LLM EXPLORER 59,420 MODELS INDEXED

Fox 1 1.6B Instruct V0.1 by tensoropera

By tensoropera · 12 downloads
HF Repo ↗ Copy URL

Fox 1 1.6B Instruct V0.1 is an open-source language model by tensoropera. Features: 1.6b LLM, VRAM: 3.3GB, Context: 8K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.13.

  Arxiv:2411.05281 Base model:finetune:tensoroper... Base model:tensoropera/fox-1-1...   Conversational   En   Endpoints compatible   Instruct   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/tensoropera/Fox-1-1.6B-Instruct-v0.1 

Fox 1 1.6B Instruct V0.1 Parameters and Internals

Model Type 
instruction tuned, decoder-only, transformer-based, small language model
Additional Notes 
This model is an instruction tuned version and requires alignment for production use. A chat version will be released soon.
Supported Languages 
en (high)
Training Details 
Data Sources:
text, code data
Data Volume:
3 trillion tokens
Methodology:
3-stage data curriculum
Context Length:
8000
Hardware Used:
8*H100 GPUs
Model Architecture:
Grouped Query Attention (GQA) with 4 key-value heads and 16 attention heads
LLM NameFox 1 1.6B Instruct V0.1
Repository 🤗https://huggingface.co/tensoropera/Fox-1-1.6B-Instruct-v0.1 
Base Model(s)  tensoropera/Fox-1-1.6B   tensoropera/Fox-1-1.6B
Model Size1.6b
Required VRAM3.3 GB
Updated2026-07-23
Maintainertensoropera
Model Typellama
Instruction-BasedYes
Model Files  3.3 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Fox 1 1.6B Instruct V0.1

Best Alternatives
Context / RAM
Downloads
Likes
1.5 Pints 16K V0.116K / 3.1 GB5716
1.5 Pints 2K V0.12K / 3.1 GB4117
Note: green Score (e.g. "73.2") means that the model is better than tensoropera/Fox-1-1.6B-Instruct-v0.1.