Base model:finetune:huggingfac... Base model:huggingfacetb/smoll... Dataset:allenai/llama-3.1-tulu... Dataset:allenai/tulu-3-sft-mix... En Instruct Llama Model-index Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/meditsolutions/SmolLM2-MedIT-Upscale-2B
SmolLM2 MedIT Upscale 2B Benchmarks
MMLU Pro: 10.78
GPQA: 1.9
MUSR: 2.45
BBH: 10.51
IFEval: 64.29 vs 88 (so35)-26.9%
MATH Lvl 5: 1.06
LLME Score: 0.31752
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)
SmolLM2 MedIT Upscale 2B Parameters and Internals
| LLM Name | SmolLM2 MedIT Upscale 2B |
| Repository 🤗 | https://huggingface.co/meditsolutions/SmolLM2-MedIT-Upscale-2B |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 4.2 GB |
| Updated | 2024-12-21 |
| Maintainer | meditsolutions |
| 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 | 4.46.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to SmolLM2 MedIT Upscale 2B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama3 2B Base | 8K / 4.7 GB | 445 | 1 |
Rank the SmolLM2 MedIT Upscale 2B 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217