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

Japanese Stablelm Instruct Gamma 7B AWQ Calib Ja 1K by mmnga

 »  All LLMs  »  mmnga  »  Japanese Stablelm Instruct Gamma 7B AWQ Calib Ja 1K   URL Share it on

  5   
  Arxiv:2306.00978   Autotrain compatible   Awq   Endpoints compatible   Instruct   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/mmnga/japanese-stablelm-instruct-gamma-7b-AWQ-calib-ja-1k 

Japanese Stablelm Instruct Gamma 7B AWQ Calib Ja 1K Benchmarks

LLME Score: 0.11552
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Japanese Stablelm Instruct Gamma 7B AWQ Calib Ja 1K (mmnga/japanese-stablelm-instruct-gamma-7b-AWQ-calib-ja-1k)
🌟 Advertise your project 🚀

Japanese Stablelm Instruct Gamma 7B AWQ Calib Ja 1K Parameters and Internals

Model Type 
Language Model, Text Generation
Use Cases 
Areas:
Research, Development
Considerations:
Performance may vary when running on non-A100 hardware.
Additional Notes 
The model uses AWQ quantization techniques for optimization and calibration with a dataset of random samples from Wikipedia in Japanese.
Supported Languages 
Japanese (Proficient)
Training Details 
Data Sources:
izumi-lab/wikipedia-ja-20230720
Data Volume:
1k samples
Methodology:
Activation quantization method used for calibration
Input Output 
Input Format:
Text format for Japanese recipe instructions
Accepted Modalities:
Text
Output Format:
Text
Performance Tips:
Use A100 GPU for better performance.
LLM NameJapanese Stablelm Instruct Gamma 7B AWQ Calib Ja 1K
Repository 🤗https://huggingface.co/mmnga/japanese-stablelm-instruct-gamma-7b-AWQ-calib-ja-1k 
Model Size7b
Required VRAM4.2 GB
Updated2025-09-28
Maintainermmnga
Model Typemistral
Instruction-BasedYes
Model Files  4.2 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Japanese Stablelm Instruct Gamma 7B AWQ Calib Ja 1K

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB60
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB209545
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB2274950
...reeze 7B 32K Instruct V1.0 AWQ32K / 4.7 GB90
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB60
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB60
...Instruct V0.2 AWQ 4bit Smashed32K / 4.2 GB81
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB61
Mistral 7B Instruct 32K AWQ32K / 4.2 GB41
...tral 7B Instruct V0.3 AWQ 4Bit32K / 4.2 GB81
Note: green Score (e.g. "73.2") means that the model is better than mmnga/japanese-stablelm-instruct-gamma-7b-AWQ-calib-ja-1k.

Rank the Japanese Stablelm Instruct Gamma 7B AWQ Calib Ja 1K 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? 51540 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 v20241124
  Support LLM Explorer