Merged Model Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/MatteoKhan/fusion
Fusion 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)
Fusion Parameters and Internals
| LLM Name | Fusion |
| Repository 🤗 | https://huggingface.co/MatteoKhan/fusion |
| Merged Model | Yes |
| Model Size | 1.5b |
| Required VRAM | 6.2 GB |
| Updated | 2025-03-26 |
| Maintainer | goulue5 |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to Fusion
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ReaderLM V2 | 500K / 3.5 GB | 25748 | 582 |
| Reader Lm 1.5B | 250K / 3.1 GB | 1380 | 594 |
| DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 1744123 | 1078 |
| DeepScaleR 1.5B Preview | 128K / 7.1 GB | 71455 | 526 |
| Qwen2.5 1.5B | 128K / 3.1 GB | 207385 | 89 |
| AlphaMaze V0.2 1.5B | 128K / 3.5 GB | 2627 | 91 |
| Stella En 1.5B V5 | 128K / 6.2 GB | 581890 | 211 |
| AceInstruct 1.5B | 128K / 3.5 GB | 755 | 18 |
| Open RS3 | 128K / 0 GB | 215 | 16 |
| Qwen2 1.5B | 128K / 3.1 GB | 66122 | 90 |
Note: green Score (e.g. "73.2") means that the model is better than MatteoKhan/fusion .
Rank the Fusion 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? 45595 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227