Text Generation
Transformers
ONNX
Safetensors
mistral
trl
sft
optimum
danbooru
text-generation-inference
Instructions to use p1atdev/dart-v2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use p1atdev/dart-v2-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="p1atdev/dart-v2-base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("p1atdev/dart-v2-base") model = AutoModelForCausalLM.from_pretrained("p1atdev/dart-v2-base") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use p1atdev/dart-v2-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "p1atdev/dart-v2-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "p1atdev/dart-v2-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/p1atdev/dart-v2-base
- SGLang
How to use p1atdev/dart-v2-base 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 "p1atdev/dart-v2-base" \ --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": "p1atdev/dart-v2-base", "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 "p1atdev/dart-v2-base" \ --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": "p1atdev/dart-v2-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use p1atdev/dart-v2-base with Docker Model Runner:
docker model run hf.co/p1atdev/dart-v2-base
Update README.md
Browse files
README.md
CHANGED
|
@@ -73,13 +73,13 @@ from dartrs.dartrs import DartTokenizer
|
|
| 73 |
from dartrs.utils import get_generation_config
|
| 74 |
from dartrs.v2 import (
|
| 75 |
compose_prompt,
|
| 76 |
-
|
| 77 |
V2Model,
|
| 78 |
)
|
| 79 |
import time
|
| 80 |
import os
|
| 81 |
MODEL_NAME = "p1atdev/dart-v2-base"
|
| 82 |
-
model =
|
| 83 |
tokenizer = DartTokenizer.from_pretrained(MODEL_NAME)
|
| 84 |
config = get_generation_config(
|
| 85 |
prompt=compose_prompt(
|
|
|
|
| 73 |
from dartrs.utils import get_generation_config
|
| 74 |
from dartrs.v2 import (
|
| 75 |
compose_prompt,
|
| 76 |
+
MistralModel,
|
| 77 |
V2Model,
|
| 78 |
)
|
| 79 |
import time
|
| 80 |
import os
|
| 81 |
MODEL_NAME = "p1atdev/dart-v2-base"
|
| 82 |
+
model = MistralModel.from_pretrained(MODEL_NAME)
|
| 83 |
tokenizer = DartTokenizer.from_pretrained(MODEL_NAME)
|
| 84 |
config = get_generation_config(
|
| 85 |
prompt=compose_prompt(
|