llmreference
DeepInfra

Using StarCoder2 15B on DeepInfra

Implementation guide · StarCoder 2 · ServiceNow Research

ServerlessOpen Source

Quick Start

  1. 1
    Create an account at DeepInfra and generate an API key.
  2. 2
    Use the DeepInfra SDK or REST API to call starcoder2-15b — see the documentation for request format.
  3. 3
    You'll be billed $0.20/1M input, $0.60/1M output tokens. See full pricing.

Code Examples

Install
pip install openai
API key
DEEPINFRA_API_KEY
Model ID
starcoder2-15b

DeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
    model="starcoder2-15b",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

About DeepInfra

DeepInfra offers serverless AI inference with a simple API, supporting hundreds of models across text generation, embeddings, and more. Pay-per-token pricing with no upfront commitments.

DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models. It provides serverless inference for leading models from Meta, Mistral, Alibaba, and others with competitive token-based pricing.

Pricing on DeepInfra

TypePrice (per 1M)
Input tokens$0.20
Output tokens$0.60

Capabilities

Structured Outputs

About StarCoder2 15B

StarCoder2-15B is a sophisticated large language model, expertly crafted for code generation and understanding. Developed by the BigCode project, it features 15 billion parameters and is trained on The Stack v2, a vast dataset of over 4 trillion tokens from more than 600 programming languages. Its advanced transformer decoder architecture, equipped with a grouped-query and sliding window attention mechanism and a Fill-in-the-Middle training objective, allows a context window of 16,384 tokens. In addition to generating and completing code, the model excels in tasks like code summarization and retrieving relevant snippets through natural language queries. The training leveraged NVIDIA's NeMo framework and the Eos Supercomputer, while usage is governed by the BigCode Open RAIL-M license, supporting royalty-free and commercial use.

Model Specs

Released2024-07-04
Parameters15B
Context8K
ArchitectureDecoder Only

Provider

DeepInfra
DeepInfra

San Francisco, California, United States