Autotrain compatible Base model:ai-sweden-models/gp... Base model:finetune:ai-sweden-... Conversational Da Dataset:databricks/databricks-... Dataset:laion/oig Dataset:openassistant/oasst1 En Endpoints compatible Gpt2 Instruct Is No Pytorch Region:us Safetensors Sv
Model Card on HF 🤗: https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m-instruct
GPT Sw3 126M Instruct Benchmarks
ARC: 23.38 vs 96.7 (so35)-75.8%
HellaSwag: 29.88 vs 95.3 (gpt4)-68.6%
MMLU: 23.78 vs 88.3 (so35)-73.1%
TruthfulQA: 42.65 vs 59 (gpt4)-27.7%
WinoGrande: 48.54 vs 87.5 (gpt4)-44.5%
GSM8K: 0.99 vs 96.4 (so35)-99%
LLME Score: 0.14135
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)
GPT Sw3 126M Instruct Parameters and Internals
| LLM Name | GPT Sw3 126M Instruct |
| Repository 🤗 | https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m-instruct |
| Base Model(s) | |
| Model Size | 126m |
| Required VRAM | 0.6 GB |
| Updated | 2025-09-23 |
| Maintainer | AI-Sweden-Models |
| Model Type | gpt2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | da sv no en is |
| Model Architecture | GPT2LMHeadModel |
| License | other |
| Model Max Length | 2048 |
| Transformers Version | 4.22.1 |
| Tokenizer Class | GPTSw3Tokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 64000 |
| Torch Data Type | float32 |
| Activation Function | gelu |
Rank the GPT Sw3 126M 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124