πŸ™ GitHub β€’ πŸ‘Ύ Discord β€’ 🐀 Twitter β€’ πŸ’¬ WeChat
πŸ“ Paper β€’ πŸ’ͺ Tech Blog β€’ πŸ™Œ FAQ β€’ πŸ“— Learning Hub

Intro

Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.

Key features:

  • Excelling in long-context understanding with a maximum context length of 128K tokens.
  • Supporting 52 major programming languages:
  'java', 'markdown', 'python', 'php', 'javascript', 'c++', 'c#', 'c', 'typescript', 'html', 'go', 'java_server_pages', 'dart', 'objective-c', 'kotlin', 'tex', 'swift', 'ruby', 'sql', 'rust', 'css', 'yaml', 'matlab', 'lua', 'json', 'shell', 'visual_basic', 'scala', 'rmarkdown', 'pascal', 'fortran', 'haskell', 'assembly', 'perl', 'julia', 'cmake', 'groovy', 'ocaml', 'powershell', 'elixir', 'clojure', 'makefile', 'coffeescript', 'erlang', 'lisp', 'toml', 'batchfile', 'cobol', 'dockerfile', 'r', 'prolog', 'verilog'

For model details and benchmarks, see Yi-Coder blog and Yi-Coder README.

demo1

Models

Name Type Length Download
Yi-Coder-9B-Chat Chat 128K πŸ€— Hugging Face β€’ πŸ€– ModelScope β€’ 🟣 wisemodel
Yi-Coder-1.5B-Chat Chat 128K πŸ€— Hugging Face β€’ πŸ€– ModelScope β€’ 🟣 wisemodel
Yi-Coder-9B Base 128K πŸ€— Hugging Face β€’ πŸ€– ModelScope β€’ 🟣 wisemodel
Yi-Coder-1.5B Base 128K πŸ€— Hugging Face β€’ πŸ€– ModelScope β€’ 🟣 wisemodel

Benchmarks

As illustrated in the figure below, Yi-Coder-9B-Chat achieved an impressive 23% pass rate in LiveCodeBench, making it the only model with under 10B parameters to surpass 20%. It also outperforms DeepSeekCoder-33B-Ins at 22.3%, CodeGeex4-9B-all at 17.8%, CodeLLama-34B-Ins at 13.3%, and CodeQwen1.5-7B-Chat at 12%.

bench1

Quick Start

You can use transformers to run inference with Yi-Coder models (both chat and base versions) as follows:

from transformers import AutoTokenizer, AutoModelForCausalLM

device = "cuda" # the device to load the model onto
model_path = "01-ai/Yi-Coder-9B-Chat"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto").eval()

prompt = "Write a quick sort algorithm."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=1024,
    eos_token_id=tokenizer.eos_token_id  
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

For getting up and running with Yi-Coder series models quickly, see Yi-Coder README.

Downloads last month
5,906
Safetensors
Model size
8.83B params
Tensor type
BF16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for 01-ai/Yi-Coder-9B-Chat

Base model

01-ai/Yi-Coder-9B
Finetuned
(4)
this model
Finetunes
1 model
Merges
2 models
Quantizations
22 models

Spaces using 01-ai/Yi-Coder-9B-Chat 9

Collection including 01-ai/Yi-Coder-9B-Chat