Autotrain compatible Base model:finetune:openai-com... Base model:openai-community/gp... Dataset:customized Endpoints compatible Generated from trainer Gpt2 Lora Pytorch Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Mikivis/gpt2-large-lora-sft
Gpt2 Large Lora Sft Benchmarks
ARC: 26.79 vs 96.7 (so35)-72.3%
HellaSwag: 44.15 vs 95.3 (gpt4)-53.7%
MMLU: 25.82 vs 88.3 (so35)-70.8%
TruthfulQA: 39.06 vs 59 (gpt4)-33.8%
WinoGrande: 55.09 vs 87.5 (gpt4)-37%
LLME Score: 0.17719
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)
Gpt2 Large Lora Sft Parameters and Internals
| Training Details |
|
| LLM Name | Gpt2 Large Lora Sft |
| Repository 🤗 | https://huggingface.co/Mikivis/gpt2-large-lora-sft |
| Base Model(s) | |
| Model Size | 774m |
| Required VRAM | 1.6 GB |
| Updated | 2025-01-20 |
| Maintainer | Mikivis |
| Model Type | gpt2 |
| Model Files | |
| Model Architecture | GPT2LMHeadModel |
| License | mit |
| Model Max Length | 1024 |
| Transformers Version | 4.32.1 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 50257 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
| Activation Function | gelu_new |
Best Alternatives to Gpt2 Large Lora Sft
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...T2 774M CINDER SHOW MULTI CHAT | 0K / 0 GB | 205 | 2 |
| Alpaca Refine Gpt2 E1 Se0 | 0K / 3.1 GB | 677 | 0 |
| Alpaca Tuned Gpt2 | 0K / 3.1 GB | 692 | 0 |
| Alpaca Refine Tuned Gpt2 Large | 0K / 3.1 GB | 686 | 0 |
| Alpaca Spin Gpt2 E1 Se0 | 0K / 3.1 GB | 681 | 0 |
| Alpaca Refine Gpt2 E0 Se1 | 0K / 3.1 GB | 685 | 0 |
| Alpaca Spin Tuned Gpt2 Large | 0K / 3.1 GB | 683 | 0 |
| Alpaca Spin Gpt2 E0 Se1 | 0K / 3.1 GB | 679 | 0 |
| Turkish Gpt2 Large | 0K / 3.1 GB | 5074 | 37 |
| Gpt2 Large Lora Sft1 | 0K / 1.6 GB | 722 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Mikivis/gpt2-large-lora-sft .
Rank the Gpt2 Large Lora Sft 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