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

Blossom V5 Llama3 8B by Azure99

 »  All LLMs  »  Azure99  »  Blossom V5 Llama3 8B   URL Share it on

  81   
  Autotrain compatible   Conversational Dataset:azure99/blossom-chat-v... Dataset:azure99/blossom-math-v... Dataset:azure99/blossom-orca-v... Dataset:azure99/blossom-wizard...   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/Azure99/blossom-v5-llama3-8b 

Blossom V5 Llama3 8B Benchmarks

MMLU Pro: 13.4
GPQA: 2.01
MUSR: 5.31
BBH: 18.31
IFEval: 43.43 vs 88 (so35)-50.6%
ARC: 56.83 vs 96.7 (so35)-41.2%
HellaSwag: 83.05 vs 95.3 (gpt4)-12.9%
MMLU: 65.48 vs 88.3 (so35)-25.8%
TruthfulQA: 57.12 vs 59 (gpt4)-3.2%
WinoGrande: 78.37 vs 87.5 (gpt4)-10.4%
GSM8K: 44.43 vs 96.4 (so35)-53.9%
MATH Lvl 5: 4.38
LLME Score: 0.25072
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Blossom V5 Llama3 8B (Azure99/blossom-v5-llama3-8b)

Blossom V5 Llama3 8B Parameters and Internals

Model Type 
conversational LLM, dialogue model
Use Cases 
Areas:
chatbots, conversational AI
Additional Notes 
Training included high-quality datasets in both Chinese and English for comprehensive context comprehension capabilities.
Supported Languages 
zh (high-quality), en (high-quality)
Training Details 
Data Sources:
Azure99/blossom-chat-v3, Azure99/blossom-math-v4, Azure99/blossom-wizard-v3, Azure99/blossom-orca-v3
Methodology:
Improved using high-quality data distilled from gpt-4-0125-preview with a two-stage training process involving large single-turn and multi-turn dialogue datasets.
Model Architecture:
Fine-tuned based on Meta-Llama-3-8B
Input Output 
Input Format:
Dialogue-based input scenarios
Accepted Modalities:
text
Output Format:
Conversational text with guidance to append `<|end_of_text|>` at the end
LLM NameBlossom V5 Llama3 8B
Repository 🤗https://huggingface.co/Azure99/blossom-v5-llama3-8b 
Model Size8b
Required VRAM16.1 GB
Updated2024-12-22
MaintainerAzure99
Model Typellama
Model Files  10.0 GB: 1-of-2   6.1 GB: 2-of-2
Supported Languageszh en
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Blossom V5 Llama3 8B

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB4850678
MrRoboto ProLong 8B V4i1024K / 16.1 GB461
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
MrRoboto ProLong 8B V2b1024K / 16.1 GB1770
MrRoboto ProLong 8B V1n1024K / 16.1 GB1560
MrRoboto ProLong 8B V4b1024K / 16.1 GB940
...o ProLongBASE Pt6 Unaligned 8B1024K / 16.1 GB600
MrRoboto ProLong 8B V4c1024K / 16.1 GB790
HEL V0.8 8B LONG DARK1024K / 16.1 GB2000
MrRoboto ProLong 8B V1a1024K / 16.1 GB1070
Note: green Score (e.g. "73.2") means that the model is better than Azure99/blossom-v5-llama3-8b.

Rank the Blossom V5 Llama3 8B 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? 40123 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.
Release v20241217
  Support LLM Explorer