Arxiv:2411.15124 Arxiv:2412.08347 Allenai Autotrain compatible Base model:finetune:sultanr/sm... Base model:sultanr/smoltulu-1.... Conversational Dataset:allenai/rlvr-gsm-math-... Dpo En Endpoints compatible Gguf Huggingface Instruct Llama Region:us Rl Rlvr Safetensors Sft Slms Small Smollm Tulu3
Model Card on HF 🤗: https://huggingface.co/SultanR/SmolTulu-1.7b-Reinforced
SmolTulu 1.7B Reinforced Benchmarks
MMLU Pro: 8.48
GPQA: 3.47
MUSR: 2.41
BBH: 10.02
IFEval: 67.91 vs 88 (so35)-22.8%
MATH Lvl 5: 7.18
LLME Score: 0.27263
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)
SmolTulu 1.7B Reinforced Parameters and Internals
| LLM Name | SmolTulu 1.7B Reinforced |
| Repository 🤗 | https://huggingface.co/SultanR/SmolTulu-1.7b-Reinforced |
| Base Model(s) | |
| Model Size | 1.7b |
| Required VRAM | 3.4 GB |
| Updated | 2025-05-15 |
| Maintainer | SultanR |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to SmolTulu 1.7B Reinforced
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM2 1.7B Instruct 16K | 16K / 3.4 GB | 78 | 9 |
| SmolLM2 1.7B Instruct | 8K / 3.4 GB | 67417 | 617 |
| Superthoughts Lite V1 | 8K / 3.4 GB | 119 | 2 |
| SmolLM2 1.7B Instruct | 8K / 3.4 GB | 3842 | 4 |
| SmolLM2 1.7 Persona | 8K / 3.5 GB | 5 | 0 |
| ...urtis E1 SmolLM2 1.7B Instruct | 8K / 6.7 GB | 52 | 0 |
| ...ghts Lite 1.8B Experimental O1 | 8K / 3.6 GB | 17 | 1 |
| Cllm 1.0.0 340000 Instruct | 8K / 3.5 GB | 9 | 0 |
| SmolLM2 1.7B Open Thought | 8K / 3.4 GB | 5 | 0 |
| SmolLM2 1.7B R1 Distilled | 8K / 3.4 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than SultanR/SmolTulu-1.7b-Reinforced .
Rank the SmolTulu 1.7B Reinforced 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? 47368 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227