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

Llama 3 8B Instruct 262K Chinese Lora by shibing624

 »  All LLMs  »  shibing624  »  Llama 3 8B Instruct 262K Chinese Lora   URL Share it on

  0   
  Adapter   Chinese   Conversational   En   Finetuned   Instruct   Llama3   Lora   Meta   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese-lora 

Llama 3 8B Instruct 262K Chinese Lora Benchmarks

LLME Score: 0.15197
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B Instruct 262K Chinese Lora (shibing624/llama-3-8b-instruct-262k-chinese-lora)
🌟 Advertise your project 🚀

Llama 3 8B Instruct 262K Chinese Lora Parameters and Internals

Model Type 
text generation, multilingual, dialogue
Use Cases 
Areas:
R&D, commercial applications
Applications:
multilingual dialogue systems
Primary Use Cases:
text generation, multilingual tasks, dialogue systems
Limitations:
Knowledge-related queries may produce hallucinations, particularly in classical Chinese knowledge.
Additional Notes 
This model extends Llama-3 8B's context from 16K to 262K tokens.
Supported Languages 
zh (fluent), en (fluent)
Training Details 
Data Sources:
shibing624/DPO-En-Zh-20k-Preference, SlimPajama
Methodology:
ORPO method with NTK-aware interpolation and RoPE theta optimization
Context Length:
262144
Hardware Used:
NVIDIA L40S GPUs
Input Output 
Input Format:
open-chat-template
Accepted Modalities:
text
Output Format:
text
Performance Tips:
The model performs better with optimized RoPE theta settings for extended context.
LLM NameLlama 3 8B Instruct 262K Chinese Lora
Repository 🤗https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese-lora 
Model Size8b
Required VRAM0.1 GB
Updated2025-09-23
Maintainershibing624
Instruction-BasedYes
Model Files  0.1 GB
Supported Languageszh en
Model ArchitectureAdapter
Licenseother
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|down_proj|o_proj|k_proj|q_proj|up_proj|gate_proj
LoRA Alpha16
LoRA Dropout0.05
R Param8

Best Alternatives to Llama 3 8B Instruct 262K Chinese Lora

Best Alternatives
Context / RAM
Downloads
Likes
... 3 8B Instruct Bvr Finetune V38K / 16.1 GB70
Flippa V60K / 0 GB16531
...B Instruct DPO 0R100L PoliTune0K / 16.1 GB60
...B Lora Rag Citation Generation0K / 0 GB113
...a 8B Rank 128 INSTRUCT Adapter0K / 0.7 GB181
...lama 3 1 8B Instruct Orca ORPO0K / 0.1 GB42
Vortex20K / 4.4 GB80
Llama3 8B Instruct Code0K / 0.2 GB41
...t Sft Rewriting Fs Promptbench0K / 0.1 GB50
Llama 3 8B Claudstruct V30K / 0.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than shibing624/llama-3-8b-instruct-262k-chinese-lora.

Rank the Llama 3 8B Instruct 262K Chinese Lora 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? 51534 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