Autotrain compatible Dataset:knutjaegersberg/wizard... Endpoints compatible Gpt2 Instruct Pytorch Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/KnutJaegersberg/megatron-gpt2-345m-evol_instruct_v2
Megatron Gpt2 345M Evol Instruct V2 Benchmarks
ARC: 26.37 vs 96.7 (so35)-72.7%
HellaSwag: 38.39 vs 95.3 (gpt4)-59.7%
MMLU: 23.6 vs 88.3 (so35)-73.3%
TruthfulQA: 41.19 vs 59 (gpt4)-30.2%
WinoGrande: 52.33 vs 87.5 (gpt4)-40.2%
LLME Score: 0.17048
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)
Megatron Gpt2 345M Evol Instruct V2 Parameters and Internals
| LLM Name | Megatron Gpt2 345M Evol Instruct V2 |
| Repository 🤗 | https://huggingface.co/KnutJaegersberg/megatron-gpt2-345m-evol_instruct_v2 |
| Model Size | 345m |
| Required VRAM | 1.4 GB |
| Updated | 2025-09-07 |
| Maintainer | KnutJaegersberg |
| Model Type | gpt2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | GPT2LMHeadModel |
| License | cc-by-nc-4.0 |
| Model Max Length | 1024 |
| Transformers Version | 4.32.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 50257 |
| Torch Data Type | float32 |
| Activation Function | gelu_new |
Rank the Megatron Gpt2 345M Evol Instruct V2 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? 51187 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124