Instructions to use TeraSpace/dialofred with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeraSpace/dialofred with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TeraSpace/dialofred")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("TeraSpace/dialofred") model = AutoModelForSeq2SeqLM.from_pretrained("TeraSpace/dialofred") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TeraSpace/dialofred with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TeraSpace/dialofred" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TeraSpace/dialofred", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TeraSpace/dialofred
- SGLang
How to use TeraSpace/dialofred with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "TeraSpace/dialofred" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TeraSpace/dialofred", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "TeraSpace/dialofred" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TeraSpace/dialofred", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TeraSpace/dialofred with Docker Model Runner:
docker model run hf.co/TeraSpace/dialofred
Update README.md
#1
by Den4ikAI - opened
README.md
CHANGED
|
@@ -11,15 +11,15 @@ tags:
|
|
| 11 |
- conversational
|
| 12 |
---
|
| 13 |
|
| 14 |
-
|
| 15 |
|
| 16 |
```python
|
| 17 |
import torch
|
| 18 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 19 |
|
| 20 |
device='cuda'
|
| 21 |
-
tokenizer = AutoTokenizer.from_pretrained('TeraSpace/
|
| 22 |
-
model = AutoModelForSeq2SeqLM.from_pretrained('TeraSpace/
|
| 23 |
while True:
|
| 24 |
text_inp = input("=>")
|
| 25 |
lm_text=f'<SC1>- {text_inp}\n- <extra_id_0>'
|
|
|
|
| 11 |
- conversational
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# Usage
|
| 15 |
|
| 16 |
```python
|
| 17 |
import torch
|
| 18 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 19 |
|
| 20 |
device='cuda'
|
| 21 |
+
tokenizer = AutoTokenizer.from_pretrained('TeraSpace/dialofred')
|
| 22 |
+
model = AutoModelForSeq2SeqLM.from_pretrained('TeraSpace/dialofred').to(device)
|
| 23 |
while True:
|
| 24 |
text_inp = input("=>")
|
| 25 |
lm_text=f'<SC1>- {text_inp}\n- <extra_id_0>'
|