Instructions to use pitangent-ds/opt-350M-tutor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pitangent-ds/opt-350M-tutor with Transformers:

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

pipe = pipeline("text-generation", model="pitangent-ds/opt-350M-tutor")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pitangent-ds/opt-350M-tutor")
model = AutoModelForCausalLM.from_pretrained("pitangent-ds/opt-350M-tutor", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pitangent-ds/opt-350M-tutor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pitangent-ds/opt-350M-tutor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pitangent-ds/opt-350M-tutor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pitangent-ds/opt-350M-tutor

SGLang

How to use pitangent-ds/opt-350M-tutor 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 "pitangent-ds/opt-350M-tutor" \
    --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": "pitangent-ds/opt-350M-tutor",
		"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 "pitangent-ds/opt-350M-tutor" \
        --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": "pitangent-ds/opt-350M-tutor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pitangent-ds/opt-350M-tutor with Docker Model Runner:
```
docker model run hf.co/pitangent-ds/opt-350M-tutor
```

arnabdhar commited on Jul 7, 2024

Commit

00e02ec

verified ·

1 Parent(s): 0b7f673

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -2

README.md CHANGED Viewed

@@ -1,14 +1,21 @@
 ---
-license: other
 base_model: facebook/opt-350m
 tags:
 - OPTForCausalLM
 - trl
 - sft
 - generated_from_trainer
 model-index:
 - name: opt-350M-tutor
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -55,4 +62,4 @@ The following hyperparameters were used during training:
 - Transformers 4.42.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.20.0
-- Tokenizers 0.19.1

 ---
+license: mit
 base_model: facebook/opt-350m
 tags:
 - OPTForCausalLM
 - trl
 - sft
 - generated_from_trainer
+- pytorch
 model-index:
 - name: opt-350M-tutor
   results: []
+datasets:
+- Rohan1998/Tutor
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 - Transformers 4.42.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.20.0
+- Tokenizers 0.19.1