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 Fast Instruct GPTQ by dahara1

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

  1885   
  Arxiv:2307.09288   4bit   Autotrain compatible   En   Gptq   Instruct   Ja   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/dahara1/ELYZA-japanese-Llama-2-7b-fast-instruct-GPTQ 

ELYZA Japanese Llama 2 7B Fast Instruct GPTQ Benchmarks

ARC: 53.16 vs 96.7 (so35)-45%
HellaSwag: 78.25 vs 95.3 (gpt4)-17.9%
MMLU: 47.07 vs 88.3 (so35)-46.7%
TruthfulQA: 39.08 vs 59 (gpt4)-33.8%
WinoGrande: 73.24 vs 87.5 (gpt4)-16.3%
GSM8K: 7.88 vs 96.4 (so35)-91.8%
LLME Score: 0.1494
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 Fast Instruct GPTQ (dahara1/ELYZA-japanese-Llama-2-7b-fast-instruct-GPTQ)
🌟 Advertise your project 🚀

ELYZA Japanese Llama 2 7B Fast Instruct GPTQ Parameters and Internals

Model Type 
text generation
Additional Notes 
The model is a quantized version of the original ELYZA-japanese-Llama-2-7b model, specifically tuned for Japanese instructions.
Supported Languages 
ja (Japanese), en (English)
Training Details 
Methodology:
Quantization and additional pre-training in Japanese followed by post-training and speed-up tuning.
Input Output 
Accepted Modalities:
text
LLM NameELYZA Japanese Llama 2 7B Fast Instruct GPTQ
Repository 🤗https://huggingface.co/dahara1/ELYZA-japanese-Llama-2-7b-fast-instruct-GPTQ 
Base Model(s)  ...A Japanese Llama 2 7B Instruct   elyza/ELYZA-japanese-Llama-2-7b-instruct
Model Size7b
Required VRAM4.1 GB
Updated2025-09-23
Maintainerdahara1
Model Typellama
Instruction-BasedYes
Model Files  4.1 GB   4.1 GB
Supported Languagesja en
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size45043
Torch Data Typefloat16

Best Alternatives to ELYZA Japanese Llama 2 7B Fast Instruct GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
... 7B 32K Instructions V4 Marlin32K / 4.1 GB80
Llama 2 7B 32K Instruct GPTQ32K / 3.9 GB1427
CodeLlama 7B Instruct GPTQ16K / 3.9 GB133346
...a 7B Instruct GPTQ Calib Ja 1K16K / 3.9 GB60
...echless Tora Code 7B V1.0 GPTQ16K / 3.9 GB121
CausalLM 7B GPTQ8K / 5.9 GB155
Leo Hessianai 7B Chat GPTQ8K / 3.9 GB230
...ssianai 7B Chat Bilingual GPTQ8K / 3.9 GB70
Xgen 7B 8K Open Instruct Gptq8K / 4.2 GB24
Deepseek Math 7B Instruct GPTQ4K / 4.8 GB70
Note: green Score (e.g. "73.2") means that the model is better than dahara1/ELYZA-japanese-Llama-2-7b-fast-instruct-GPTQ.

Rank the ELYZA Japanese Llama 2 7B Fast Instruct GPTQ 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? 51545 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