H2o Llama 3 8B Japanese Instruct by haqishen

 ยป  All LLMs  ยป  haqishen  ยป  H2o Llama 3 8B Japanese Instruct   URL Share it on

  Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Conversational Dataset:fujiki/japanese hh-rlh...   En   Gpt   H2o-llmstudio   Instruct   Ja   Llama   Region:us   Safetensors   Sharded   Tensorflow

H2o Llama 3 8B Japanese Instruct Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
H2o Llama 3 8B Japanese Instruct (haqishen/h2o-Llama-3-8B-Japanese-Instruct)
๐ŸŒŸ Advertise your project ๐Ÿš€

H2o Llama 3 8B Japanese Instruct Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model has the architecture: LlamaForCausalLM Quantization is supported with options for load_in_8bit or load_in_4bit.
Supported Languages 
en (fluent), ja (fluent)
Training Details 
Data Sources:
fujiki/japanese_hh-rlhf-49k
Context Length:
8000
Model Architecture:
LlamaForCausalLM
Input Output 
Input Format:
structured as messages
Accepted Modalities:
text
Output Format:
text generation
Performance Tips:
Ensure pip is installed with correct version of transformers. Provide a GPU-enabled environment for optimal performance.
LLM NameH2o Llama 3 8B Japanese Instruct
Repository ๐Ÿค—https://huggingface.co/haqishen/h2o-Llama-3-8B-Japanese-Instruct 
Base Model(s)  Meta Llama 3 8B Instruct   meta-llama/Meta-Llama-3-8B-Instruct
Model Size8b
Required VRAM16.1 GB
Updated2025-09-08
Maintainerhaqishen
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen ja
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to H2o Llama 3 8B Japanese Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB9912119
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB413
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB118215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB607450
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
Zero Llama 3.1 8B Beta61048K / 16.1 GB2251
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB173
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB113
Note: green Score (e.g. "73.2") means that the model is better than haqishen/h2o-Llama-3-8B-Japanese-Instruct.

Rank the H2o Llama 3 8B Japanese Instruct Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51187 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124