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

Blossom V2 3B by Azure99

 »  All LLMs  »  Azure99  »  Blossom V2 3B   URL Share it on

  933   

Blossom V2 3B is an open-source language model by Azure99. Features: 3b LLM, VRAM: 6GB, License: apache-2.0, Instruction-Based, HF Score: 36, LLM Explorer Score: 0.14, Arc: 35.3, HellaSwag: 54.1, MMLU: 24, TruthfulQA: 43.1, WinoGrande: 58.8, GSM8K: 0.5.

  Bloom Dataset:azure99/blossom-chat-v... Dataset:azure99/blossom-math-v...   Dataset:ehartford/dolphin Dataset:wizardlm/wizardlm evol...   En   Endpoints compatible   Instruct   Pytorch   Region:us   Zh
Model Card on HF 🤗: https://huggingface.co/Azure99/blossom-v2-3b 

Blossom V2 3B Benchmarks

ARC: 35.32 vs 96.7 (so35)-63.5%
HellaSwag: 54.1 vs 95.3 (gpt4)-43.2%
MMLU: 23.99 vs 88.3 (so35)-72.8%
TruthfulQA: 43.11 vs 59 (gpt4)-26.9%
WinoGrande: 58.8 vs 87.5 (gpt4)-32.8%
GSM8K: 0.53 vs 96.4 (so35)-99.5%
LLME Score: 0.13947
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Blossom V2 3B (Azure99/blossom-v2-3b)
🌟 Advertise your project 🚀

Blossom V2 3B Parameters and Internals

Model Type 
Conversational, Instruction-tuned
Use Cases 
Areas:
Conversational AI
Primary Use Cases:
Chatbot applications
Supported Languages 
zh (Chinese), en (English)
Training Details 
Data Sources:
Azure99/blossom-chat-v1, Azure99/blossom-math-v1, ehartford/dolphin, WizardLM/WizardLM_evol_instruct_V2_196k
Methodology:
Instruction fine-tuning in two phases: 120K Wizard and 180K Dolphin single round instruction dataset for 1 epoch; 60K Blossom chat and 2K Blossom math multiple round dialogue dataset for 3 epochs.
Input Output 
Input Format:
Chat input format with prompts like: A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
Accepted Modalities:
text
Output Format:
Chat output format
LLM NameBlossom V2 3B
Repository 🤗https://huggingface.co/Azure99/blossom-v2-3b 
Model Size3b
Required VRAM6 GB
Updated2026-04-02
MaintainerAzure99
Model Typebloom
Instruction-BasedYes
Model Files  6.0 GB
Supported Languageszh en
Model ArchitectureBloomForCausalLM
Licenseapache-2.0
Transformers Version4.31.0
Tokenizer ClassBloomTokenizerFast
Padding Token<pad>
Vocabulary Size250880
Torch Data Typefloat16

Best Alternatives to Blossom V2 3B

Best Alternatives
Context / RAM
Downloads
Likes
Bloom 3B Conversational0K / 6.1 GB112
Gpt3 Finnish 3B Instruct0K / 12.7 GB61
...a English Instruction Existing0K / 3.6 GB41
...nstruction Slimorca Pretrained0K / 3.6 GB80
...nstruction Slimorca Pretrained0K / 3.6 GB70
Instruct Tuned 3B0K / 6 GB00
Note: green Score (e.g. "73.2") means that the model is better than Azure99/blossom-v2-3b.

Rank the Blossom V2 3B 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