LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen2 1.5B Instruct Function Calling V1 by devanshamin

 »  All LLMs  »  devanshamin  »  Qwen2 1.5B Instruct Function Calling V1   URL Share it on

  49   

Qwen2 1.5B Instruct Function Calling V1 is an open-source language model by devanshamin. Features: 1.5b LLM, VRAM: 6.2GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.14.

  Adapter Base model:adapter:qwen/qwen2-... Base model:qwen/qwen2-1.5b-ins...   Conversational Dataset:devanshamin/gem-viggo-...   Finetuned   Generated from trainer   Instruct   Lora   Peft   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/devanshamin/Qwen2-1.5B-Instruct-Function-Calling-v1 

Qwen2 1.5B Instruct Function Calling V1 Benchmarks

LLME Score: 0.14318
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 1.5B Instruct Function Calling V1 (devanshamin/Qwen2-1.5B-Instruct-Function-Calling-v1)
🌟 Advertise your project 🚀

Qwen2 1.5B Instruct Function Calling V1 Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model adds a chat template to the tokenizer configuration that supports multiple tools, but the fine-tuning was specifically on a dataset that uses a single tool. Various usage examples including tool usage for function calling have been provided.
Training Details 
Data Sources:
devanshamin/gem-viggo-function-calling
LLM NameQwen2 1.5B Instruct Function Calling V1
Repository 🤗https://huggingface.co/devanshamin/Qwen2-1.5B-Instruct-Function-Calling-v1 
Base Model(s)  Qwen/Qwen2-1.5B-Instruct   Qwen/Qwen2-1.5B-Instruct
Model Size1.5b
Required VRAM6.2 GB
Updated2026-04-04
Maintainerdevanshamin
Instruction-BasedYes
Model Files  0.1 GB   5.0 GB: 1-of-2   1.2 GB: 2-of-2   0.0 GB
Model ArchitectureAdapter
Licenseapache-2.0
Model Max Length32768
Is Biasednone
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdown_proj|gate_proj|up_proj
LoRA Alpha64
LoRA Dropout0.05
R Param32
Errorsreplace

Best Alternatives to Qwen2 1.5B Instruct Function Calling V1

Best Alternatives
Context / RAM
Downloads
Likes
WavGPT 1.00K / 0 GB92
...Qwen2 1.5B Instruct 17188248560K / 0 GB50
Note: green Score (e.g. "73.2") means that the model is better than devanshamin/Qwen2-1.5B-Instruct-Function-Calling-v1.

Rank the Qwen2 1.5B Instruct Function Calling V1 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer