Model Card on HF 🤗: https://huggingface.co/TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4
DiffMerge Pygmalion Main Onto V8P4 Benchmarks
ARC: 40.53 vs 96.7 (so35)-58.1%
HellaSwag: 67.48 vs 95.3 (gpt4)-29.2%
MMLU: 25.68 vs 88.3 (so35)-70.9%
TruthfulQA: 32.55 vs 59 (gpt4)-44.8%
WinoGrande: 62.51 vs 87.5 (gpt4)-28.6%
GSM8K: 1.14 vs 96.4 (so35)-98.8%
LLME Score: 0.13056
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)
DiffMerge Pygmalion Main Onto V8P4 Parameters and Internals
| LLM Name | DiffMerge Pygmalion Main Onto V8P4 |
| Repository 🤗 | https://huggingface.co/TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4 |
| Required VRAM | 12.3 GB |
| Updated | 2025-08-17 |
| Maintainer | TehVenom |
| Model Type | gptj |
| Model Files | |
| Model Architecture | GPTJForCausalLM |
| Model Max Length | 1024 |
| Transformers Version | 4.25.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Beginning of Sentence Token | <|endoftext|> |
| End of Sentence Token | <|endoftext|> |
| Unk Token | <|endoftext|> |
| Vocabulary Size | 50400 |
| Torch Data Type | float16 |
| Activation Function | gelu_new |
| Errors | replace |
Best Alternatives to DiffMerge Pygmalion Main Onto V8P4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| DiffMerge DollyGPT Pygmalion | 0K / 12.1 GB | 1927 | 2 |
| ChanMalion | 0K / 12.3 GB | 1937 | 9 |
| Javalion GPTJ | 0K / 12.3 GB | 1793 | 1 |
| Skegma GPTJ | 0K / 12.3 GB | 1777 | 0 |
| Javalion R | 0K / 12.3 GB | 1791 | 5 |
| Adventien GPTJ | 0K / 12.3 GB | 1795 | 0 |
| Janin GPTJ | 0K / 12.3 GB | 1795 | 0 |
| Javelin R | 0K / 12.3 GB | 1781 | 2 |
| Javelin GPTJ | 0K / 12.3 GB | 1785 | 4 |
| Janin R | 0K / 12.3 GB | 1775 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4 .
Rank the DiffMerge Pygmalion Main Onto V8P4 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? 50723 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124