Model Card on HF 🤗: https://huggingface.co/LordNoah/latent_gpt2_medium_alpaca_e2
Latent Gpt2 Medium Alpaca E2 Benchmarks
ARC: 26.96 vs 96.7 (so35)-72.1%
HellaSwag: 39.72 vs 95.3 (gpt4)-58.3%
MMLU: 26.93 vs 88.3 (so35)-69.5%
TruthfulQA: 41.01 vs 59 (gpt4)-30.5%
WinoGrande: 53.2 vs 87.5 (gpt4)-39.2%
GSM8K: 0.38 vs 96.4 (so35)-99.6%
LLME Score: 0.21839
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)
Latent Gpt2 Medium Alpaca E2 Parameters and Internals
| LLM Name | Latent Gpt2 Medium Alpaca E2 |
| Repository 🤗 | https://huggingface.co/LordNoah/latent_gpt2_medium_alpaca_e2 |
| Model Size | 354.8m |
| Required VRAM | 1.4 GB |
| Updated | 2025-02-02 |
| Maintainer | LordNoah |
| Model Type | gpt2 |
| Model Files | |
| Model Architecture | GPT2LMHeadModel |
| License | mit |
| Model Max Length | 1024 |
| Transformers Version | 4.38.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 50257 |
| Torch Data Type | float32 |
| Activation Function | gelu_new |
| Errors | replace |
Best Alternatives to Latent Gpt2 Medium Alpaca E2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gpt2 Finetuned Headliner | 0K / 1.4 GB | 173 | 1 |
| Latent Gpt2 Medium Alpaca E4 | 0K / 1.4 GB | 123 | 0 |
| Spin Gpt2 Medium Alpaca E3 | 0K / 1.4 GB | 124 | 0 |
| Latent Gpt2 Medium Alpaca E3 | 0K / 1.4 GB | 122 | 0 |
| Spin Gpt2 Medium Alpaca E2 | 0K / 1.4 GB | 125 | 0 |
| GPT2 Review | 0K / 1.4 GB | 25 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than LordNoah/latent_gpt2_medium_alpaca_e2 .
Rank the Latent Gpt2 Medium Alpaca E2 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