Model Card on HF 🤗: https://huggingface.co/LordNoah/Alpaca_refine_gpt2_e0_se1
Alpaca Refine Gpt2 E0 Se1 Benchmarks
ARC: 29.18 vs 96.7 (so35)-69.8%
HellaSwag: 45.35 vs 95.3 (gpt4)-52.4%
MMLU: 26.91 vs 88.3 (so35)-69.5%
TruthfulQA: 37.89 vs 59 (gpt4)-35.8%
WinoGrande: 54.3 vs 87.5 (gpt4)-37.9%
GSM8K: 0.68 vs 96.4 (so35)-99.3%
LLME Score: 0.22627
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)
Alpaca Refine Gpt2 E0 Se1 Parameters and Internals
| LLM Name | Alpaca Refine Gpt2 E0 Se1 |
| Repository 🤗 | https://huggingface.co/LordNoah/Alpaca_refine_gpt2_e0_se1 |
| Model Size | 774m |
| Required VRAM | 3.1 GB |
| Updated | 2025-02-02 |
| Maintainer | LordNoah |
| Model Type | gpt2 |
| Model Files | |
| Model Architecture | GPT2LMHeadModel |
| License | apache-2.0 |
| Model Max Length | 1024 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 50257 |
| Torch Data Type | float32 |
| Activation Function | gelu_new |
| Errors | replace |
Best Alternatives to Alpaca Refine Gpt2 E0 Se1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...T2 774M CINDER SHOW MULTI CHAT | 0K / 0 GB | 208 | 2 |
| Alpaca Refine Gpt2 E1 Se0 | 0K / 3.1 GB | 1081 | 0 |
| Alpaca Tuned Gpt2 | 0K / 3.1 GB | 1080 | 0 |
| Alpaca Spin Gpt2 E1 Se0 | 0K / 3.1 GB | 1066 | 0 |
| Alpaca Spin Gpt2 E0 Se1 | 0K / 3.1 GB | 1082 | 0 |
| Alpaca Spin Tuned Gpt2 Large | 0K / 3.1 GB | 1073 | 0 |
| Alpaca Refine Tuned Gpt2 Large | 0K / 3.1 GB | 1034 | 0 |
| Turkish Gpt2 Large | 0K / 3.1 GB | 3346 | 38 |
| Gpt2 Large Lora Sft1 | 0K / 1.6 GB | 1289 | 0 |
| Gpt2 Large Lora Sft2 | 0K / 1.6 GB | 1296 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than LordNoah/Alpaca_refine_gpt2_e0_se1 .
Rank the Alpaca Refine Gpt2 E0 Se1 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