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

Gigi Llama3 8B Chinese Zh by yaojialzc

 »  All LLMs  »  yaojialzc  »  Gigi Llama3 8B Chinese Zh   URL Share it on

  1687   
  Autotrain compatible   Conversational   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Instruct   Latest   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/yaojialzc/Gigi-Llama3-8B-Chinese-zh 

Gigi Llama3 8B Chinese Zh Benchmarks

ARC: 59.64 vs 96.7 (so35)-38.3%
HellaSwag: 80.28 vs 95.3 (gpt4)-15.8%
MMLU: 66.91 vs 88.3 (so35)-24.2%
TruthfulQA: 52.14 vs 59 (gpt4)-11.6%
WinoGrande: 76.48 vs 87.5 (gpt4)-12.6%
GSM8K: 66.79 vs 96.4 (so35)-30.7%
LLME Score: 0.21897
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gigi Llama3 8B Chinese Zh (yaojialzc/Gigi-Llama3-8B-Chinese-zh)

Gigi Llama3 8B Chinese Zh Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
text generation
Applications:
Chinese-English bilingual contexts
Primary Use Cases:
Improved tasks in Chinese and English
Additional Notes 
To achieve more efficient inference, vLLM is recommended for use with this model.
Supported Languages 
en (High), zh (High)
Training Details 
Data Sources:
Hermes, glaive-function-calling, refgpt_fact_v2, GPT3.5-translated Chinese data
Data Volume:
over 1.3 million pieces of high-quality Chinese-English bilingual corpus
Methodology:
fine-tuning with data such as Hermes and glaive-function-calling instructions, and GPT4 data translated using GPT3.5
Model Architecture:
Llama-3-8B
Input Output 
Input Format:
<|begin_of_text|><|system|>SYSTEM_PROMPT<|user|>USER_MESSAGE<|assistant|>ASSISTANT_RESPONSE
Accepted Modalities:
text
Output Format:
text with <|end_of_text|> as the pad token
LLM NameGigi Llama3 8B Chinese Zh
Repository 🤗https://huggingface.co/yaojialzc/Gigi-Llama3-8B-Chinese-zh 
Model Size8b
Required VRAM16.1 GB
Updated2025-02-22
Maintaineryaojialzc
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 zh
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Gigi Llama3 8B Chinese Zh

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB3927680
Mpasila Viking 8B1024K / 16.1 GB840
Hel V2 8B DARK FICTION1024K / 16.1 GB220
161024K / 16.1 GB1690
...di95 LewdStorytellerMix 8B 64K1024K / 16.1 GB692
Because Im Bored Nsfw11024K / 16.1 GB361
121024K / 16.1 GB600
MrRoboto ProLong 8B V4b1024K / 16.1 GB1070
MrRoboto ProLong 8B V1a1024K / 16.1 GB1080
MrRoboto ProLong 8B V2a1024K / 16.1 GB1020
Note: green Score (e.g. "73.2") means that the model is better than yaojialzc/Gigi-Llama3-8B-Chinese-zh.

Rank the Gigi Llama3 8B Chinese Zh 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