stable-code-instruct-3b
is a 2.7B billion parameter decoder-only language model tuned from
stable-code-3b
. This model was trained on a mix of publicly available datasets, synthetic datasets using
Direct Preference Optimization (DPO)
.
This instruct tune demonstrates state-of-the-art performance (compared to models of similar size) on the MultiPL-E metrics across multiple programming languages tested using
BigCode's Evaluation Harness
, and on the code portions of
MT Bench
.
The model is finetuned to make it useable in tasks like,
General purpose Code/Software Engineering like conversations.
SQL related generation and conversation.
Usage
Here's how you can run the model use the model:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stable-code-instruct-3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("stabilityai/stable-code-instruct-3b", torch_dtype=torch.bfloat16, trust_remote_code=True)
model.eval()
model = model.cuda()
messages = [
{
"role": "system",
"content": "You are a helpful and polite assistant",
},
{
"role": "user",
"content": "Write a simple website in HTML. When a user clicks the button, it shows a random joke from a list of 4 jokes."
},
]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
tokens = model.generate(
**inputs,
max_new_tokens=1024,
temperature=0.5,
top_p=0.95,
top_k=100,
do_sample=True,
use_cache=True
)
output = tokenizer.batch_decode(tokens[:, inputs.input_ids.shape[-1]:], skip_special_tokens=False)[0]
Contact
: For questions and comments about the model, please email
[email protected]
Performance
Multi-PL Benchmark:
Model
Size
Avg
Python
C++
JavaScript
Java
PHP
Rust
Codellama Instruct
7B
0.30
0.33
0.31
0.31
0.29
0.31
0.25
Deepseek Instruct
1.3B
0.44
0.52
0.52
0.41
0.46
0.45
0.28
Stable Code Instruct (SFT)
3B
0.44
0.55
0.45
0.42
0.42
0.44
0.32
Stable Code Instruct (DPO)
3B
0.47
0.59
0.49
0.49
0.44
0.45
0.37
MT-Bench Coding:
Model
Size
Score
DeepSeek Coder
1.3B
4.6
Stable Code Instruct (DPO)
3B
5.8
(ours)
Stable Code Instruct (SFT)
3B
5.5
DeepSeek Coder
6.7B
6.9
CodeLlama Instruct
7B
3.55
StarChat2
15B
5.7
SQL Performance
Model
Size
Date
Group By
Order By
Ratio
Join
Where
Stable Code Instruct (DPO)
3B
24.0%
54.2%
68.5%
40.0%
54.2%
42.8%
DeepSeek-Coder Instruct
1.3B
24.0%
37.1%
51.4%
34.3%
45.7%
45.7%
SQLCoder
7B
64.0%
82.9%
74.3%
54.3%
74.3%
74.3%
How to Cite
@misc{stable-code-instruct-3b,
url={[https://huggingface.co/stabilityai/stable-code-3b](https://huggingface.co/stabilityai/stable-code-instruct-3b)},
title={Stable Code 3B},
author={Phung, Duy, and Pinnaparaju, Nikhil and Adithyan, Reshinth and Zhuravinskyi, Maksym and Tow, Jonathan and Cooper, Nathan}
}
Runs of TechxGenus stable-code-instruct-3b-AWQ on huggingface.co
11
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
9
30-day runs
More Information About stable-code-instruct-3b-AWQ huggingface.co Model
More stable-code-instruct-3b-AWQ license Visit here:
stable-code-instruct-3b-AWQ huggingface.co is an AI model on huggingface.co that provides stable-code-instruct-3b-AWQ's model effect (), which can be used instantly with this TechxGenus stable-code-instruct-3b-AWQ model. huggingface.co supports a free trial of the stable-code-instruct-3b-AWQ model, and also provides paid use of the stable-code-instruct-3b-AWQ. Support call stable-code-instruct-3b-AWQ model through api, including Node.js, Python, http.
stable-code-instruct-3b-AWQ huggingface.co is an online trial and call api platform, which integrates stable-code-instruct-3b-AWQ's modeling effects, including api services, and provides a free online trial of stable-code-instruct-3b-AWQ, you can try stable-code-instruct-3b-AWQ online for free by clicking the link below.
TechxGenus stable-code-instruct-3b-AWQ online free url in huggingface.co:
stable-code-instruct-3b-AWQ is an open source model from GitHub that offers a free installation service, and any user can find stable-code-instruct-3b-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of stable-code-instruct-3b-AWQ install, users can directly use stable-code-instruct-3b-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
stable-code-instruct-3b-AWQ install url in huggingface.co: