Downloads · 30 days
0
Mistral-7B-Instruct-v0.1-ft-sharded
umerm/Mistral-7B-Instruct-v0.1-ft-sharded
Mistral-7B-Instruct-v0.1-ft-sharded is a text generation model from umerm. Use it when you need the model to write or continue text. The card lists the license as other.
This model was trained using AutoTrain. For more information, please visit AutoTrain.
Access
Public
Updated Mar 10, 2024
Repo size
82.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt54.6 MB · 48%
At a glance
- Task
- Text Generation
- License
- other
- Access
- Public
- Created
- Mar 10, 2024
- Updated
- Mar 10, 2024
- SHA
- 46733c53
Try a prompt
Model card
From the Hugging Face model README
Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit AutoTrain.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
- Task
- Text Generation
- License
- other
- Created
- Mar 10, 2024
- Updated
- Mar 10, 2024