Instructions to use ColleenMacklin/gpt-neo-125m-finetuned-couples2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ColleenMacklin/gpt-neo-125m-finetuned-couples2 with Transformers:

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

pipe = pipeline("text-generation", model="ColleenMacklin/gpt-neo-125m-finetuned-couples2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ColleenMacklin/gpt-neo-125m-finetuned-couples2")
model = AutoModelForCausalLM.from_pretrained("ColleenMacklin/gpt-neo-125m-finetuned-couples2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ColleenMacklin/gpt-neo-125m-finetuned-couples2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ColleenMacklin/gpt-neo-125m-finetuned-couples2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ColleenMacklin/gpt-neo-125m-finetuned-couples2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ColleenMacklin/gpt-neo-125m-finetuned-couples2

SGLang

How to use ColleenMacklin/gpt-neo-125m-finetuned-couples2 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 "ColleenMacklin/gpt-neo-125m-finetuned-couples2" \
    --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": "ColleenMacklin/gpt-neo-125m-finetuned-couples2",
		"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 "ColleenMacklin/gpt-neo-125m-finetuned-couples2" \
        --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": "ColleenMacklin/gpt-neo-125m-finetuned-couples2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ColleenMacklin/gpt-neo-125m-finetuned-couples2 with Docker Model Runner:
```
docker model run hf.co/ColleenMacklin/gpt-neo-125m-finetuned-couples2
```

gpt-neo-125m-finetuned-couples2

This model is a fine-tuned version of EleutherAI/gpt-neo-125m on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.6169

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-07
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: 6.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	91	2.6242
No log	2.0	182	2.6215
No log	3.0	273	2.6194
No log	4.0	364	2.6180
No log	5.0	455	2.6171
2.6194	6.0	546	2.6169

Framework versions

Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 6

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for ColleenMacklin/gpt-neo-125m-finetuned-couples2

Base model

EleutherAI/gpt-neo-125m

Finetuned

(183)

this model