Model Card on HF 🤗: https://huggingface.co/Wesleythu/init_model
Init Model Benchmarks
ARC: 28.5 vs 96.7 (so35)-70.5%
HellaSwag: 25.4 vs 95.3 (gpt4)-73.3%
MMLU: 25.65 vs 88.3 (so35)-71%
TruthfulQA: 48.48 vs 59 (gpt4)-17.8%
WinoGrande: 49.57 vs 87.5 (gpt4)-43.3%
LLME Score: 0.23549
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)
Init Model Parameters and Internals
| Training Details |
|
| LLM Name | Init Model |
| Repository 🤗 | https://huggingface.co/Wesleythu/init_model |
| Model Size | 6.6b |
| Required VRAM | 26.6 GB |
| Updated | 2025-02-22 |
| Maintainer | Wesleythu |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaModel |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 32001 |
| Torch Data Type | float32 |
Rank the Init Model 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227