Downloads · 30 days
14
4% of all-time downloads
rocket-3B-GGUF-fp16
ddh0/rocket-3B-GGUF-fp16
rocket-3B-GGUF-fp16 is a text generation model from ddh0. Use it when you need the model to write or continue text. The card lists the license as cc-by-sa-4.0.
This is pansophic's rocket-3B, converted to GGUF. No other changes were made.
All-time downloads
384
Public
Repo size
8.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf8.7 GB · 100%
At a glance
- Task
- Text Generation
- License
- cc-by-sa-4.0
- Access
- Public
- Created
- Nov 22, 2023
- Updated
- Nov 23, 2023
- SHA
- cdefa574
Try a prompt
Model card
From the Hugging Face model README
This is pansophic's rocket-3B, converted to GGUF. No other changes were made.
Two files are avaliable here:
- rocket-3B-fp16.gguf: the original model converted to GGUF without quantization
- rocket-3B-q8_0-LOT.gguf: the original model converted to GGUF with q8_0 quantization using the
--leave-output-tensorcommand-line option
From llama.cpp/quantize --help:
--leave-output-tensor: Will leave output.weight un(re)quantized. Increases model size but may also increase quality, especially when requantizing
The model was converted using convert-hf-to-gguf.py from Georgi Gerganov's llama.cpp repo, commit #8e672ef.
All credit belongs to pansophic for training and releasing this model. Thank you!
- Task
- Text Generation
- License
- cc-by-sa-4.0
- Created
- Nov 22, 2023
- Updated
- Nov 23, 2023