Model Card on HF 🤗: https://huggingface.co/jojo0217/step3_mk7
Step3 Mk7 Benchmarks
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)
Step3 Mk7 Parameters and Internals
| LLM Name | Step3 Mk7 |
| Repository 🤗 | https://huggingface.co/jojo0217/step3_mk7 |
| Required VRAM | 25.8 GB |
| Updated | 2025-02-22 |
| Maintainer | jojo0217 |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.31.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 30008 |
| Torch Data Type | float16 |
Best Alternatives to Step3 Mk7
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Catlm | 8K / 7.8 GB | 45 | 4 |
| ...Prover 14final Checkpoint 5830 | 4K / 14.9 GB | 5 | 0 |
| Neox Musenet Untrained | 4K / 7.3 GB | 6 | 0 |
| Stabillm Instruct De | 4K / 31.8 GB | 5 | 0 |
| Open Calm Large | 2K / 1.8 GB | 3495 | 10 |
| MonoCoder OMP | 2K / 3.6 GB | 202 | 0 |
| KULLM RLHF | 2K / 25.8 GB | 2026 | 3 |
| ProofGPT V0.1 | 2K / 2.9 GB | 1974 | 3 |
| GPT NeoX Pretrain News | 2K / 0.3 GB | 306 | 0 |
| GPT NeoX Pretrain 1GB | 2K / 0.3 GB | 162 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than jojo0217/step3_mk7 .
Rank the Step3 Mk7 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