Instructions to use nuprl/MultiPL-T-StarCoderBase_1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nuprl/MultiPL-T-StarCoderBase_1b with Transformers:

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

pipe = pipeline("text-generation", model="nuprl/MultiPL-T-StarCoderBase_1b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nuprl/MultiPL-T-StarCoderBase_1b")
model = AutoModelForCausalLM.from_pretrained("nuprl/MultiPL-T-StarCoderBase_1b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nuprl/MultiPL-T-StarCoderBase_1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nuprl/MultiPL-T-StarCoderBase_1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nuprl/MultiPL-T-StarCoderBase_1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nuprl/MultiPL-T-StarCoderBase_1b

SGLang

How to use nuprl/MultiPL-T-StarCoderBase_1b 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 "nuprl/MultiPL-T-StarCoderBase_1b" \
    --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": "nuprl/MultiPL-T-StarCoderBase_1b",
		"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 "nuprl/MultiPL-T-StarCoderBase_1b" \
        --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": "nuprl/MultiPL-T-StarCoderBase_1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nuprl/MultiPL-T-StarCoderBase_1b with Docker Model Runner:
```
docker model run hf.co/nuprl/MultiPL-T-StarCoderBase_1b
```

MultiPL-T-StarCoderBase_1b / config.json

arjunguha

rkt-more_stack-epoch_6

5b8e3da verified almost 2 years ago

raw

history blame

1.02 kB

	{
	"_name_or_path": "more_stack/rkt/checkpoint_final",
	"activation_function": "gelu_pytorch_tanh",
	"architectures": [
	"GPTBigCodeForCausalLM"
	],
	"attention_softmax_in_fp32": true,
	"attn_pdrop": 0.1,
	"bos_token_id": 0,
	"embd_pdrop": 0.1,
	"eos_token_id": 0,
	"inference_runner": 0,
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"max_batch_size": null,
	"max_sequence_length": null,
	"model_type": "gpt_bigcode",
	"multi_query": true,
	"n_embd": 2048,
	"n_head": 16,
	"n_inner": 8192,
	"n_layer": 24,
	"n_positions": 8192,
	"pad_key_length": true,
	"pre_allocate_kv_cache": false,
	"resid_pdrop": 0.1,
	"scale_attention_softmax_in_fp32": true,
	"scale_attn_weights": true,
	"summary_activation": null,
	"summary_first_dropout": 0.1,
	"summary_proj_to_labels": true,
	"summary_type": "cls_index",
	"summary_use_proj": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.40.0",
	"use_cache": false,
	"validate_runner_input": true,
	"vocab_size": 49152
	}