Autotrain compatible Dataset:huggingfaceh4/ultracha... Dataset:intel/orca dpo pairs Dpo En Endpoints compatible Gpt2 Model-index Region:us Safetensors Trl
Chat Gpt2 DPO Benchmarks
ARC: 23.98 vs 96.7 (so35)-75.2%
HellaSwag: 31.22 vs 95.3 (gpt4)-67.2%
MMLU: 24.95 vs 88.3 (so35)-71.7%
TruthfulQA: 41.26 vs 59 (gpt4)-30.1%
WinoGrande: 49.96 vs 87.5 (gpt4)-42.9%
LLME Score: 0.24119
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)
Chat Gpt2 DPO Parameters and Internals
| LLM Name | Chat Gpt2 DPO |
| Repository 🤗 | https://huggingface.co/Sharathhebbar24/chat_gpt2_dpo |
| Model Size | 124.4m |
| Required VRAM | 0.5 GB |
| Updated | 2024-10-07 |
| Maintainer | Sharathhebbar24 |
| Model Type | gpt2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GPT2LMHeadModel |
| License | apache-2.0 |
| Model Max Length | 1024 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 50257 |
| Torch Data Type | float32 |
| Activation Function | gelu_new |
Best Alternatives to Chat Gpt2 DPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| OCRonos Vintage | 0K / 0.2 GB | 653 | 65 |
| Originos Icn Savant | 0K / 0.5 GB | 31 | 1 |
| Quble Test Model V1 Pretrain | 0K / 0.5 GB | 208 | 2 |
| Awareness Test | 0K / 0.5 GB | 15 | 1 |
| Gpt2 NoLN | 0K / 0.5 GB | 252 | 2 |
| Gpt2 Alpaca Finetuned | 0K / 0.5 GB | 25 | 0 |
| Gpt2 Supervised | 0K / 0.5 GB | 13 | 0 |
| Sandboxlm | 0K / 0.5 GB | 7 | 2 |
| HW2 Supervised | 0K / 0.5 GB | 12 | 0 |
| Math Gpt2 Sft | 0K / 0.5 GB | 361 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than Sharathhebbar24/chat_gpt2_dpo .
Rank the Chat Gpt2 DPO 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? 36599 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803