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 32K Instruct V1.0 AWQ by chienweichang

 »  All LLMs  »  chienweichang  »  Breeze 7B 32K Instruct V1.0 AWQ   URL Share it on

  6   
  4-bit   Autotrain compatible   Awq   Conversational   En   Endpoints compatible   Instruct   Mistral   Quantized   Region:us   Safetensors   Zh

Breeze 7B 32K Instruct V1.0 AWQ 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: 0.21717
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Breeze 7B 32K Instruct V1.0 AWQ Parameters and Internals

Additional Notes 
This model supports AWQ, a low-bit weight quantization method, providing efficient 4-bit quantization especially for Transformers-based inference. It can be used via several libraries and frameworks such as Text Generation Webui, vLLM, and Transformers.
Supported Languages 
zh (presumed), en (presumed)
LLM NameBreeze 7B 32K Instruct V1.0 AWQ
Repository 🤗https://huggingface.co/chienweichang/Breeze-7B-32k-Instruct-v1_0-AWQ 
Base Model(s)  Breeze 7B Instruct V1.0   MediaTek-Research/Breeze-7B-Instruct-v1_0
Model Size7b
Required VRAM4.7 GB
Updated2024-11-21
Maintainerchienweichang
Model Typemistral
Instruction-BasedYes
Model Files  4.7 GB
Supported Languageszh en
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size62464
Torch Data Typefloat16
Breeze 7B 32K Instruct V1.0 AWQ (chienweichang/Breeze-7B-32k-Instruct-v1_0-AWQ)

Best Alternatives to Breeze 7B 32K Instruct V1.0 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB50
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB1062522
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB9171941
Mistral 7B Instruct V0.1 AWQ32K / 4.2 GB21561137
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB440
...Instruct V0.2 AWQ 4bit Smashed32K / 4.2 GB111
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB50
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB1751
Mistral 7B Instruct 32K AWQ32K / 4.2 GB71
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB71
Note: green Score (e.g. "73.2") means that the model is better than chienweichang/Breeze-7B-32k-Instruct-v1_0-AWQ.

Rank the Breeze 7B 32K Instruct V1.0 AWQ 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