Model reference · open weights
EleutherAI_pythia-deduped__sft__tldr is an open-weight language model from Hugging Face. EleutherAI_pythia-6.9b-deduped__sft__tldr (FP32) weighs 13.7 GB; the smallest configuration that runs it is 2× RTX 3060 12 GB.
What it is
| Released by | Hugging Face |
|---|---|
| Released | 2024-07-25 |
| Parameters | 6.9B |
| VRAM | 13.7 GB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory |
|---|---|---|---|
| 2K each | |||
| RTX 3060 12 GB | — | — | 11.6 GB |
| RTX 4060 Ti 16 GB | — | 1K | 15.4 GB |
| RTX 3090 24 GB | 8 | all 2K | 23.4 GB |
| RTX 4090 24 GB | 8 | all 2K | 23.4 GB |
| RTX 5090 32 GB | 15 | all 2K | 31.0 GB |
| L40S 48 GB | 27 | all 2K | 44.0 GB |
| A100 80 GB | 59 | all 2K | 78.2 GB |
| H100 80 GB | 56 | all 2K | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | 70 | all 2K | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | 83 | all 2K | 107 GB |
| H200 141 GB | 112 | all 2K | 138 GB |
| B200 180 GB | 146 | all 2K | 176 GB |
| 2× RTX 3060 12 GB tensor parallel | 7 | all 2K | 11.6 GB a card |
| 2× RTX 4060 Ti 16 GB tensor parallel | 14 | all 2K | 15.4 GB a card |
| Requests at once | 2K tokens each |
|---|---|
| 1 | 15.5 GB |
| 5 | 19.8 GB |
| 8 | 23.0 GB |
| 16 | 31.6 GB |
| 32 | 48.8 GB |
| 64 | 83.1 GB |
One card, with vLLM's small-card settings.
From the model card
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
Use the code below to get started with the model.
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.