Instructions to use dagger-realms/narrative_to_dagger with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dagger-realms/narrative_to_dagger with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="dagger-realms/narrative_to_dagger")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dagger-realms/narrative_to_dagger")
model = AutoModelForCausalLM.from_pretrained("dagger-realms/narrative_to_dagger")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dagger-realms/narrative_to_dagger with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dagger-realms/narrative_to_dagger"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dagger-realms/narrative_to_dagger",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dagger-realms/narrative_to_dagger

SGLang

How to use dagger-realms/narrative_to_dagger 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 "dagger-realms/narrative_to_dagger" \
    --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": "dagger-realms/narrative_to_dagger",
		"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 "dagger-realms/narrative_to_dagger" \
        --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": "dagger-realms/narrative_to_dagger",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dagger-realms/narrative_to_dagger with Docker Model Runner:
```
docker model run hf.co/dagger-realms/narrative_to_dagger
```

narrative_to_dagger / datadreamer.json

AjayP13

Pushed by DataDreamer

bdcf8a0 verified about 2 years ago

raw

history blame contribute delete

2.24 kB

	{
	"model_card": {
	"Date & Time": "2024-04-07T01:56:02.043003",
	"Model Card": [
	"https://huggingface.co/LouisML/tinyllama_32k"
	],
	"License Information": [
	"apache-2.0"
	],
	"Citation Information": [
	"\n@inproceedings{Wolf_Transformers_State-of-the-Art_Natural_2020,\n author = {Wolf, Thomas and Debut, Lysandre and Sanh, Victor and Chaumond, Julien",
	"\n@Misc{peft,\n title = {PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods},\n author = {Sourab Mangrulkar and Sylvain Gugger and Lysandre Debut and Younes"
	]
	},
	"data_card": {
	"Create Dataset of Locations": {
	"Date & Time": "2024-04-06T10:17:45.009636"
	},
	"zipped(Create Dataset of Locations, Generate Fiction for Each Location (select_columns))": {
	"Date & Time": "2024-04-06T15:17:35.786655"
	},
	"zipped(zipped(Create Dataset of Locations, Generate Fiction for Each Location (select_columns)), Clean Location Subset JSON)": {
	"Date & Time": "2024-04-06T15:17:39.288866"
	},
	"zipped(zipped(Create Dataset of Locations, Generate Fiction for Each Location (select_columns)), Clean Location Subset JSON) (train split)": {
	"Date & Time": "2024-04-06T15:17:39.562538"
	}
	},
	"__version__": "0.28.0",
	"datetime": "2024-04-06T23:37:47.115672",
	"type": "TrainHFFineTune",
	"name": "Train a Fictional Story => DAGGER JSON Model",
	"version": 1.0,
	"fingerprint": "91f4a2305e0abfa9",
	"req_versions": {
	"dill": "0.3.8",
	"sqlitedict": "2.1.0",
	"torch": "2.2.2",
	"numpy": "1.26.4",
	"transformers": "4.39.3",
	"datasets": "2.18.0",
	"huggingface_hub": "0.22.2",
	"accelerate": "0.28.0",
	"peft": "0.10.0",
	"tiktoken": "0.6.0",
	"tokenizers": "0.15.2",
	"openai": "1.16.2",
	"ctransformers": "0.2.27",
	"optimum": "1.18.0",
	"bitsandbytes": "0.43.0",
	"litellm": "1.31.14",
	"trl": "0.8.1",
	"setfit": "1.0.3"
	},
	"interpreter": "3.10.9 (main, Apr 17 2023, 21:32:03) [GCC 7.5.0]"
	}