Pythia Chat Base 7B is an open-source language model by togethercomputer. Features: 7b LLM, VRAM: 13.8GB, Context: 2K, License: apache-2.0, HF Score: 39.8, LLM Explorer Score: 0.12, Arc: 40, HellaSwag: 68.7, MMLU: 27.4, TruthfulQA: 34.6, WinoGrande: 64, GSM8K: 4.1.
| LLM Name | Pythia Chat Base 7B |
| Repository ๐ค | https://huggingface.co/togethercomputer/Pythia-Chat-Base-7B |
| Model Size | 7b |
| Required VRAM | 13.8 GB |
| Updated | 2026-03-25 |
| Maintainer | togethercomputer |
| 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 | 4.21.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Literature 7B 16384 | 16K / 36 GB | 9 | 15 |
| RedPajama 7B 16384 | 16K / 36 GB | 6 | 4 |
| Stablelm Tuned Alpha 7B | 4K / 31.9 GB | 1811 | 360 |
| Stablelm Base Alpha 7B | 4K / 31.9 GB | 2547 | 208 |
| Stablelm 7B Sft V7 Epoch 3 | 4K / 32.4 GB | 670 | 67 |
| StableLManticore 7B | 4K / 16 GB | 6 | 1 |
| Pythia 6.9B Deduped 4K | 4K / 27.2 GB | 8 | 10 |
| Stablelm 7B | 4K / 31.9 GB | 1 | 2 |
| RedPajama INCITE 7B Instruct | 2K / 13.8 GB | 1858 | 108 |
| Open Calm 7B | 2K / 13.9 GB | 935 | 205 |
๐ 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! ๐