deepseek coder v2 instruct awq
by casperhansen
Open source · 161k downloads · 11 likes
1.3
(11 reviews)CodeAPI & LocalAbout
DeepSeek Coder V2 Instruct AWQ is an artificial intelligence model specialized in code generation and comprehension, designed to rival closed models like GPT-4 Turbo in programming tasks. With its advanced architecture and extensive training on billions of tokens, it excels particularly in solving complex problems, analyzing code, and assisting with software development. The model stands out for its ability to handle both pure coding tasks and applied mathematical reasoning while maintaining strong performance in general language domains. It caters to developers, researchers, and businesses seeking a high-performing open-source solution to automate or optimize their programming workflows. Its quantization-based approach also makes it more resource-efficient without compromising accuracy.
Documentation
Quantized details
This model was quantized on 4x A100 80GB with 1TB system ram. It was quantized using the chosen preferences from the coding dataset of OpenHermes 2.5: https://huggingface.co/datasets/alvarobartt/openhermes-preferences-coding
Quantized evaluations:
- int4 perplexity: 5.325
Original Model Card
API Platform | How to Use | License |
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
1. Introduction
We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder-33B, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K.
In standard benchmark evaluations, DeepSeek-Coder-V2 achieves superior performance compared to closed-source models such as GPT4-Turbo, Claude 3 Opus, and Gemini 1.5 Pro in coding and math benchmarks. The list of supported programming languages can be found here.
2. Model Downloads
We release the DeepSeek-Coder-V2 with 16B and 236B parameters based on the DeepSeekMoE framework, which has actived parameters of only 2.4B and 21B , including base and instruct models, to the public.
| Model | #Total Params | #Active Params | Context Length | Download |
|---|---|---|---|---|
| DeepSeek-Coder-V2-Lite-Base | 16B | 2.4B | 128k | 🤗 HuggingFace |
| DeepSeek-Coder-V2-Lite-Instruct | 16B | 2.4B | 128k | 🤗 HuggingFace |
| DeepSeek-Coder-V2-Base | 236B | 21B | 128k | 🤗 HuggingFace |
| DeepSeek-Coder-V2-Instruct | 236B | 21B | 128k | 🤗 HuggingFace |
3. Chat Website
You can chat with the DeepSeek-Coder-V2 on DeepSeek's official website: coder.deepseek.com
4. API Platform
We also provide OpenAI-Compatible API at DeepSeek Platform: platform.deepseek.com, and you can also pay-as-you-go at an unbeatable price.
5. How to run locally
Here, we provide some examples of how to use DeepSeek-Coder-V2-Lite model. If you want to utilize DeepSeek-Coder-V2 in BF16 format for inference, 80GB*8 GPUs are required.
Inference with Huggingface's Transformers
You can directly employ Huggingface's Transformers for model inference.
Code Completion
Python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
input_text = "#write a quick sort algorithm"
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Code Insertion
Python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Base", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
input_text = """<｜fim▁begin｜>def quick_sort(arr):
if len(arr) <= 1:
return arr
pivot = arr[0]
left = []
right = []
<｜fim▁hole｜>
if arr[i] < pivot:
left.append(arr[i])
else:
right.append(arr[i])
return quick_sort(left) + [pivot] + quick_sort(right)<｜fim▁end｜>"""
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True)[len(input_text):])
Chat Completion
Python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
messages=[
{ 'role': 'user', 'content': "write a quick sort algorithm in python."}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
# tokenizer.eos_token_id is the id of <｜end▁of▁sentence｜> token
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
The complete chat template can be found within tokenizer_config.json located in the huggingface model repository.
An example of chat template is as belows:
Bash
<｜begin▁of▁sentence｜>User: {user_message_1}
Assistant: {assistant_message_1}<｜end▁of▁sentence｜>User: {user_message_2}
Assistant:
You can also add an optional system message:
Bash
<｜begin▁of▁sentence｜>{system_message}
User: {user_message_1}
Assistant: {assistant_message_1}<｜end▁of▁sentence｜>User: {user_message_2}
Assistant:
Inference with vLLM (recommended)
To utilize vLLM for model inference, please merge this Pull Request into your vLLM codebase: https://github.com/vllm-project/vllm/pull/4650.
Python
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
max_model_len, tp_size = 8192, 1
model_name = "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True, enforce_eager=True)
sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
messages_list = [
[{"role": "user", "content": "Who are you?"}],
[{"role": "user", "content": "write a quick sort algorithm in python."}],
[{"role": "user", "content": "Write a piece of quicksort code in C++."}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)
6. License
This code repository is licensed under the MIT License. The use of DeepSeek-Coder-V2 Base/Instruct models is subject to the Model License. DeepSeek-Coder-V2 series (including Base and Instruct) supports commercial use.
7. Contact
If you have any questions, please raise an issue or contact us at [email protected].
Capabilities & Tags
transformerssafetensorsdeepseek_v2text-generationconversationalcustom_codetext-generation-inferenceendpoints_compatible4-bitawq
Links & Resources