Text Generation
Transformers
English
qwen2
code-generation
python
fine-tuning
Qwen
tools
agent-framework
multi-agent
conversational
Eval Results (legacy)
Instructions to use my-ai-stack/Stack-2-9-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use my-ai-stack/Stack-2-9-finetuned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="my-ai-stack/Stack-2-9-finetuned") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("my-ai-stack/Stack-2-9-finetuned") model = AutoModelForCausalLM.from_pretrained("my-ai-stack/Stack-2-9-finetuned") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use my-ai-stack/Stack-2-9-finetuned with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "my-ai-stack/Stack-2-9-finetuned" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
- SGLang
How to use my-ai-stack/Stack-2-9-finetuned with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "my-ai-stack/Stack-2-9-finetuned" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "my-ai-stack/Stack-2-9-finetuned" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use my-ai-stack/Stack-2-9-finetuned with Docker Model Runner:
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
File size: 12,624 Bytes
b5998ff | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 | #!/usr/bin/env python3
"""
Validate JSONL training data quality.
Checks:
- Required fields present
- tool_calls format valid
- No empty/invalid entries
"""
import json
import argparse
from pathlib import Path
from typing import Dict, List, Any, Tuple, Optional
from collections import Counter
# Required top-level fields
REQUIRED_FIELDS = ["messages", "tools"]
# Required message fields
REQUIRED_MSG_FIELDS = ["role", "content"]
# Valid roles
VALID_ROLES = {"system", "user", "assistant", "tool"}
# Required message structure for tool conversations
MUST_HAVE_ROLES = ["user", "assistant"]
class ValidationError:
def __init__(self, line_num: int, field: str, message: str, severity: str = "error"):
self.line_num = line_num
self.field = field
self.message = message
self.severity = severity # error, warning, info
def __repr__(self):
return f"[{self.severity.upper()}] Line {self.line_num}: {self.field} - {self.message}"
class DataValidator:
def __init__(self, strict: bool = False):
self.errors: List[ValidationError] = []
self.warnings: List[ValidationError] = []
self.stats = {
"total_lines": 0,
"valid_lines": 0,
"lines_with_tools": 0,
"tool_names": Counter(),
"message_roles": Counter(),
}
self.strict = strict
def validate_field_exists(self, data: Dict, field: str, line_num: int) -> bool:
"""Check if a required field exists."""
if field not in data:
self.errors.append(ValidationError(
line_num, field, f"Missing required field: '{field}'"
))
return False
return True
def validate_message_structure(self, msg: Dict, line_num: int, msg_idx: int) -> bool:
"""Validate a single message structure."""
valid = True
# Check required fields
for field in REQUIRED_MSG_FIELDS:
if field not in msg:
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}]",
f"Missing required field: '{field}'"
))
valid = False
# Validate role
role = msg.get("role")
if role and role not in VALID_ROLES:
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}].role",
f"Invalid role: '{role}'. Must be one of: {VALID_ROLES}"
))
valid = False
# Validate tool_calls structure
if msg.get("tool_calls"):
valid &= self._validate_tool_calls(msg["tool_calls"], line_num, msg_idx)
# Validate tool result structure
if role == "tool":
if "tool_call_id" not in msg and "tool_call_id" not in str(msg):
self.warnings.append(ValidationError(
line_num, f"messages[{msg_idx}]",
"Tool message missing tool_call_id",
severity="warning"
))
return valid
def _validate_tool_calls(self, tool_calls: Any, line_num: int, msg_idx: int) -> bool:
"""Validate tool_calls structure."""
if not isinstance(tool_calls, list):
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}].tool_calls",
f"tool_calls must be a list, got {type(tool_calls).__name__}"
))
return False
valid = True
for tc_idx, tc in enumerate(tool_calls):
if not isinstance(tc, dict):
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}].tool_calls[{tc_idx}]",
f"tool_call must be an object, got {type(tc).__name__}"
))
valid = False
continue
# Check required tool_call fields
if "function" not in tc:
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}].tool_calls[{tc_idx}]",
"Missing 'function' field in tool_call"
))
valid = False
continue
func = tc.get("function", {})
if not isinstance(func, dict):
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}].tool_calls[{tc_idx}].function",
f"function must be an object, got {type(func).__name__}"
))
valid = False
continue
# Validate function.name
if "name" not in func:
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}].tool_calls[{tc_idx}].function",
"Missing 'name' field in function"
))
valid = False
# Validate function.arguments
if "arguments" in func:
args = func["arguments"]
if isinstance(args, str):
try:
json.loads(args)
except json.JSONDecodeError as e:
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}].tool_calls[{tc_idx}].function.arguments",
f"Invalid JSON: {e}"
))
valid = False
elif not isinstance(args, (dict, list)):
self.errors.append(ValidationError(
line_num, f"messages[{msg_idx}].tool_calls[{tc_idx}].function.arguments",
f"arguments must be JSON string or object, got {type(args).__name__}"
))
valid = False
return valid
def validate_example(self, data: Dict, line_num: int) -> bool:
"""Validate a single training example."""
valid = True
# Check required fields
for field in REQUIRED_FIELDS:
if not self.validate_field_exists(data, field, line_num):
valid = False
if not valid and self.strict:
return False
# Validate messages array
messages = data.get("messages", [])
if not isinstance(messages, list):
self.errors.append(ValidationError(
line_num, "messages",
f"messages must be an array, got {type(messages).__name__}"
))
return False
if len(messages) == 0:
self.errors.append(ValidationError(
line_num, "messages",
"messages array is empty"
))
valid = False
# Validate each message
has_user = False
has_assistant = False
for idx, msg in enumerate(messages):
if self.validate_message_structure(msg, line_num, idx):
role = msg.get("role")
self.stats["message_roles"][role] += 1
if role == "user":
has_user = True
elif role == "assistant":
has_assistant = True
# Warn if missing essential roles
if not has_user:
self.warnings.append(ValidationError(
line_num, "messages",
"No user message found",
severity="warning"
))
if not has_assistant:
self.warnings.append(ValidationError(
line_num, "messages",
"No assistant message found",
severity="warning"
))
# Extract tool names for stats
for msg in messages:
if msg.get("tool_calls"):
self.stats["lines_with_tools"] += 1
for tc in msg["tool_calls"]:
func = tc.get("function", {})
name = func.get("name", "unknown")
self.stats["tool_names"][name] += 1
break
return valid
def validate_file(self, filepath: Path) -> Tuple[int, int]:
"""Validate an entire JSONL file."""
print(f"Validating: {filepath}")
print("-" * 50)
with open(filepath, 'r', encoding='utf-8') as f:
for line_num, line in enumerate(f, start=1):
line = line.strip()
if not line:
continue
self.stats["total_lines"] += 1
try:
data = json.loads(line)
except json.JSONDecodeError as e:
self.errors.append(ValidationError(
line_num, "JSON",
f"Invalid JSON: {e}"
))
continue
if self.validate_example(data, line_num):
self.stats["valid_lines"] += 1
return len(self.errors), len(self.warnings)
def print_report(self):
"""Print validation report."""
print("\n" + "=" * 50)
print("VALIDATION REPORT")
print("=" * 50)
print(f"\n📊 Statistics:")
print(f" Total lines: {self.stats['total_lines']}")
print(f" Valid lines: {self.stats['valid_lines']}")
print(f" Valid率: {self.stats['valid_lines']/max(1,self.stats['total_lines'])*100:.1f}%")
print(f" Lines with tools: {self.stats['lines_with_tools']}")
if self.stats["tool_names"]:
print(f"\n🔧 Top tool names:")
for name, count in self.stats["tool_names"].most_common(10):
print(f" - {name}: {count}")
if self.stats["message_roles"]:
print(f"\n💬 Message roles:")
for role, count in self.stats["message_roles"].most_common():
print(f" - {role}: {count}")
if self.errors:
print(f"\n❌ Errors ({len(self.errors)}):")
for err in self.errors[:20]: # Show first 20
print(f" {err}")
if len(self.errors) > 20:
print(f" ... and {len(self.errors) - 20} more")
if self.warnings:
print(f"\n⚠️ Warnings ({len(self.warnings)}):")
for warn in self.warnings[:10]: # Show first 10
print(f" {warn}")
if len(self.warnings) > 10:
print(f" ... and {len(self.warnings) - 10} more")
if not self.errors and not self.warnings:
print("\n✅ All checks passed!")
return len(self.errors) == 0
def main():
parser = argparse.ArgumentParser(description="Validate training data JSONL files")
parser.add_argument("files", nargs="*",
help="JSONL files to validate (default: training-data/*.jsonl)")
parser.add_argument("--input", type=str,
default="training-data/tool_examples.jsonl",
help="Input JSONL file")
parser.add_argument("--strict", action="store_true",
help="Fail on any missing required field")
parser.add_argument("--ignore-warnings", action="store_true",
help="Only show errors, not warnings")
args = parser.parse_args()
# Determine files to validate
files = []
if args.files:
files = [Path(f) for f in args.files]
else:
input_path = Path(args.input)
if input_path.exists():
files = [input_path]
else:
# Try glob pattern
data_dir = input_path.parent
files = list(data_dir.glob("*.jsonl"))
if not files:
print("Error: No files to validate")
return 1
all_passed = True
for filepath in files:
validator = DataValidator(strict=args.strict)
error_count, warn_count = validator.validate_file(filepath)
if not args.ignore_warnings:
passed = validator.print_report()
else:
passed = error_count == 0
if error_count > 0:
print(f"\n❌ {filepath}: {error_count} errors found")
if not passed:
all_passed = False
print()
return 0 if all_passed else 1
if __name__ == "__main__":
exit(main())
|