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

Breeze 7B Instruct V1.0 by MediaTek-Research

 »  All LLMs  »  MediaTek-Research  »  Breeze 7B Instruct V1.0   URL Share it on

  9571   
  Arxiv:2403.02712   Autotrain compatible   Conversational   En   Endpoints compatible   Instruct   Mistral   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Zh

Breeze 7B Instruct V1.0 Benchmarks

ARC: 61.35 vs 96.7 (so35)-36.6%
HellaSwag: 82.59 vs 95.3 (gpt4)-13.3%
MMLU: 62.11 vs 88.3 (so35)-29.7%
TruthfulQA: 53.46 vs 59 (gpt4)-9.4%
WinoGrande: 77.74 vs 87.5 (gpt4)-11.2%
GSM8K: 43.14 vs 96.4 (so35)-55.2%
LLME Score: 0.25673
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Breeze 7B Instruct V1.0 Parameters and Internals

Model Type 
Causal decoder-only transformer
Use Cases 
Areas:
Research, Commercial applications
Applications:
Q&A, RAG, Multi-round chat, Summarization
Primary Use Cases:
Commonly seen tasks
Limitations:
No special handling for harmfulness
Additional Notes 
Expanded vocabulary with 30,000 Traditional Chinese tokens. Faster inference for Traditional Chinese compared to other models.
Supported Languages 
English (Supported), Traditional Chinese (Supported)
Training Details 
Methodology:
Fine-tuning from base model.
Context Length:
8000
Model Architecture:
Causal decoder-only transformer
Input Output 
Input Format:
~~SYS_PROMPT [INST] QUERY1 [/INST] RESPONSE1 [INST] QUERY2 [/INST]
Accepted Modalities:
text
Output Format:
text
LLM NameBreeze 7B Instruct V1.0
Repository 🤗https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0 
Model Size7b
Required VRAM15 GB
Updated2024-11-21
MaintainerMediaTek-Research
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   4.6 GB: 3-of-4   0.5 GB: 4-of-4
Supported Languageszh en
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size61952
Torch Data Typebfloat16
Breeze 7B Instruct V1.0 (MediaTek-Research/Breeze-7B-Instruct-v1_0)

Quantized Models of the Breeze 7B Instruct V1.0

Model
Likes
Downloads
VRAM
Breeze 7B Instruct V1.0 AWQ0444 GB
...reeze 7B 32K Instruct V1.0 AWQ064 GB
Breeze 7B Instruct V1.0 AWQ174 GB
...Instruct V1.0 Bnb 4bit Smashed074 GB

Best Alternatives to Breeze 7B Instruct V1.0

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25148
SpydazWeb AI HumanAI RP512K / 14.4 GB971
SpydazWeb AI HumanAI 002512K / 14.4 GB171
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB70
...1 Summarize 64K LoRANET Merged128K / 14.4 GB60
Mistral 7B Instruct V0.232K / 14.4 GB8879132578
Mistral 7B Instruct V0.132K / 14.4 GB1819631528
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB49253
...ty Instruct 3M 0625 Mistral 7B32K / 14.4 GB48563
Note: green Score (e.g. "73.2") means that the model is better than MediaTek-Research/Breeze-7B-Instruct-v1_0.

Rank the Breeze 7B Instruct V1.0 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? 38149 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 v20241110
  Support LLM Explorer