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 / training_data /SHA256SUMS

sraivante

Publish Custom GPT 40M base model with training data

87842ae verified 17 days ago

Raw History Blame Contribute Delete

1.19 kB

	b8318ac40ad81eb21cc8f20261fc3242cba76119cac05cf5f717b7c6f16d497d .gitattributes
	9fe9c519e898fa33a38f294604ff1a8057d7f5f2b853191893d0d81e5568911a artifact_integrity.json
	54db7ec78aa51785651c913cdac0580ede00d574c2bf48727e95b9099824710e ATTRIBUTION.md
	178a7ba7499dc94c3dbe3c52f1ba5e5db3c737018b9b361211ea8b6f28a7f60f bpe_tokenizer.json
	9ba9550ad48438d0836ddab3da480b3b69ffa0aac7b7878b5a0039e7ab429411 LICENSE
	3ddf9be5c28fe27dad143a5dc76eea25222ad1dd68934a047064e56ed2fa40c5 LICENSE-APACHE-2.0
	88663b3c4f85e0f0abb019f0cf456c30f7069ca990f56d6731441bc240b02816 NOTICE
	59eb225e402099af329eb8fcbdea3316061b4d60af45dad0f98c68a31e0df103 provenance/data_audit.json
	93803f5c71a78da1a22ddf1753f0e4114cb837b3ac8e789b4ec2a88a12ddb637 provenance/upstream_README.md
	3c080ef54239f17351162353e9ee957f9fdd6d158570e27186480805231bdade raw/data-0.parquet
	5fadacb535e8eeb17326cf909e86e54aa49d8ad189da73e5801a08e358f5375e raw/data-1.parquet
	dbff7dd854e5ec60d86902c83d895bfe76c699dcf83580126f85dc3a8900cf38 README.md
	11268ecb2281adf1cdc6340df8f9517931afa2af166aa5099a114edb69e6210b tokens/train_ids.npy
	c9f6e7c13916ce8987a9caa80bfef4957e648ade97f30ffbb9ebacd943e736ee tokens/val_ids.npy