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

Llama3 8B Traditional Chinese Roleplay Chat Lora by Tarklanse

 »  All LLMs  »  Tarklanse  »  Llama3 8B Traditional Chinese Roleplay Chat Lora   URL Share it on

  10   
  Adapter   Conversational Dataset:tarklanse/traditional ...   En   Finetuned   Lora   Peft   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/Tarklanse/Llama3-8B_Traditional_Chinese_roleplay_chat_lora 

Llama3 8B Traditional Chinese Roleplay Chat Lora Benchmarks

LLME Score: 0.19346
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 8B Traditional Chinese Roleplay Chat Lora (Tarklanse/Llama3-8B_Traditional_Chinese_roleplay_chat_lora)

Llama3 8B Traditional Chinese Roleplay Chat Lora Parameters and Internals

Model Type 
text-generation
Additional Notes 
Known issue: responses may begin repeating after lengthy dialogues.
Supported Languages 
zh (high), en (medium)
Training Details 
Data Sources:
Tarklanse/Traditional_Chinese_roleplay_chat_Dataset
Data Volume:
Approximately 9,000 instructions, 12.6MB in total
Methodology:
Utilized alpaca-format for dataset
Hardware Used:
L4 GPU on Google Colab
Input Output 
Input Format:
Prompts need to specify character persona and personality; dialog examples may be necessary for clarification.
Accepted Modalities:
text
Performance Tips:
Provide detailed prompts including character perspectives.
LLM NameLlama3 8B Traditional Chinese Roleplay Chat Lora
Repository 🤗https://huggingface.co/Tarklanse/Llama3-8B_Traditional_Chinese_roleplay_chat_lora 
Model Size8b
Required VRAM0.2 GB
Updated2025-02-22
MaintainerTarklanse
Model Files  0.2 GB
Supported Languageszh en
Model ArchitectureAdapter
Licensecc-by-sa-4.0
Model Max Length8192
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|k_proj|down_proj|up_proj|v_proj|o_proj|q_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to Llama3 8B Traditional Chinese Roleplay Chat Lora

Best Alternatives
Context / RAM
Downloads
Likes
... 3 8B Instruct Bvr Finetune V38K / 16.1 GB50
Flippa V60K / 0 GB91
Llama 3 Korean 8B R V 0.10K / 0 GB70
...a7 4262 4abb 97b1 1879f340d32e0K / 0.3 GB220
Llama 3.1 8B Smart Lora0K / 0.2 GB01
...ultiModal Llama 3 8B Finetuned0K / 0 GB151
...lama 3 1 8B Instruct Orca ORPO0K / 0.1 GB142
FatDPOv2LoRA0K / 0.8 GB41
Adapter Test0K / 0.1 GB60
Vortex20K / 4.4 GB80
Note: green Score (e.g. "73.2") means that the model is better than Tarklanse/Llama3-8B_Traditional_Chinese_roleplay_chat_lora.

Rank the Llama3 8B Traditional Chinese Roleplay Chat 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? 43470 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 v20241227
  Support LLM Explorer