Merged Model Base model:newsbang/homer-v1.0... Base model:qwen/qwen2.5-math-7... Newsbang/homer-v1.0-qwen2.5-7b Qwen/qwen2.5-math-7b Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/HeraiHench/Marge-Qwen-Math-7B
Marge Qwen Math 7B 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)
Marge Qwen Math 7B Parameters and Internals
| LLM Name | Marge Qwen Math 7B |
| Repository 🤗 | https://huggingface.co/HeraiHench/Marge-Qwen-Math-7B |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 7b |
| Required VRAM | 14.8 GB |
| Updated | 2025-02-04 |
| Maintainer | HeraiHench |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.47.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Marge Qwen Math 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 7B Instruct 1M | 986K / 15.4 GB | 36112 | 192 |
| Qwen2.5 7B MixStock V0.1 | 986K / 15.2 GB | 329 | 3 |
| Qwen2.5 7B RRP 1M | 986K / 15.2 GB | 177 | 4 |
| Qwen2.5 7B CelestialHarmony 1M | 986K / 14.8 GB | 58 | 4 |
| COCO 7B Instruct 1M | 986K / 15.2 GB | 77 | 9 |
| Q2.5 Instruct 1M Harmony | 986K / 15.2 GB | 38 | 1 |
| SJT 7B V1.1 | 986K / 14.8 GB | 45 | 1 |
| Impish QWEN 7B 1M | 986K / 15.2 GB | 45 | 1 |
| SJT 8B V1.1 | 986K / 17.8 GB | 18 | 0 |
| Qwen2.5 7B DeepSeek R1 1M | 986K / 15.2 GB | 70 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than HeraiHench/Marge-Qwen-Math-7B .
Rank the Marge Qwen Math 7B 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? 42884 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227