Arxiv:2410.17215 Autotrain compatible Conversational Dataset:minillm/pile-diff samp... Dataset:monology/pile-uncopyri... En Endpoints compatible Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/MiniLLM/MiniPLM-Qwen-500M
MiniPLM Qwen 500M Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MiniPLM Qwen 500M Parameters and Internals
| LLM Name | MiniPLM Qwen 500M |
| Repository 🤗 | https://huggingface.co/MiniLLM/MiniPLM-Qwen-500M |
| Model Size | 1.8b |
| Required VRAM | 1.9 GB |
| Updated | 2025-05-14 |
| Maintainer | MiniLLM |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.45.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to MiniPLM Qwen 500M
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Dhanishtha | 128K / 3.5 GB | 82 | 2 |
| LaConfiance PRYMMAL ECE TW3 | 128K / 7.1 GB | 8 | 0 |
| Qwen1.5 1.8B Chat | 32K / 3.7 GB | 31010 | 50 |
| Qwen1.5 1.8B | 32K / 3.7 GB | 29647 | 50 |
| MiniPLM Qwen 200M | 32K / 0.8 GB | 265 | 4 |
| Qwen1.5 1.8B Seed Sft | 32K / 3.7 GB | 7 | 0 |
| Neural Chat Mini V2.2 1.8B | 32K / 3.7 GB | 21 | 6 |
| Qwen1.5 Wukong 1.8B | 32K / 3.7 GB | 8 | 4 |
| Orca 2.0 Tau 1.8B | 32K / 3.7 GB | 27 | 9 |
| SmartQwen1.5 1.8B Orpo V1 | 32K / 3.7 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than MiniLLM/MiniPLM-Qwen-500M .
Rank the MiniPLM Qwen 500M 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! 🌟
What open-source LLMs or SLMs are you in search of? 47340 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227