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

ELYZA Japanese Llama 2 7B Instruct AWQ by dahara1

 »  All LLMs  »  dahara1  »  ELYZA Japanese Llama 2 7B Instruct AWQ   URL Share it on

  6   
  Arxiv:2306.00978   Arxiv:2307.09288   Autotrain compatible   Awq   En   Instruct   Ja   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/dahara1/ELYZA-japanese-Llama-2-7b-instruct-AWQ 

ELYZA Japanese Llama 2 7B Instruct AWQ Benchmarks

LLME Score: 0.10951
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ELYZA Japanese Llama 2 7B Instruct AWQ (dahara1/ELYZA-japanese-Llama-2-7b-instruct-AWQ)
🌟 Advertise your project 🚀

ELYZA Japanese Llama 2 7B Instruct AWQ Parameters and Internals

Model Type 
Instruction-following, Quantized
Use Cases 
Areas:
Japanese instruction following
Limitations:
Quantized model deteriorates instruction-following ability
Supported Languages 
ja (Japanese), en (English)
Training Details 
Methodology:
Additional pre-training in Japanese instruction
Input Output 
Input Format:
[INST] <> Input Prompt <>
Accepted Modalities:
text
Output Format:
Generated text
LLM NameELYZA Japanese Llama 2 7B Instruct AWQ
Repository 🤗https://huggingface.co/dahara1/ELYZA-japanese-Llama-2-7b-instruct-AWQ 
Base Model(s)  ...Japanese CodeLlama 7B Instruct   elyza/ELYZA-japanese-CodeLlama-7b-instruct
Model Size7b
Required VRAM3.9 GB
Updated2025-08-22
Maintainerdahara1
Model Typellama
Instruction-BasedYes
Model Files  3.9 GB
Supported Languagesja en
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.33.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to ELYZA Japanese Llama 2 7B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB162
CodeLlama 7B Instruct AWQ16K / 3.9 GB15034
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB171
...ama 7B Instruct Hf W4 G128 AWQ16K / 3.9 GB70
CausalLM 7B AWQ8K / 5.8 GB83
Leo Hessianai 7B Chat AWQ8K / 3.9 GB241
...essianai 7B Chat Bilingual AWQ8K / 3.9 GB72
...epseek Math 7B Instruct AWQ Q44K / 4.8 GB210
Llama 2 7B Ft Instruct Es AWQ4K / 3.9 GB61
Swallow 7B Instruct AWQ4K / 4.1 GB81
Note: green Score (e.g. "73.2") means that the model is better than dahara1/ELYZA-japanese-Llama-2-7b-instruct-AWQ.

Rank the ELYZA Japanese Llama 2 7B Instruct 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? 50835 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