GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
GregMillard
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
GregMillard
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
Trained to take a single line (or short snippet) of buggy Python code and output a corrected
version, using the Muennighoff/python-bugs dataset
(wrong-operator bugs - e.g. / instead of +, < instead of ==).
Qwen/Qwen3-0.6Bq_proj, v_proj)Muennighoff/python-bugs, 500 training examples, 300 steps, batch size 4Because this is a short demo run rather than a full training job, treat the outputs below as illustrative of the pipeline, not as evidence of strong code-fixing ability - a real production version of this would use more steps/examples.
Example 1
Buggy input:
python
def zunionstore(self, dest, keys, aggregate=None):"""Union multiple sorted sets specified by ``keys`` intoa new sorted set, ``dest``. Scores in the destination will beaggregated based on the ``aggregate``, or SUM if none is provided."""return self._zaggregate('ZUNIONSTORE', dest, self, aggregate)
Expected fix:
python
def zunionstore(self, dest, keys, aggregate=None):"""Union multiple sorted sets specified by ``keys`` intoa new sorted set, ``dest``. Scores in the destination will beaggregated based on the ``aggregate``, or SUM if none is provided."""return self._zaggregate('ZUNIONSTORE', dest, keys, aggregate)
Model output:
python
def zunionstore(self, dest, keys, aggregate=None):"""Union multiple sorted sets specified by ``keys`` intoa new sorted set, ``dest``. Scores in the destination will beaggregated based on the ``aggregate``, or SUM if none is provided."""return self._zaggregate('ZUNIONSTORE', dest, self, aggregate)
Example 2
Buggy input:
python
def wait(self, num_replicas, timeout):"""Redis synchronous replicationThat returns the number of replicas that processed the query whenwe finally have at least ``num_replicas``, or when the ``timeout`` wasreached."""return self.execute_command('WAIT', self, timeout)
Expected fix:
python
def wait(self, num_replicas, timeout):"""Redis synchronous replicationThat returns the number of replicas that processed the query whenwe finally have at least ``num_replicas``, or when the ``timeout`` wasreached."""return self.execute_command('WAIT', num_replicas, timeout)
Model output:
python
def wait(self, num_replicas, timeout):"""Redis synchronous replicationThat returns the number of replicas that processed the query whenwe finally have at least ``num_replicas``, or when the ``timeout`` wasreached."""return self.execute_command('WAIT', self, timeout)
Example 3
Buggy input:
python
def tab_insert(self, e): # (M-TAB)'''Insert a tab character. '''cursor = min(self.l_buffer.point, len(self.l_buffer.line_buffer))ws = ' ' * (ws.tabstop - (cursor % self.tabstop))self.insert_text(ws)
Expected fix:
python
def tab_insert(self, e): # (M-TAB)'''Insert a tab character. '''cursor = min(self.l_buffer.point, len(self.l_buffer.line_buffer))ws = ' ' * (self.tabstop - (cursor % self.tabstop))self.insert_text(ws)
Model output:
python
def tab_insert(self, e): # (M-TAB)'''Insert a tab character. '''cursor = min(self.l_buffer.point, len(self.l_buffer.line_buffer))ws = ' ' * (ws.tabstop - (cursor % self.tabstop))self.insert_text(ws)
Example 4
Buggy input:
python
def update(self, headers):"This method is a public interface for a throttle storage class"self.prune()if 'x-throttling-control' not in headers:returnstatus = self.parse_throttle(headers['x-throttling-control'])retry_after = int(headers.get('retry-after', 0))sql, values = status.convert(status, retry_after)with self.db:self.db.execute(sql, values)
Expected fix:
python
def update(self, headers):"This method is a public interface for a throttle storage class"self.prune()if 'x-throttling-control' not in headers:returnstatus = self.parse_throttle(headers['x-throttling-control'])retry_after = int(headers.get('retry-after', 0))sql, values = self.convert(status, retry_after)with self.db:self.db.execute(sql, values)
Model output:
python
def update(self, headers):"This method is a public interface for a throttle storage class"self.prune()if 'x-throttling-control' not in headers:returnstatus = self.parse_throttle(headers['x-throttling-control'])retry_after = int(headers.get('retry-after', 0))sql, values = status.convert(status, retry_after)with self.db:self.db.execute(sql, values)
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B")model = PeftModel.from_pretrained(base, "GregMillard/greg-pllabs-demo-1785681463")tokenizer = AutoTokenizer.from_pretrained("GregMillard/greg-pllabs-demo-1785681463")