Downloads · 30 days
12
3% of all-time downloads
gemma-7b-8bit
merve/gemma-7b-8bit
gemma-7b-8bit is a text generation model from merve. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This is the repository for Gemma-7B quantized to 8-bit using bitsandbytes. Original model card and license for Gemma-7B can be found here. This is the base model and it's not instruction fine-tuned.
All-time downloads
380
Public
Repo size
23.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin9.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- gemma
- Access
- Public
- Created
- Feb 22, 2024
- Updated
- Feb 22, 2024
- SHA
- 549dad93
Try a prompt
Model card
From the Hugging Face model README
Gemma-7B in 8-bit with bitsandbytes
This is the repository for Gemma-7B quantized to 8-bit using bitsandbytes. Original model card and license for Gemma-7B can be found here. This is the base model and it's not instruction fine-tuned.
Usage
Please visit original Gemma-7B model card for intended uses and limitations.
You can use this model like following:
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained(
"merve/gemma-7b-8bit",
device_map='auto'
)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
- Task
- Text Generation
- Library
- transformers
- Type
- gemma
- License
- other
- Created
- Feb 22, 2024
- Updated
- Feb 22, 2024