Instructions to use Shreyasff6666/Magical2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shreyasff6666/Magical2 with Transformers:

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

pipe = pipeline("text-generation", model="Shreyasff6666/Magical2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Shreyasff6666/Magical2")
model = AutoModelForCausalLM.from_pretrained("Shreyasff6666/Magical2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Shreyasff6666/Magical2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Shreyasff6666/Magical2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shreyasff6666/Magical2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Shreyasff6666/Magical2

SGLang

How to use Shreyasff6666/Magical2 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 "Shreyasff6666/Magical2" \
    --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": "Shreyasff6666/Magical2",
		"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 "Shreyasff6666/Magical2" \
        --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": "Shreyasff6666/Magical2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Shreyasff6666/Magical2 with Docker Model Runner:
```
docker model run hf.co/Shreyasff6666/Magical2
```

Magical2

This model is a fine-tuned version of crumb/gpt-joke on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.5533

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 30
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	33	1.6553
No log	2.0	66	1.5406
No log	3.0	99	1.4875
No log	4.0	132	1.4571
No log	5.0	165	1.4472
No log	6.0	198	1.4450
No log	7.0	231	1.4522
No log	8.0	264	1.4694
No log	9.0	297	1.4754
No log	10.0	330	1.4947
No log	11.0	363	1.5067
No log	12.0	396	1.5227
No log	13.0	429	1.5341
No log	14.0	462	1.5436
No log	15.0	495	1.5533

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.14.3
Tokenizers 0.13.3

Downloads last month: 11

Model tree for Shreyasff6666/Magical2

Base model

crumb/gpt-joke

Finetuned

(2)

this model