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

Merak 7B V4 4bit Q128 AWQ by Ichsan2895

 »  All LLMs  »  Ichsan2895  »  Merak 7B V4 4bit Q128 AWQ   URL Share it on

  17   
  4-bit   4bit   Autotrain compatible   Awq   Conversational Dataset:ichsan2895/alpaca-gpt4... Dataset:ichsan2895/oasst top1 ...   Dataset:wikipedia   En   Endpoints compatible   Id   Mistral   Q128   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Ichsan2895/Merak-7B-v4_4bit_q128_awq 

Merak 7B V4 4bit Q128 AWQ Benchmarks

LLME Score: 0.18826
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Merak 7B V4 4bit Q128 AWQ (Ichsan2895/Merak-7B-v4_4bit_q128_awq)

Merak 7B V4 4bit Q128 AWQ Parameters and Internals

Model Type 
text-generation
Additional Notes 
Licensed under Creative Commons-By Attribution-Share Alike-Non Commercial (CC-BY-SA-NC 4.0). Model is designed to empower AI enthusiasts and researchers.
Supported Languages 
id (Indonesian), en (English)
Training Details 
Data Sources:
wikipedia, Ichsan2895/OASST_Top1_Indonesian, Ichsan2895/alpaca-gpt4-indonesian
Methodology:
fine-tuned using cleaned Indonesian Wikipedia articles
LLM NameMerak 7B V4 4bit Q128 AWQ
Repository 🤗https://huggingface.co/Ichsan2895/Merak-7B-v4_4bit_q128_awq 
Model Size7b
Required VRAM4.2 GB
Updated2025-02-22
MaintainerIchsan2895
Model Typemistral
Model Files  2.0 GB: 1-of-3   1.9 GB: 2-of-3   0.3 GB: 3-of-3
Supported Languagesid en
AWQ QuantizationYes
Quantization Typeawq|q128|4bit
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-sa-4.0
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Merak 7B V4 4bit Q128 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB790
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB197463
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB3349643
Ghost 7B Alpha AWQ32K / 4.2 GB800
Mahou 1.3a Mistral 7B AWQ32K / 4.2 GB801
Tess 7B V2.0 AWQ32K / 4.2 GB791
Mahou 1.3 Mistral 7B AWQ32K / 4.2 GB870
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB90
...reeze 7B 32K Instruct V1.0 AWQ32K / 4.7 GB90
...Instruct V0.2 AWQ 4bit Smashed32K / 4.2 GB901
Note: green Score (e.g. "73.2") means that the model is better than Ichsan2895/Merak-7B-v4_4bit_q128_awq.

Rank the Merak 7B V4 4bit Q128 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? 43470 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 v20241227
  Support LLM Explorer