Oasst Pythia 6.9B 4000 Steps is an open-source language model by dvruette. Features: 6.9b LLM, VRAM: 13.8GB, Context: 2K, HF Score: 39.2, LLM Explorer Score: 0.11, Arc: 41.6, HellaSwag: 64.2, MMLU: 26.3, TruthfulQA: 40.4, WinoGrande: 61.8, GSM8K: 0.5.
Model Card on HF 🤗: https://huggingface.co/dvruette/oasst-pythia-6.9b-4000-steps
Oasst Pythia 6.9B 4000 Steps Benchmarks
ARC: 41.64 vs 96.7 (so35)-56.9%
HellaSwag: 64.24 vs 95.3 (gpt4)-32.6%
MMLU: 26.26 vs 88.3 (so35)-70.3%
TruthfulQA: 40.43 vs 59 (gpt4)-31.5%
WinoGrande: 61.8 vs 87.5 (gpt4)-29.4%
GSM8K: 0.53 vs 96.4 (so35)-99.5%
LLME Score: 0.11028
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)
Oasst Pythia 6.9B 4000 Steps Parameters and Internals
| LLM Name | Oasst Pythia 6.9B 4000 Steps |
| Repository 🤗 | https://huggingface.co/dvruette/oasst-pythia-6.9b-4000-steps |
| Model Size | 6.9b |
| Required VRAM | 13.8 GB |
| Updated | 2026-03-29 |
| 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 Pythia 6.9B 4000 Steps
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pythia 6.9B Deduped 8K | 8K / 13.8 GB | 6 | 1 |
| ...I Pythia 6.9B Deduped Sft Tldr | 2K / 27.4 GB | 474 | 0 |
| Pythia 6.9B | 2K / 13.8 GB | 69609 | 59 |
| Ppo Tldr 6.9B | 2K / 13.8 GB | 8 | 0 |
| Pythia 6.9B Deduped | 2K / 13.8 GB | 6873 | 8 |
| ...I Pythia 6.9B Deduped Sft Tldr | 2K / 13.8 GB | 40 | 0 |
| Pythia 6.9B HC3 | 2K / 27.7 GB | 8 | 2 |
| Open Instruct Pythia 6.9B Tulu | 2K / 27.6 GB | 723 | 6 |
| ...an Large Pythia 6.9B Dev Phase | 2K / 27.6 GB | 3 | 3 |
| ....9B Deduped Synthetic Instruct | 2K / 27.5 GB | 2670 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than dvruette/oasst-pythia-6.9b-4000-steps .
Rank the Oasst Pythia 6.9B 4000 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? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a