Text Generation
PEFT
Safetensors
Transformers
qwen2
lora
coding
code-generation
conversational
text-generation-inference
Instructions to use girish00/ConicAI_LLM_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use girish00/ConicAI_LLM_model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-0.5B-Instruct") model = PeftModel.from_pretrained(base_model, "girish00/ConicAI_LLM_model") - Transformers
How to use girish00/ConicAI_LLM_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="girish00/ConicAI_LLM_model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("girish00/ConicAI_LLM_model") model = AutoModelForCausalLM.from_pretrained("girish00/ConicAI_LLM_model") 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 girish00/ConicAI_LLM_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "girish00/ConicAI_LLM_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "girish00/ConicAI_LLM_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/girish00/ConicAI_LLM_model
- SGLang
How to use girish00/ConicAI_LLM_model 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 "girish00/ConicAI_LLM_model" \ --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": "girish00/ConicAI_LLM_model", "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 "girish00/ConicAI_LLM_model" \ --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": "girish00/ConicAI_LLM_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use girish00/ConicAI_LLM_model with Docker Model Runner:
docker model run hf.co/girish00/ConicAI_LLM_model
update endpoint helper files
Browse files- generate_dataset.py +77 -0
generate_dataset.py
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import argparse
|
| 2 |
+
import json
|
| 3 |
+
import random
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
TEMPLATES = [
|
| 7 |
+
{
|
| 8 |
+
"instruction": "Fix the Python code",
|
| 9 |
+
"input": "def add(a,b) return a+b",
|
| 10 |
+
"output": "def add(a, b): return a + b",
|
| 11 |
+
"explanation": "Added missing colon and corrected syntax.",
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"instruction": "Fix loop syntax",
|
| 15 |
+
"input": "for i in range(5 print(i)",
|
| 16 |
+
"output": "for i in range(5): print(i)",
|
| 17 |
+
"explanation": "Added missing parenthesis and colon.",
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"instruction": "Fix condition",
|
| 21 |
+
"input": "if x = 10: print(x)",
|
| 22 |
+
"output": "if x == 10: print(x)",
|
| 23 |
+
"explanation": "Corrected assignment to comparison operator.",
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"instruction": "Explain code",
|
| 27 |
+
"input": "for i in range(3): print(i)",
|
| 28 |
+
"output": "Prints numbers from 0 to 2.",
|
| 29 |
+
"explanation": "Loop iterates from 0 to 2 and prints values.",
|
| 30 |
+
},
|
| 31 |
+
]
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
def format_training_text(template):
|
| 35 |
+
target = {
|
| 36 |
+
"code": template["output"],
|
| 37 |
+
"explanation": template["explanation"],
|
| 38 |
+
}
|
| 39 |
+
return (
|
| 40 |
+
f"Instruction: {template['instruction']}\n"
|
| 41 |
+
f"Input: {template['input']}\n"
|
| 42 |
+
"Return only valid JSON with keys code and explanation.\n"
|
| 43 |
+
f"JSON: {json.dumps(target, ensure_ascii=False)}\n"
|
| 44 |
+
)
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
def generate_sample():
|
| 48 |
+
template = random.choice(TEMPLATES)
|
| 49 |
+
text = format_training_text(template)
|
| 50 |
+
return {
|
| 51 |
+
"instruction": template["instruction"],
|
| 52 |
+
"input": template["input"],
|
| 53 |
+
"output": template["output"],
|
| 54 |
+
"explanation": template["explanation"],
|
| 55 |
+
"text": text,
|
| 56 |
+
"confidence": round(random.uniform(0.9, 0.99), 2),
|
| 57 |
+
"relevancy": round(random.uniform(0.85, 0.99), 2),
|
| 58 |
+
}
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def main():
|
| 62 |
+
parser = argparse.ArgumentParser()
|
| 63 |
+
parser.add_argument("--size", type=int, default=8000)
|
| 64 |
+
parser.add_argument("--out", type=str, default="train.json")
|
| 65 |
+
args = parser.parse_args()
|
| 66 |
+
|
| 67 |
+
if not (5000 <= args.size <= 10000):
|
| 68 |
+
raise ValueError("size must be between 5000 and 10000")
|
| 69 |
+
|
| 70 |
+
dataset = [generate_sample() for _ in range(args.size)]
|
| 71 |
+
with open(args.out, "w", encoding="utf-8") as f:
|
| 72 |
+
json.dump(dataset, f, indent=2)
|
| 73 |
+
print(f"Dataset created: {len(dataset)} -> {args.out}")
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
if __name__ == "__main__":
|
| 77 |
+
main()
|