DeepSeek-V3-bf16 / README.md
tabrezahmed's picture
Update README.md
70657e5 verified
|
raw
history blame
678 Bytes
metadata
base_model:
  - deepseek-ai/DeepSeek-V3
license: mit
datasets:
  - openai/gdpval
  - openai/gsm8k
  - HuggingFaceFW/finepdfs
  - HuggingFaceM4/FineVision
  - HuggingFaceFW/fineweb
  - HuggingFaceFW/fineweb-2
  - HuggingFaceH4/ultrachat_200k
  - HuggingFaceVLA/libero
  - HuggingFaceFW/fineweb-edu
language:
  - ur
  - hi
  - en
  - kn
metrics:
  - accuracy
  - bertscore
  - bleurt
  - cer
  - charcut_mt
  - code_eval
new_version: Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
library_name: adapter-transformers
tags:
  - agent
  - chemistry
  - art
  - code
  - medical
  - not-for-all-audiences
  - music
  - finance
  - biology
  - climate
  - moe
  - legal
  - text-generation-inference
  - merge

Model converted from DeepSeek-V3 to BF16.