Instructions to use sraivante/Custom-GPT-40M-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sraivante/Custom-GPT-40M-Base with Transformers:

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

pipe = pipeline("text-generation", model="sraivante/Custom-GPT-40M-Base")

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

tokenizer = AutoTokenizer.from_pretrained("sraivante/Custom-GPT-40M-Base")
model = AutoModelForCausalLM.from_pretrained("sraivante/Custom-GPT-40M-Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sraivante/Custom-GPT-40M-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sraivante/Custom-GPT-40M-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sraivante/Custom-GPT-40M-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sraivante/Custom-GPT-40M-Base

SGLang

How to use sraivante/Custom-GPT-40M-Base 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 "sraivante/Custom-GPT-40M-Base" \
    --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": "sraivante/Custom-GPT-40M-Base",
		"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 "sraivante/Custom-GPT-40M-Base" \
        --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": "sraivante/Custom-GPT-40M-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sraivante/Custom-GPT-40M-Base with Docker Model Runner:
```
docker model run hf.co/sraivante/Custom-GPT-40M-Base
```

Custom-GPT-40M-Base

File size: 348 Bytes

87842ae

{
  "batch_size": 32,
  "block_size": 256,
  "dropout": 0.1,
  "eval_interval": 250,
  "eval_iters": 50,
  "grad_accum": 2,
  "grad_clip": 1.0,
  "learning_rate": 0.0003,
  "max_iters": 5000,
  "min_lr": 3e-05,
  "n_embd": 512,
  "n_head": 8,
  "n_layer": 10,
  "vocab_size": 16000,
  "warmup_iters": 200,
  "weight_decay": 0.1
}