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

Llama2 13B Chinese Chat by shareAI

 »  All LLMs  »  shareAI  »  Llama2 13B Chinese Chat   URL Share it on

  0   
  Chat   Chatgpt Dataset:freedomintelligence/sh... Dataset:shareai/sharegpt-chine...   Endpoints compatible   Instruct   Llama2   Lora   Region:us   Zh
Model Card on HF 🤗: https://huggingface.co/shareAI/llama2-13b-Chinese-chat 

Llama2 13B Chinese Chat Benchmarks

ARC: 73.9 vs 96.7 (so35)-23.6%
HellaSwag: 72.8 vs 95.3 (gpt4)-23.6%
MMLU: 55.5 vs 88.3 (so35)-37.1%
TruthfulQA: 45.11 vs 59 (gpt4)-23.5%
WinoGrande: 76.64 vs 87.5 (gpt4)-12.4%
GSM8K: 33.8 vs 96.4 (so35)-64.9%
OpenCompas: 48.7 vs 73.3 (gpt4)-33.6%
Exam: 55.2 vs 77.2 (gpt4)-28.5%
Language: 36.3 vs 62 (gpt4)-41.5%
Knowledge: 55.9 vs 73.5 (gpt4)-23.9%
Understand: 57.8 vs 70 (gpt4)-17.4%
Reasoning: 45.1 vs 74.4 (gpt4)-39.4%
LLME Score: 0.12649
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama2 13B Chinese Chat (shareAI/llama2-13b-Chinese-chat)
🌟 Advertise your project 🚀

Llama2 13B Chinese Chat Parameters and Internals

Model Type 
text generation, question-answering
Use Cases 
Areas:
research, commercial applications
Considerations:
推荐继续二次训练以针对性调优对话效果
Additional Notes 
实测用中文对话体验优于baichuan13b(仅主观感受)。还需进一步调优。
Supported Languages 
zh (high)
Training Details 
Data Sources:
shareAI/ShareGPT-Chinese-English-90k, FreedomIntelligence/ShareGPT-CN
Input Output 
Input Format:
text in zh
Accepted Modalities:
text
Output Format:
text
Performance Tips:
二次训练以针对性调优对话效果
Release Notes 
Version:
v1
Date:
2023-07-19
Notes:
首个llama2 13b中文对话版本放出.
Version:
v2
Date:
2023-07-23
Notes:
完成第2个epoch训练放出，测试有更好的对话体验.
Version:
bimoGPT
Date:
2023-08-03
Notes:
拥有自我身份认知、不错的代码问答能力.
Version:
2023-08-21
Date:
2023-08-21
Notes:
更新世界模型排名榜，超越国内社区收费模型.
LLM NameLlama2 13B Chinese Chat
Repository 🤗https://huggingface.co/shareAI/llama2-13b-Chinese-chat 
Model Size13b
Required VRAM0 GB
Updated2025-08-16
MaintainershareAI
Model Files  1.0 GB   2.0 GB   0.0 GB   0.0 GB
Supported Languageszh
Model ArchitectureAutoModel
Is Biasednone
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|q_proj|up_proj|k_proj|o_proj|v_proj|down_proj
LoRA Alpha16
LoRA Dropout0.05
R Param64

Best Alternatives to Llama2 13B Chinese Chat

Best Alternatives
Context / RAM
Downloads
Likes
...p 13B DPO Lora Hh Rlhf Ja V1.10K / 0.8 GB01
Nous Hermes Llama2 Llamafile0K /  GB2592
BimoGPT Llama2 13B0K / 0.6 GB07
PhysicsLlama 13B0K / 0 GB01
...fast Codellama 13B Instruct Hf0K / 13 GB11
...lama 2 13B Alpaca Spanish LoRA0K / 1.7 GB02
Medalpaca Lora 13B 8bit0K / 0.1 GB01
MythoMax L2 13B GGUF0K / 5.4 GB124181173
Llama 3 13B Instruct V0.1 GGUF0K / 5.1 GB12245
Hermes 2 Pro Llama 3 13B GGUF0K / 4.6 GB510
Note: green Score (e.g. "73.2") means that the model is better than shareAI/llama2-13b-Chinese-chat.

Rank the Llama2 13B Chinese Chat 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? 50705 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