-000163.safetensors (4.0 GB)
• model-00012-of-000163.safetensors (1.2 GB)
• model-00013-of-000163.safetensors (4.0 GB)
• model-00014-of-000163.safetensors (4.0 GB)
• model-00015-of-000163.safetensors (4.0 GB)
• model-00016-of-000163.safetensors (4.0 GB)
• model-00017-of-000163.safetensors (4.0 GB)
• model-00018-of-000163.safetensors (4.0 GB)
• model-00019-of-000163.safetensors (4.0 GB)
• model-00020-of-000163.safetensors (4.0 GB)
• model-00021-of-000163.safetensors (4.0 GB)
• model-00022-of-000163.safetensors (4.0 GB)
• model-00023-of-000163.safetensors (4.0 GB)
• model-00024-of-000163.safetensors (4.0 GB)
• model-00025-of-000163.safetensors (4.0 GB)
• model-00026-of-000163.safetensors (4.0 GB)
• model-00027-of-000163.safetensors (4.0 GB)
• model-00028-of-000163.safetensors (4.0 GB)
• model-00029-of-000163.safetensors (4.0 GB)
• model-00030-of-000163.safetensors (4.0 GB)
• model-00031-of-000163.safetensors (4.0 GB)
• model-00032-of-000163.safetensors (4.0 GB)
• model-00033-of-000163.safetensors (4.0 GB)
• model-00034-of-000163.safetensors (1.6 GB)
• model-00035-of-000163.safetensors (4.0 GB)
• model-00036-of-000163.safetensors (4.0 GB)
• model-00037-of-000163.safetensors (4.0 GB)
• model-00038-of-000163.safetensors (4.0 GB)
• model-00039-of-000163.safetensors (4.0 GB)
• model-00040-of-000163.safetensors (4.0 GB)
• model-00041-of-000163.safetensors (4.0 GB)
• model-00042-of-000163.safetensors (4.0 GB)
• model-00043-of-000163.safetensors (4.0 GB)
• model-00044-of-000163.safetensors (4.0 GB)
• model-00045-of-000163.safetensors (4.0 GB)
• model-00046-of-000163.safetensors (4.0 GB)
• model-00047-of-000163.safetensors (4.0 GB)
• model-00048-of-000163.safetensors (4.0 GB)
• model-00049-of-000163.safetensors (4.0 GB)
• model-00050-of-000163.safetensors (4.0 GB)
• model-00051-of-000163.safetensors (4.0 GB)
• model-00052-of-000163.safetensors (4.0 GB)
• model-00053-of-000163.safetensors (4.0 GB)
• model-00054-of-000163.safetensors (4.0 GB)
• model-00055-of-000163.safetensors (4.0 GB)
• model-00056-of-000163.safetensors (1.6 GB)
• model-00057-of-000163.safetensors (4.0 GB)
• model-00058-of-000163.safetensors (4.0 GB)
• model-00059-of-000163.safetensors (4.0 GB)
• model-00060-of-000163.safetensors (4.0 GB)
• model-00061-of-000163.safetensors (4.0 GB)
• model-00062-of-000163.safetensors (4.0 GB)
• model-00063-of-000163.safetensors (4.0 GB)
• model-00064-of-000163.safetensors (4.0 GB)
• model-00065-of-000163.safetensors (4.0 GB)
• model-00066-of-000163.safetensors (4.0 GB)
• model-00067-of-000163.safetensors (4.0 GB)
• model-00068-of-000163.safetensors (4.0 GB)
• model-00069-of-000163.safetensors (4.0 GB)
• model-00070-of-000163.safetensors (4.0 GB)
• model-00071-of-000163.safetensors (4.0 GB)
• model-00072-of-000163.safetensors (4.0 GB)
• model-00073-of-000163.safetensors (4.0 GB)
• model-00074-of-000163.safetensors (4.0 GB)
• model-00075-of-000163.safetensors (4.0 GB)
• model-00076-of-000163.safetensors (4.0 GB)
• model-00077-of-000163.safetensors (4.0 GB)
• model-00078-of-000163.safetensors (1.6 GB)
• model-00079-of-000163.safetensors (4.0 GB)
• model-00080-of-000163.safetensors (4.0 GB)
• model-00081-of-000163.safetensors (4.0 GB)
• model-00082-of-000163.safetensors (4.0 GB)
• model-00083-of-000163.safetensors (4.0 GB)
• model-00084-of-000163.safetensors (4.0 GB)
• model-00085-of-000163.safetensors (4.0 GB)
• model-00086-of-000163.safetensors (4.0 GB)
• model-00087-of-000163.safetensors (4.0 GB)
• model-00088-of-000163.safetensors (4.0 GB)
• model-00089-of-000163.safetensors (4.0 GB)
• model-00090-of-000163.safetensors (4.0 GB)
• model-00091-of-000163.safetensors (4.0 GB)
• model-00092-of-000163.safetensors (4.0 GB)
• model-00093-of-000163.safetensors (4.0 GB)
• model-00094-of-000163.safetensors (4.0 GB)
• model-00095-of-000163.safetensors (4.0 GB)
• model-00096-of-000163.safetensors (4.0 GB)
• model-00097-of-000163.safetensors (4.0 GB)
• model-00098-of-000163.safetensors (4.0 GB)
• model-00099-of-000163.safetensors (4.0 GB)
• model-00100-of-000163.safetensors (1.6 GB)
• model-00101-of-000163.safetensors (4.0 GB)
• model-00102-of-000163.safetensors (4.0 GB)
• model-00103-of-000163.safetensors (4.0 GB)
• model-00104-of-000163.safetensors (4.0 GB)
• model-00105-of-000163.safetensors (4.0 GB)
• model-00106-of-000163.safetensors (4.0 GB)
• model-00107-of-000163.safetensors (4.0 GB)
• model-00108-of-000163.safetensors (4.0 GB)
• model-00109-of-000163.safetensors (4.0 GB)
• model-00110-of-000163.safetensors (4.0 GB)
• model-00111-of-000163.safetensors (4.0 GB)
• model-00112-of-000163.safetensors (4.0 GB)
• model-00113-of-000163.safetensors (4.0 GB)
• model-00114-of-000163.safetensors (4.0 GB)
• model-00115-of-000163.safetensors (4.0 GB)
• model-00116-of-000163.safetensors (4.0 GB)
• model-00117-of-000163.safetensors (4.0 GB)
• model-00118-of-000163.safetensors (4.0 GB)
• model-00119-of-000163.safetensors (4.0 GB)
• model-00120-of-000163.safetensors (4.0 GB)
• model-00121-of-000163.safetensors (4.0 GB)
• model-00122-of-000163.safetensors (1.6 GB)
• model-00123-of-000163.safetensors (4.0 GB)
• model-00124-of-000163.safetensors (4.0 GB)
• model-00125-of-000163.safetensors (4.0 GB)
• model-00126-of-000163.safetensors (4.0 GB)
• model-00127-of-000163.safetensors (4.0 GB)
• model-00128-of-000163.safetensors (4.0 GB)
• model-00129-of-000163.safetensors (4.0 GB)
• model-00130-of-000163.safetensors (4.0 GB)
• model-00131-of-000163.safetensors (4.0 GB)
• model-00132-of-000163.safetensors (4.0 GB)
• model-00133-of-000163.safetensors (4.0 GB)
• model-00134-of-000163.safetensors (4.0 GB)
• model-00135-of-000163.safetensors (4.0 GB)
• model-00136-of-000163.safetensors (4.0 GB)
• model-00137-of-000163.safetensors (4.0 GB)
• model-00138-of-000163.safetensors (4.0 GB)
• model-00139-of-000163.safetensors (4.0 GB)
• model-00140-of-000163.safetensors (4.0 GB)
• model-00141-of-000163.safetensors (2.9 GB)
• model-00142-of-000163.safetensors (4.0 GB)
• model-00143-of-000163.safetensors (4.0 GB)
• model-00144-of-000163.safetensors (4.0 GB)
• model-00145-of-000163.safetensors (4.0 GB)
• model-00146-of-000163.safetensors (4.0 GB)
• model-00147-of-000163.safetensors (4.0 GB)
• model-00148-of-000163.safetensors (4.0 GB)
• model-00149-of-000163.safetensors (4.0 GB)
• model-00150-of-000163.safetensors (4.0 GB)
• model-00151-of-000163.safetensors (4.0 GB)
• model-00152-of-000163.safetensors (4.0 GB)
• model-00153-of-000163.safetensors (4.0 GB)
• model-00154-of-000163.safetensors (4.0 GB)
• model-00155-of-000163.safetensors (4.0 GB)
• model-00156-of-000163.safetensors (4.0 GB)
• model-00157-of-000163.safetensors (4.0 GB)
• model-00158-of-000163.safetensors (4.0 GB)
• model-00159-of-000163.safetensors (4.0 GB)
• model-00160-of-000163.safetensors (4.9 GB)
• model-00161-of-000163.safetensors (4.0 GB)
• model-00162-of-000163.safetensors (4.0 GB)
• model-00163-of-000163.safetensors (6.1 GB)
• model.safetensors.index.json (9.0 MB)
• modeling_deepseek.py (74.0 KB)
• tokenizer.json (7.5 MB)
• tokenizer_config.json (3.1 KB)

Back to Main