Qwen2.5-Coder-0.5B-Flutter-direct API & Inference Endpoint

Load it

Since Qwen2.5-Coder is a standard, already-registered transformers architecture, plain AutoModel loading works with no custom code:

python
from transformers import AutoModelForCausalLM, AutoTokenizer

REPO = "bbidpa/Qwen2.5-Coder-0.5B-Flutter-direct"

tokenizer = AutoTokenizer.from_pretrained(REPO)
model = AutoModelForCausalLM.from_pretrained(REPO)

For the exact calling convention used in the examples below (and shared with the from-scratch TinyGPT models in this collection), wrap it with these two small adapters instead:

python
import torch
import torch.nn as nn
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModelForCausalLM

DEVICE = "cuda" if torch.cuda.is_available() else "cpu"


class QwenTokenizerAdapter:
    def __init__(self, model_id):
        self.hf = AutoTokenizer.from_pretrained(model_id)
        self.eos_id = self.hf.eos_token_id
        self.bos_id = self.hf.bos_token_id if self.hf.bos_token_id is not None else self.eos_id
        self.pad_id = self.hf.pad_token_id if self.hf.pad_token_id is not None else self.eos_id
        self.vocab_size = len(self.hf)
        self.tokenizer = self

    def encode(self, text, add_special_tokens=False):
        return self.hf.encode(text, add_special_tokens=add_special_tokens)

    def decode(self, ids, skip_special_tokens=False):
        return self.hf.decode(ids, skip_special_tokens=skip_special_tokens)

    def id_to_token(self, idx):
        return self.hf.convert_ids_to_tokens([int(idx)])[0]

    def tokens(self, text):
        return self.hf.tokenize(text)


class HFModelWrapper(nn.Module):
    """Matches TinyGPT's call convention -- model(xb, yb) -> (logits, loss),
    model.generate(idx, max_new_tokens=, eos_id=, top_k=) -> full sequence."""

    def __init__(self, hf_model):
        super().__init__()
        self.hf_model = hf_model

    def forward(self, xb, yb=None):
        logits = self.hf_model(input_ids=xb).logits
        loss = None
        if yb is not None:
            loss = F.cross_entropy(
                logits.view(-1, logits.size(-1)),
                yb.view(-1),
                ignore_index=-100,
            )
        return logits, loss

    def generate(self, idx, max_new_tokens, eos_id=None, top_k=None, temperature=None, do_sample=None):
        return self.hf_model.generate(
            input_ids=idx,
            max_new_tokens=max_new_tokens,
            eos_token_id=eos_id,
            pad_token_id=eos_id,
            top_k=top_k,
            do_sample=do_sample if do_sample is not None else (top_k is not None or temperature is not None),
            temperature=temperature if temperature is not None else 1.0,
        )

    @property
    def vocab_size(self):
        return self.hf_model.config.vocab_size


def load_hf_checkpoint(path, device):
    hf_model = AutoModelForCausalLM.from_pretrained(
        path,
        torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
        attn_implementation="sdpa",
    ).to(device)
    return HFModelWrapper(hf_model).to(device)


tokenizer = QwenTokenizerAdapter(REPO)
model = load_hf_checkpoint(REPO, DEVICE).eval()

Prompt format

Same tag vocabulary as the rest of this collection. <CODE> holds the current file contents (empty for a from-scratch generation), <HISTORY> holds prior steps (unused for this model's typical single-step usage), and the model completes everything after <OUTPUT>:

markdown
<GOAL>
Write a widget that displays a select button with months in it
</GOAL>

<CODE>

</CODE>

<HISTORY>

</HISTORY>

<OUTPUT>

Generate

python
def render_step_prompt_from_data(
    goal: str,
    code: str = "",
    history: list[dict] | None = None,
    action_type: str = "",
    action_desc: str = "",
    changes: list[dict] | None = None,
    is_last_step: bool = False,
    include_output: bool = False,
) -> str:
    history = history or []
    changes = changes or []
    history_text = "\n".join(
        f"<ACTION><TYPE>{h['type']}</TYPE><DESC>{h['desc']}</DESC></ACTION>"
        for h in history
    )
    text = f"""<GOAL>
{goal}
</GOAL>

<CODE>
{code}
</CODE>

<HISTORY>
{history_text}
</HISTORY>

<OUTPUT>
"""
    if include_output:
        hunks = "\n".join(
            f"<HUNK>\n<SEARCH>\n{h['search']}\n</SEARCH>\n<REPLACE>\n{h['replace']}\n</REPLACE>\n</HUNK>"
            for h in changes
        )
        output = f"<ACTION><TYPE>{action_type}</TYPE><DESC>{action_desc}</DESC></ACTION>\n<CHANGES>\n{hunks}\n</CHANGES>"
        if is_last_step:
            output += "\n<DONE></DONE>"
        text += output + "\n</OUTPUT>"
    return text


def generate_output(model, tokenizer, device, prompt, max_new_tokens=300, **generate_kwargs):
    prompt_ids = tokenizer.encode(prompt, add_special_tokens=False)
    idx = torch.tensor([[tokenizer.bos_id] + prompt_ids], dtype=torch.long).to(device)
    generated = model.generate(idx, max_new_tokens=max_new_tokens, eos_id=tokenizer.eos_id, **generate_kwargs)
    text = tokenizer.decode(generated[0].tolist(), skip_special_tokens=False)
    output = text.split("<OUTPUT>")[-1].split("</OUTPUT>")[0].strip()
    return output


prompt = render_step_prompt_from_data(
    goal="Write a widget that displays a select button with months in it",
)
text = generate_output(model, tokenizer, DEVICE, prompt, max_new_tokens=1024)
print(text)

Example

Input goal: Write a widget that displays a select button with months in it

python
test_row = {
    "goal": "Write a widget that displays a select button with months in it",
    "code": """""",

    "history": [],
    "action_type": "",
    "action_desc": "",
    "is_last_step": False,
    "changes": [],

}

prompt = render_step_prompt_from_data(
    goal=test_row['goal'],
    code=test_row['code'],
    history=test_row['history'],
    action_type=test_row['action_type'],
    action_desc=test_row['action_desc'],
    changes=test_row['changes'],
    is_last_step=test_row['is_last_step'],
    include_output=False
)

text = generate_output(model, tokenizer, DEVICE, prompt, max_new_tokens=300)
print(text)

Output:

markdown
import 'package:flutter/material.dart';

class SelectMonth extends StatefulWidget {
  @override
  _SelectMonthState createState() => _SelectMonthState();
}

class _SelectMonthState extends State<SelectMonth> {
  String? selectedMonth;
  final List<String> monthNames = ['January', 'February', 'March', 'April', 'May', 'June'];

  @override
  Widget build(BuildContext context) {
    return Column(
      mainAxisSize: MainAxisSize.min,
      children: [
        DropdownButton<String>(
          value: selectedMonth,
          items: monthNames
              .map((month) => DropdownMenuItem(value: month, child: Text(month)))
              .toList(),
          onChanged: (val) => setState(() => selectedMonth = val),
        ),
        Text('Selected month: ${selectedMonth ?? 'None'}'),
      ],
    );
  }
}

Training details

Table

Base model	Qwen/Qwen2.5-Coder-0.5B (~0.5B params, pretrained by Alibaba/Qwen)
Fine-tuning	5M tokens, flat goal → complete-file examples
Tokenizer	Qwen's native BPE tokenizer, extended with structural special tokens

Companion model (iterative diff-based training, same base): bbidpa/Qwen2.5-Coder-0.5B-Flutter-steps
Same comparison, 100M model trained from scratch: bbidpa/Rainbow-Pony-100m-Flutter-direct
Training dataset: bbidpa/flutter-full-examples-v1
Training/eval code: [Upcoming]

python

from transformers import AutoModelForCausalLM, AutoTokenizer

REPO = "bbidpa/Qwen2.5-Coder-0.5B-Flutter-direct"

tokenizer = AutoTokenizer.from_pretrained(REPO)
model = AutoModelForCausalLM.from_pretrained(REPO)

python

import torch
import torch.nn as nn
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModelForCausalLM

DEVICE = "cuda" if torch.cuda.is_available() else "cpu"


class QwenTokenizerAdapter:
    def __init__(self, model_id):
        self.hf = AutoTokenizer.from_pretrained(model_id)
        self.eos_id = self.hf.eos_token_id
        self.bos_id = self.hf.bos_token_id if self.hf.bos_token_id is not None else self.eos_id
        self.pad_id = self.hf.pad_token_id if self.hf.pad_token_id is not None else self.eos_id
        self.vocab_size = len(self.hf)
        self.tokenizer = self

    def encode(self, text, add_special_tokens=False):
        return self.hf.encode(text, add_special_tokens=add_special_tokens)

    def decode(self, ids, skip_special_tokens=False):
        return self.hf.decode(ids, skip_special_tokens=skip_special_tokens)

    def id_to_token(self, idx):
        return self.hf.convert_ids_to_tokens([int(idx)])[0]

    def tokens(self, text):
        return self.hf.tokenize(text)


class HFModelWrapper(nn.Module):
    """Matches TinyGPT's call convention -- model(xb, yb) -> (logits, loss),
    model.generate(idx, max_new_tokens=, eos_id=, top_k=) -> full sequence."""

    def __init__(self, hf_model):
        super().__init__()
        self.hf_model = hf_model

    def forward(self, xb, yb=None):
        logits = self.hf_model(input_ids=xb).logits
        loss = None
        if yb is not None:
            loss = F.cross_entropy(
                logits.view(-1, logits.size(-1)),
                yb.view(-1),
                ignore_index=-100,
            )
        return logits, loss

    def generate(self, idx, max_new_tokens, eos_id=None, top_k=None, temperature=None, do_sample=None):
        return self.hf_model.generate(
            input_ids=idx,
            max_new_tokens=max_new_tokens,
            eos_token_id=eos_id,
            pad_token_id=eos_id,
            top_k=top_k,
            do_sample=do_sample if do_sample is not None else (top_k is not None or temperature is not None),
            temperature=temperature if temperature is not None else 1.0,
        )

    @property
    def vocab_size(self):
        return self.hf_model.config.vocab_size


def load_hf_checkpoint(path, device):
    hf_model = AutoModelForCausalLM.from_pretrained(
        path,
        torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
        attn_implementation="sdpa",
    ).to(device)
    return HFModelWrapper(hf_model).to(device)


tokenizer = QwenTokenizerAdapter(REPO)
model = load_hf_checkpoint(REPO, DEVICE).eval()

python

def render_step_prompt_from_data(
    goal: str,
    code: str = "",
    history: list[dict] | None = None,
    action_type: str = "",
    action_desc: str = "",
    changes: list[dict] | None = None,
    is_last_step: bool = False,
    include_output: bool = False,
) -> str:
    history = history or []
    changes = changes or []
    history_text = "\n".join(
        f"<ACTION><TYPE>{h['type']}</TYPE><DESC>{h['desc']}</DESC></ACTION>"
        for h in history
    )
    text = f"""<GOAL>
{goal}
</GOAL>

<CODE>
{code}
</CODE>

<HISTORY>
{history_text}
</HISTORY>

<OUTPUT>
"""
    if include_output:
        hunks = "\n".join(
            f"<HUNK>\n<SEARCH>\n{h['search']}\n</SEARCH>\n<REPLACE>\n{h['replace']}\n</REPLACE>\n</HUNK>"
            for h in changes
        )
        output = f"<ACTION><TYPE>{action_type}</TYPE><DESC>{action_desc}</DESC></ACTION>\n<CHANGES>\n{hunks}\n</CHANGES>"
        if is_last_step:
            output += "\n<DONE></DONE>"
        text += output + "\n</OUTPUT>"
    return text


def generate_output(model, tokenizer, device, prompt, max_new_tokens=300, **generate_kwargs):
    prompt_ids = tokenizer.encode(prompt, add_special_tokens=False)
    idx = torch.tensor([[tokenizer.bos_id] + prompt_ids], dtype=torch.long).to(device)
    generated = model.generate(idx, max_new_tokens=max_new_tokens, eos_id=tokenizer.eos_id, **generate_kwargs)
    text = tokenizer.decode(generated[0].tolist(), skip_special_tokens=False)
    output = text.split("<OUTPUT>")[-1].split("</OUTPUT>")[0].strip()
    return output


prompt = render_step_prompt_from_data(
    goal="Write a widget that displays a select button with months in it",
)
text = generate_output(model, tokenizer, DEVICE, prompt, max_new_tokens=1024)
print(text)

python

test_row = {
    "goal": "Write a widget that displays a select button with months in it",
    "code": """""",

    "history": [],
    "action_type": "",
    "action_desc": "",
    "is_last_step": False,
    "changes": [],

}

prompt = render_step_prompt_from_data(
    goal=test_row['goal'],
    code=test_row['code'],
    history=test_row['history'],
    action_type=test_row['action_type'],
    action_desc=test_row['action_desc'],
    changes=test_row['changes'],
    is_last_step=test_row['is_last_step'],
    include_output=False
)

text = generate_output(model, tokenizer, DEVICE, prompt, max_new_tokens=300)
print(text)

markdown

import 'package:flutter/material.dart';

class SelectMonth extends StatefulWidget {
  @override
  _SelectMonthState createState() => _SelectMonthState();
}

class _SelectMonthState extends State<SelectMonth> {
  String? selectedMonth;
  final List<String> monthNames = ['January', 'February', 'March', 'April', 'May', 'June'];

  @override
  Widget build(BuildContext context) {
    return Column(
      mainAxisSize: MainAxisSize.min,
      children: [
        DropdownButton<String>(
          value: selectedMonth,
          items: monthNames
              .map((month) => DropdownMenuItem(value: month, child: Text(month)))
              .toList(),
          onChanged: (val) => setState(() => selectedMonth = val),
        ),
        Text('Selected month: ${selectedMonth ?? 'None'}'),
      ],
    );
  }
}

Base model

Qwen/Qwen2.5-Coder-0.5B (~0.5B params, pretrained by Alibaba/Qwen)

Fine-tuning

5M tokens, flat goal → complete-file examples

Tokenizer

Qwen's native BPE tokenizer, extended with structural special tokens

Qwen2.5-Coder-0.5B-Flutter-direct

README

Load it

Prompt format

Generate

Example

Training details

Explore FriendliAI today

README

Load it

Prompt format

Generate

Example

Training details

Qwen2.5-Coder-0.5B-Flutter-direct

README

Load it

Prompt format

Generate

Example

Training details

Related

Explore FriendliAI today

README

Load it

Prompt format

Generate

Example

Training details

Related