Tiny Llm Sft 92M by wdndev

 ยป  All LLMs  ยป  wdndev  ยป  Tiny Llm Sft 92M   URL Share it on

  Autotrain compatible   Chat   Conversational   Custom code   Region:us   Safetensors   Tinyllm   Zh
Model Card on HF ๐Ÿค—: https://huggingface.co/wdndev/tiny_llm_sft_92m 

Tiny Llm Sft 92m 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 92M (wdndev/tiny_llm_sft_92m)

Tiny Llm Sft 92M Parameters and Internals

Model Type 
text generation, chat
Use Cases 
Limitations:
Low scores in evaluation due to resource constraints, Some generation errors
Considerations:
Main priority is to go through the entire process of large model training rather than achieving top performance.
Additional Notes 
The project aims to run through the entire large model process due to resource constraints.
Supported Languages 
Chinese (proficient)
Training Details 
Data Sources:
taobao, wikipedia, open source datasets
Data Volume:
approximately 9B tokens
Methodology:
RMSNorm, RoPE, MHA
Model Architecture:
RMSNorm, RoPE, MHA
Input Output 
Input Format:
<|system|> system text <|user|> user text <|assistant|>
Accepted Modalities:
text
Output Format:
text
LLM NameTiny Llm Sft 92m
Repository ๐Ÿค—https://huggingface.co/wdndev/tiny_llm_sft_92m 
Model Size92m
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 Version4.38.2
Tokenizer ClassChatGLMTokenizer
Padding Token<unk>
Vocabulary Size64798
Torch Data Typefloat16

Rank the Tiny Llm Sft 92M 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