Dayhoff 170M GRS 76000 is an open-source language model by microsoft. Features: 170m LLM, VRAM: 0.3GB, Context: 256K, License: mit.
Arxiv:2502.12479 Custom code Dataset:microsoft/dayhoff Endpoints compatible Jamba Protein-generation Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/microsoft/Dayhoff-170M-GRS-76000
Dayhoff 170M GRS 76000 Parameters and Internals
| LLM Name | Dayhoff 170M GRS 76000 |
| Repository 🤗 | https://huggingface.co/microsoft/Dayhoff-170M-GRS-76000 |
| Model Size | 170m |
| Required VRAM | 0.3 GB |
| Updated | 2026-03-27 |
| Maintainer | microsoft |
| Model Type | jamba |
| Model Files | |
| Model Architecture | JambaForCausalLM |
| License | mit |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | ProteinTokenizer |
| Padding Token | ! |
| Vocabulary Size | 40 |
| Torch Data Type | bfloat16 |
Best Alternatives to Dayhoff 170M GRS 76000
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Dayhoff 170M UR50 | 256K / 0.7 GB | 115 | 4 |
Rank the Dayhoff 170M GRS 76000 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? 51648 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b