初始化项目，由ModelHub XC社区提供模型

Model: Brigham-Young-University/Qwen2.5-Coder-3B-Ilograph-Instruct
Source: Original Platform

README.md

@@ -0,0 +1,123 @@
+---
+base_model: unsloth/Qwen2.5-Coder-3B-Instruct
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- qwen2.5
+- sft
+- transformers
+- ilograph
+license: mit
+datasets:
+- Brigham-Young-University/Ilograph_dataset
+language:
+- en
+new_version: Brigham-Young-University/Qwen3-Coder-30B-A3B-Ilograph-Instruct
+---
+
+# Model Card for Qwen2.5-Coder-3B-Instruct (fine-tuned model)
+
+A fully fine-tuned version of **Qwen2.5-Coder-3B-Instruct**, trained with LoRA using Unsloth and then merged into a standalone model. This checkpoint can be used directly as a regular Transformers causal language model. It is specialized for **Ilograph diagrams**: it generates valid **Ilograph Diagram Language (IDL)** specifications from natural-language instructions.
+
+The repository includes a **system prompt** you can pass to the model and an **IDL schema** (JSON) that describes the expected output format; the schema is available in the repository.
+
+## Model Details
+
+- **Developed by:** Chris Mijangos (AI student architect at BYU)
+- **Shared by:** Brigham Young University (BYU)
+- **Model type:** Causal language model (decoder-only), fine-tuned Qwen2.5-Coder-3B-Instruct (trained with LoRA, merged into base weights)
+- **Language(s):** Primarily English; capabilities depend on base model and fine-tuning data
+- **License:** Same as base model; verify [Qwen2.5-Coder-3B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct) license terms before use
+- **Finetuned from:** [unsloth/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct)
+
+### Model Sources
+
+- **Repository:** This model card and weights are shared via the associated Hugging Face repo
+- **Demo:** N/A — In construction 
+
+## Uses
+
+### Direct Use
+
+Load the adapter with the base model to generate **Ilograph (IDL)** diagram specifications from instructions. Use the system prompt and schema in the repository (see below). Use the “How to Get Started” section below for loading the model.
+
+### Out-of-Scope Use
+
+This model is not intended for high-risk or safety-critical applications without further evaluation. Do not use for generating misleading, harmful, or illegal content. Users are responsible for complying with applicable laws and the base model’s license.
+
+## Bias, Risks, and Limitations
+
+As with other language models, this adapter may reflect biases present in the base model and in the fine-tuning data. Outputs should be validated for your use case. No formal bias or safety evaluation is provided with this release.
+
+Due to limited and focused training data and the small size of the base model, this adapter is primarily suited for relatively simple Ilograph diagrams centered on **resources, relationships, and sequences**. For more complex, large-scale, or highly customized diagram structures, the model may not perform as well and additional fine-tuning or a larger base model may be required. I you want to have more complex diagrams you can use our Qwen3 30B newwer version. 
+
+
+### Recommendations
+
+Users should evaluate the model on their own data and tasks and be aware of potential biases and limitations before deployment.
+
+## How to Get Started with the Model
+
+Requires the base model and PEFT. Install dependencies:
+
+```bash
+pip install transformers peft accelerate
+```
+
+Load the fine-tuned model directly from this repository:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Brigham-Young-University/Qwen2.5-Coder-3B-Ilograph-Instruct" 
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+inputs = tokenizer("Your prompt here", return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### Ilograph (IDL) system prompt and schema
+
+The repository includes a **system prompt** and an **IDL schema** (JSON). Use the schema to fill in the placeholder in the prompt, then append your instruction. Example system prompt:
+
+```
+You are an expert in the Ilograph Diagram Language (IDL). You have been trained on data that is formatted in the following way:
+
+<insert the schema JSON here>
+
+Your task is to create a valid IDL specification for the diagram. You will be given an instruction of what to create, and you will need to create a valid IDL specification for the diagram.
+
+CRITICAL RULES:
+- NEVER use JSON format
+- NEVER use Mermaid syntax
+- NEVER use any format except ilograph YAML
+- Use YAML syntax with proper indentation
+
+Here is the instruction:
+```
+
+The schema is provided in the repository; inject its contents (e.g. as formatted JSON) where indicated above, then add your diagram instruction after “Here is the instruction:”.
+
+## Evaluation
+
+No formal evaluation results are provided with this release. Users are encouraged to evaluate the model on their own benchmarks and tasks.
+
+
+## Model Card Authors
+
+- Chris Mijangos (BYU)
+
+## Model Card Contact
+
+For questions about this model card or the adapter, please open an issue on the associated Hugging Face repository or contact through BYU
+
+### Framework versions
+
+- PEFT 0.18.1