Downloads · 30 days
17
21% of all-time downloads
goliath-120b-Instruct-FP8-Dynamic
Infermatic/goliath-120b-Instruct-FP8-Dynamic
goliath-120b-Instruct-FP8-Dynamic is a text generation model from Infermatic. Use it when you need the model to write or continue text. The card lists the license as llama2.
All-time downloads
80
Public
Parameters
118B
118 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors118 GB · 100%
Parameter types
How the weights are stored.
F8_E4M3117B · 100%
Try a prompt
Model card
From the Hugging Face model README
This quant was made for infermatic.ai
Dynamic FP8 quant of goliath-120b-Instruct-FP8-Dynamic made with AutoFP8.
Goliath 120B
An auto-regressive causal LM created by combining 2x finetuned Llama-2 70B into one.
Prompting Format
Both Vicuna and Alpaca will work, but due the initial and final layers belonging primarily to Xwin, I expect Vicuna to work the best.
- Task
- Text Generation
- Type
- llama
- License
- llama2
- Languages
- en
- Created
- Aug 13, 2024
- Updated
- Aug 13, 2024