Instructions to use human/lm-colab-tutorial with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use human/lm-colab-tutorial with Transformers:

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

pipe = pipeline("text-generation", model="human/lm-colab-tutorial")

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

tokenizer = AutoTokenizer.from_pretrained("human/lm-colab-tutorial")
model = AutoModelForCausalLM.from_pretrained("human/lm-colab-tutorial", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use human/lm-colab-tutorial with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/human/lm-colab-tutorial

SGLang

How to use human/lm-colab-tutorial 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 "human/lm-colab-tutorial" \
    --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": "human/lm-colab-tutorial",
		"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 "human/lm-colab-tutorial" \
        --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": "human/lm-colab-tutorial",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use human/lm-colab-tutorial with Docker Model Runner:
```
docker model run hf.co/human/lm-colab-tutorial
```

lm-colab-tutorial

File size: 1,342 Bytes

99fdd86

---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: lm-colab-tutorial
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# lm-colab-tutorial

This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.6391

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.742         | 1.0   | 2334 | 3.6593          |
| 3.6297        | 2.0   | 4668 | 3.6440          |
| 3.5795        | 3.0   | 7002 | 3.6391          |


### Framework versions

- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1