Arxiv:2401.06066 Autotrain compatible Conversational Custom code Deepseek Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat
Deepseek MoE 16B Chat Benchmarks
MMLU Pro: 10.71
MUSR: 5.26
BBH: 6.57
IFEval: 36.63 vs 88 (so35)-58.4%
MATH Lvl 5: 2.57
LLME Score: 0.2034
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Deepseek MoE 16B Chat Parameters and Internals
| Model Type |
|
| LLM Name | Deepseek MoE 16B Chat |
| Repository 🤗 | https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat |
| Model Size | 16.4b |
| Required VRAM | 32.8 GB |
| Updated | 2025-09-23 |
| Maintainer | deepseek-ai |
| Model Type | deepseek |
| Model Files | |
| Model Architecture | DeepseekForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizerFast |
| Beginning of Sentence Token | <｜begin▁of▁sentence｜> |
| End of Sentence Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 102400 |
| Torch Data Type | bfloat16 |
Best Alternatives to Deepseek MoE 16B Chat
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Deepseek MoE 16B Base | 4K / 32.8 GB | 8607 | 127 |
Note: green Score (e.g. "73.2") means that the model is better than deepseek-ai/deepseek-moe-16b-chat .
Rank the Deepseek MoE 16B Chat Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51534 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124