Autotrain compatible Dataset:openassistant/oasst1 En Gpt Gpt neox H2o-llmstudio Pytorch Region:us Sharded
Model Card on HF 🤗: https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-1024-20b
H2ogpt Gm Oasst1 En 1024 20B Benchmarks
ARC: 48.04 vs 96.7 (so35)-50.3%
HellaSwag: 72.76 vs 95.3 (gpt4)-23.7%
MMLU: 25.96 vs 88.3 (so35)-70.6%
TruthfulQA: 39.92 vs 59 (gpt4)-32.3%
WinoGrande: 66.3 vs 87.5 (gpt4)-24.2%
GSM8K: 2.5 vs 96.4 (so35)-97.4%
LLME Score: 0.14927
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)
H2ogpt Gm Oasst1 En 1024 20B Parameters and Internals
| LLM Name | H2ogpt Gm Oasst1 En 1024 20B |
| Repository 🤗 | https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-1024-20b |
| Model Size | 20b |
| Required VRAM | 41.2 GB |
| Updated | 2025-01-20 |
| Maintainer | h2oai |
| Model Type | gpt_neox |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GPTNeoXForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.28.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | float16 |
Best Alternatives to H2ogpt Gm Oasst1 En 1024 20B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| EleutherAI GPT Neox 20B 4bits | 2K / 12.5 GB | 9 | 0 |
| GPT NeoXT Chat Base 20B | 2K / 41.2 GB | 825 | 696 |
| ...t Gm Oasst1 Multilang 1024 20B | 2K / 41.2 GB | 747 | 10 |
| H2ogpt Oasst1 512 20B | 2K / 41.2 GB | 759 | 40 |
| GPT Neox 20B Full Precision | 2K / 82.5 GB | 747 | 0 |
| GPTNeoX 20B TestGen Dart V1.0 | 2K / 41.2 GB | 10 | 2 |
| Oasst GPT Neox 20B 1000 Steps | 2K / 41.2 GB | 735 | 0 |
| Oasst GPT Neox 20B 3000 Steps | 2K / 41.2 GB | 748 | 0 |
| GPT Neox 20B | 2K / 40.8 GB | 21775 | 551 |
| GPT NeoX 20B Erebus | 2K / 41.4 GB | 2792 | 84 |
Note: green Score (e.g. "73.2") means that the model is better than h2oai/h2ogpt-gm-oasst1-en-1024-20b .
Rank the H2ogpt Gm Oasst1 En 1024 20B 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? 41636 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227