🧠
Shrew 2b model by btbtyler09
⭐ 37.4
🧠
Model

Shrew 2b

by btbtyler09 hf-model--btbtyler09--shrew-2b
Nexus Index
37.4 Top 15%
S: Semantic 50
A: Authority 0
P: Popularity 10
R: Recency 97
Q: Quality 50
Tech Context
2 Params
4.096K Ctx
Vital Performance
122 DL / 30D
0.0%
Source →
Audited 37.4 FNI Score
Tiny 2B Params
4k Context
122 Downloads
8G GPU ~3GB Est. VRAM
Commercial APACHE License
Model Information Summary
Entity Passport
Registry ID hf-model--btbtyler09--shrew-2b
License Apache-2.0
Provider huggingface
💾

Compute Threshold

~2.8GB VRAM

Interactive
Analyze Hardware
â–ŧ

* Static estimation for 4-Bit Quantization.

📜

Cite this model

Academic & Research Attribution

BibTeX 
@misc{hf_model__btbtyler09__shrew_2b,
  author = {btbtyler09},
  title = {Shrew 2b Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/btbtyler09/shrew-2b}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}
APA Style
btbtyler09. (2026). Shrew 2b [Model]. Free2AITools. https://huggingface.co/btbtyler09/shrew-2b

đŸ”ŦTechnical Deep Dive

Full Specifications [+]

Quick Commands

đŸĻ™ Ollama Run
ollama run shrew-2b
🤗 HF Download
huggingface-cli download btbtyler09/shrew-2b
đŸ“Ļ Install Lib
pip install -U transformers

⚖ī¸ Nexus Index V2.0

Methodology Index Protocol
37.4
TOP 15% SYSTEM IMPACT
Semantic (S) 50
Authority (A) 0
Popularity (P) 10
Recency (R) 97
Quality (Q) 50

đŸ’Ŧ Index Insight

FNI V2.0 for Shrew 2b: Semantic (S:50), Authority (A:0), Popularity (P:10), Recency (R:97), Quality (Q:50).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit
Unbiased Data Node Refresh: VFS Live
---

🚀 What's Next?

📊

Find Training Datasets

Discover datasets compatible with this model

📈

Compare Benchmarks

See how this model ranks on standard tests

⚡

Deployment Guide

Understand deployment options

Technical Deep Dive

Shrew LoRA Adapters

Work in progress -- adapters are functional but under active development.

LoRA adapters for Qwen/Qwen3.5-2B fine-tuned for structured extraction as part of a production RAG application. These are the models that power Shrew's structured extraction pipeline.

Adapters

Adapter Task LoRA Rank Status
extract_metadata/ Extract structured metadata (title, authors, dates, etc.) from document text r32 / alpha 64 Production
summarize_document/ Generate document summaries r32 / alpha 64 Production
semantic_chunk_beta/ Split documents into semantically coherent sections r64 / alpha 128 Beta (10k subset, full dataset training in progress)

Usage

Load with PEFT on the base model:

python 
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-2B")

model = PeftModel.from_pretrained(base, "./extract_metadata")

GGUF versions can be used with llama.cpp as LoRA adapters:

bash 
llama-cli -m Qwen3.5-2B.gguf --lora semantic_chunk_beta.gguf -p ""

For the full pipeline integration, see shrew-server.

Sampling Parameters

Use Qwen 3.5 instruct-general parameters with enable_thinking=False:

  • temperature: 0.7
  • top_p: 0.8
  • top_k: 20

License

Same as base model (Qwen/Qwen3.5-2B).

⚠ī¸ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

  • â€ĸ Benchmark scores may vary based on evaluation methodology and hardware configuration.
  • â€ĸ VRAM requirements are estimates; actual usage depends on quantization and batch size.
  • â€ĸ FNI scores are relative rankings and may change as new models are added.
  • ⚠ License Unknown: Verify licensing terms before commercial use.

Social Proof

HuggingFace Hub
122Downloads
Hub Discussions
🤗 Data Source: Hugging Face ↗
🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹī¸ Verify with original source

🛡ī¸ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id
hf-model--btbtyler09--shrew-2b
slug
btbtyler09--shrew-2b
source
huggingface
author
btbtyler09
license
Apache-2.0
tags
transformers, safetensors, gguf, qwen3.5, lora, peft, vllm, document-processing, text-generation, base_model:qwen/qwen3.5-2b, base_model:adapter:qwen/qwen3.5-2b, license:apache-2.0, endpoints_compatible, region:us

⚙ī¸ Technical Specs

architecture
null
params billions
2
context length
4,096
pipeline tag
text-generation
vram gb
2.8
vram is estimated
true
vram formula
VRAM ≈ (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)

📊 Engagement & Metrics

downloads
122
stars
0
forks
0

Data indexed from public sources. Updated daily.