Arxiv:1910.09700 Arxiv:2410.01679 Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/rho-math-... Endpoints compatible Llama Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/realtreetune/rho-1b-sft-MATH
Rho 1B Sft MATH Benchmarks
MMLU Pro: 1.3
GPQA: 0.34
MUSR: 2.9
BBH: 4.2
IFEval: 21.21 vs 88 (so35)-75.9%
MATH Lvl 5: 2.19
LLME Score: 0.26206
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)
Rho 1B Sft MATH Parameters and Internals
| LLM Name | Rho 1B Sft MATH |
| Repository 🤗 | https://huggingface.co/realtreetune/rho-1b-sft-MATH |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 2.2 GB |
| Updated | 2025-01-20 |
| Maintainer | realtreetune |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.38.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Rho 1B Sft MATH
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LWM Text Chat 1M | 1024K / 13.5 GB | 1764 | 176 |
| LWM Text 1M | 1024K / 13.5 GB | 1124 | 28 |
| JOSIE 1M Base | 1024K / 13.5 GB | 12 | 1 |
| JOSIE 1M Base | 1024K / 13.5 GB | 6 | 1 |
| Llama 3.2 1B | 128K / 2.5 GB | 1245477 | 1466 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 1034903 | 706 |
| MiniThinky V2 1B Llama 3.2 | 128K / 4.9 GB | 6408 | 32 |
| Dolphin3.0 Llama3.2 1B | 128K / 2.5 GB | 7462 | 19 |
| Orca Mini V9 6 1B Instruct | 128K / 2.5 GB | 291 | 3 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 72761 | 56 |
Note: green Score (e.g. "73.2") means that the model is better than realtreetune/rho-1b-sft-MATH .
Rank the Rho 1B Sft MATH 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? 41636 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227