Arxiv:2411.15124 Arxiv:2412.08347 Allenai Autotrain compatible Base model:finetune:huggingfac... Base model:huggingfacetb/smoll... Conversational Dataset:allenai/llama-3.1-tulu... Dataset:allenai/tulu-3-sft-mix... Dpo En Endpoints compatible Gguf Huggingface Instruct Llama Model-index Quantized Region:us Safetensors Sft Slms Small Smollm Tulu3
Model Card on HF 🤗: https://huggingface.co/SultanR/SmolTulu-1.7b-Instruct
SmolTulu 1.7B Instruct Benchmarks
MMLU Pro: 7.89
GPQA: 2.57
MUSR: 1.92
BBH: 12.26
IFEval: 65.41 vs 88 (so35)-25.7%
MATH Lvl 5: 2.64
LLME Score: 0.30837
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 Instruct Parameters and Internals
| LLM Name | SmolTulu 1.7B Instruct |
| Repository 🤗 | https://huggingface.co/SultanR/SmolTulu-1.7b-Instruct |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 3.4 GB |
| Updated | 2025-02-05 |
| Maintainer | SultanR |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.45.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to SmolTulu 1.7B Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...truct Gradient 1048K IMat GGUF | 1024K / 2 GB | 200 | 6 |
| ...B Instruct Gradient 1048K GGUF | 1024K / 3.2 GB | 80 | 3 |
| Llama 3 8B Instruct 262K GGUF | 256K / 3.2 GB | 232 | 2 |
| ... 8B Instruct Reasoner 1o1 V0.3 | 128K / 16.1 GB | 388 | 7 |
| Nsfw Plz Gguf Me | 128K / 16.1 GB | 35 | 3 |
| ...lama 3.1 Cantonese 8B Instruct | 128K / 16.1 GB | 91 | 5 |
| Alpha R S V2 Q8 0 GGUF | 39K / 8.5 GB | 18 | 0 |
| Llama 3 Cantonese 8B Instruct | 8K / 16.1 GB | 173 | 6 |
| ...ama3 8B Chinese Chat GGUF 8bit | 8K / 8.5 GB | 885 | 165 |
| ...hinese 8B Instruct V3 Accident | 8K / 16.1 GB | 87 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than SultanR/SmolTulu-1.7b-Instruct .
Rank the SmolTulu 1.7B Instruct 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227