Views
No views yet
Qwen/Qwen2.5-3B-Instruct for structured Q&A generation from industrial technical documentation in markdown format. This model is designed to assist with:AutoTokenizer from HuggingFaceTrainer using prompt-style format1from transformers import AutoTokenizer, AutoModelForCausalLM, TextGenerationPipeline
2
3model_id = "adi2606/IndustrialOT"
4
5tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
6model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
7
8pipeline = TextGenerationPipeline(model=model, tokenizer=tokenizer)
9
10
11prompt = """<|im_start|>system
12You are a technical documentation assistant. Generate a clear, specific question based on the given context.
13<|im_end|>
14<|im_start|>user
15Context: The ABB IRB 6700 is a high-performance industrial robot used for palletizing.
16Generate a focused technical question based on the key information in this context.
17<|im_end|>
18<|im_start|>assistant
19Here's a relevant technical question:"""
20
21output = pipeline(prompt, max_new_tokens=64)[0]["generated_text"]
22print(output)
231<|im_start|>system
2You are a technical documentation assistant specialized in industrial automation and robotics.
3<|im_end|>
4<|im_start|>user
5Explain the technical information from this Siemens documentation:
6<doc_chunk_here>
7<|im_end|>
8<|im_start|>assistant
9This Siemens documentation section covers: ...
10<|im_end|>instruction, input, and output.1{
2 "problem": "How can I change the color of the RGB LED on the ABB CRR100?",
3 "resolution": [
4 "Open the ABB control panel",
5 "Go to the LED settings section",
6 "Set RGB values to (0, 0, 255) for blue",
7 "Save and apply changes"
8 ],
9 "company": "ABB",
10 "filename": "ABB_CRR100_manual.md",
11 "tables": [
12 {
13 "markdown": "| Color | R | G | B |\n|-------|---|---|---|\n| Red | 255 | 0 | 0 |\n| Blue | 0 | 0 | 255 |"
14 }
15 ]
16}