Oasst GPT Neox 20B 3000 Steps Benchmarks
ARC: 46.42-51.8%
HellaSwag: 72.08-24.4%
MMLU: 26.16-69.8%
TruthfulQA: 35.53-39.8%
WinoGrande: 68.75-21.4%
GSM8K: 2.88-96.9%
nn.n% — How the model compares to the GPT-4.
Oasst GPT Neox 20B 3000 Steps Parameters and Internals
| LLM Name | Oasst GPT Neox 20B 3000 Steps |
| Repository | Open on 🤗 |
| Model Size | 20b |
| Required VRAM | 41.2 GB |
| Updated | 2024-07-26 |
| Maintainer | dvruette |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.26.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50288 |
| Torch Data Type | float16 |
Best Alternatives to Oasst GPT Neox 20B 3000 Steps
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| EleutherAI GPT Neox 20B 4bits | 0.2 | 2K / 12.5 GB | 12 | 0 |
| GPT NeoXT Chat Base 20B | 0.2 | 2K / 41.2 GB | 1228 | 693 |
| H2ogpt Gm Oasst1 En 1024 20B | 0.2 | 2K / 41.2 GB | 3247 | 4 |
| ...t Gm Oasst1 Multilang 1024 20B | 0.2 | 2K / 41.2 GB | 982 | 10 |
| H2ogpt Oasst1 512 20B | 0.2 | 2K / 41.2 GB | 972 | 38 |
| GPTNeoX 20B TestGen Dart V1.0 | 0.2 | 2K / 41.2 GB | 7 | 2 |
| GPT Neox 20B Full Precision | 0.2 | 2K / 82.5 GB | 963 | 0 |
| Oasst GPT Neox 20B 1000 Steps | 0.2 | 2K / 41.2 GB | 956 | 0 |
| GPT Neox 20B | 0.1 | 2K / 40.8 GB | 27306 | 504 |
| GPT NeoX 20B Erebus | 0.1 | 2K / 41.4 GB | 4195 | 82 |
Note: green Score (e.g. "73.2") means that the model is better than dvruette/oasst-gpt-neox-20b-3000-steps .
Rank the Oasst GPT Neox 20B 3000 Steps 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501