Tiny Llm Sft 76M Llama by wdndev

 ยป  All LLMs  ยป  wdndev  ยป  Tiny Llm Sft 76M Llama   URL Share it on

  Autotrain compatible   Chat   Custom code   Pytorch   Region:us   Tinyllm   Zh

Tiny Llm Sft 76m Llama Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tiny Llm Sft 76M Llama (wdndev/tiny_llm_sft_76m_llama)

Tiny Llm Sft 76M Llama Parameters and Internals

Model Type 
text generation, chat
Additional Notes 
The first priority was to complete the large model workflow rather than achieving high-quality fine-tuning.
Supported Languages 
Chinese (High)
Training Details 
Data Sources:
Chinese Wikipedia
Data Volume:
9 billion tokens
Methodology:
pre-training -> instruction fine-tuning -> human alignment
Model Architecture:
RMSNorm, RoPE, MHA
LLM NameTiny Llm Sft 76m Llama
Repository ๐Ÿค—https://huggingface.co/wdndev/tiny_llm_sft_76m_llama 
Model Size76m
Required VRAM0.2 GB
Updated2025-02-22
Maintainerwdndev
Model Typetinyllm
Model Files  0.2 GB
Supported Languageszh
Model ArchitectureTinyllmForCausalLM
Context Length1024
Model Max Length1024
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size49958
Torch Data Typefloat16

Rank the Tiny Llm Sft 76M Llama 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227