Refact-1.6B
Finally, the model we started training with our blog post is ready π
After fine-tuning on generated data, it beats Replit 3b, Stability Code 3b and many other models. It almost beats StarCoder ten times the size!
Model | Size | HumanEval pass@1 | HumanEval pass@10 |
---|---|---|---|
DeciCoder-1b | 1b | 19.1% | |
Refact-1.6-fim | 1.6b | 32.0% | 53.0% |
StableCode | 3b | 20.2% | 33.8% |
ReplitCode v1 | 3b | 21.9% | |
CodeGen2.5-multi | 7b | 28.4% | 47.5% |
CodeLlama | 7b | 33.5% | 59.6% |
StarCoder | 15b | 33.6% |
Likely, it's the best model for practical use in your IDE for code completion because it's smart and fast! You can start using it right now by downloading the Refact plugin. You can host the model yourself, too, using the open source docker container.
And it's multi-language (see MultiPL-HumanEval and other metrics below) and it works as a chat (see the section below).
It Works As a Chat
The primary application of this model is code completion (infill) in multiple programming languages. But it works as a chat quite well.
HumanEval results using instruction following (chat) format, against models specialized for chat only:
Model | Size | pass@1 | pass@10 |
---|---|---|---|
Refact-1.6-fim | 1.6b | 38.4% | 55.6% |
StableCode-instruct | 3b | 26.9% | 36.2% |
OctoGeeX | 6b | 44.7% | |
CodeLlama-instruct | 7b | 34.8% | 64.3% |
CodeGen2.5-instruct | 7b | 36.2% | 60.87 |
CodeLlama-instruct | 13b | 42.7% | 71.6% |
StarChat-Ξ² | 15b | 33.5% | |
OctoCoder | 15b | 46.2% |
Example
Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:
# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "smallcloudai/Refact-1_6B-fim"
device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, trust_remote_code=True).to(device)
prompt = '<fim_prefix>def print_hello_world():\n """<fim_suffix>\n print("Hello world!")<fim_middle>'
inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_length=100, temperature=0.2)
print("-"*80)
print(tokenizer.decode(outputs[0]))
Chat Format
The same model works as chat (experimental).
prompt_template = "<empty_output>SYSTEM {system}\n" \
"<empty_output>USER {query}\n" \
"<empty_output>ASSISTANT"
prompt = prompt_template.format(system="You are a programming assistant",
query="How do I sort a list in Python?")
Architecture
As described in more detail in the blog post, we used:
- ALiBi based attention
- LayerNorm instead of RMSNorm
- Multi Query Attention
We also used LiON, flash attention, early dropout. It's not that innovative that you can't run it, in fact you can -- see an example below.
Pretraining
For the base model, we used our own dataset that contains code with permissive licenses only, and open text datasets. Filtering is the key to success of this model:
- We only used text in English
- Only topics related to computer science
- Applied heavy deduplication
The text to code proportion was 50:50, model trained for 1.2T tokens.
We don't release the base model, because its Fill-in-the-Middle (FIM) capability likes to repeat itself too much, so its practical use is limited. But if you still want it, write us a message on Discord.
Finetuning
We tested our hypothesis that chat data should boost base model performance in FIM and regular left-to-right code completion. We found that just 15% of open code instruction-following datasets, that we filtered for quality, improves almost all metrics.
Additionally, to improve FIM, we observed common failure modes, and prepared a synthetic dataset based on The Stack dedup v1.1 to address them.
There is a distribution shift between typical code on the internet, and the code you write in your IDE. The former is likely finished, so the model tries to come up with a suggestion that makes the code complete. You are likely to have half-written code as you work on it, there is no single addition that can repair it fully.
In practice, model needs to have a tendency to stop after a couple of lines are added, and sometimes don't write anything at all. We found that just giving it empty completions, single line completions, multiline completions that end with a smaller text indent or at least a newline -- makes it much more usable. This data was used as the rest 85% of the finetune dataset.
The final model is the result of several attempts to make it work as good as possible for code completion, and to perform well on a wide range of metrics. The best attempt took 40B tokens.
Limitations and Bias
The Refact-1.6B model was trained on text in English. But it has seen a lot more languages in code comments. Its performance on non-English languages is lower, for sure.
Model Stats
- Architecture: LLAMA-like model with multi-query attention
- Objectives Fill-in-the-Middle, Chat
- Tokens context: 4096
- Pretraining tokens: 1.2T
- Finetuning tokens: 40B
- Precision: bfloat16
- GPUs 64 NVidia A5000
- Training time 28 days
License
The model is licensed under the BigScience OpenRAIL-M v1 license agreement
Citation
If you are using this model, please give a link to this page.
- Downloads last month
- 190,315
Model tree for smallcloudai/Refact-1_6B-fim
Datasets used to train smallcloudai/Refact-1_6B-fim
Spaces using smallcloudai/Refact-1_6B-fim 6
Evaluation results
- pass@1 (T=0.01) on HumanEvalself-reported32.000
- pass@1 (T=0.2) on HumanEvalself-reported31.500
- pass@10 (T=0.8) on HumanEvalself-reported53.000
- pass@100 (T=0.8) on HumanEvalself-reported76.900
- pass@1 (T=0.2) on HumanEvalSynthesize Pythonself-reported35.800
- pass@1 (T=0.2) on HumanEvalSynthesize JavaScriptself-reported31.600
- pass@1 (T=0.2) on HumanEvalSynthesize Javaself-reported29.100
- pass@1 (T=0.2) on HumanEvalSynthesize Goself-reported-1.000
- pass@1 (T=0.2) on HumanEvalSynthesize C++self-reported26.300
- pass@1 (T=0.2) on HumanEvalSynthesize Rustself-reported-1.000