nelsondiasandre
/

qwen25-1.5b-pt-qa-lora

@@ -1,209 +1,131 @@
 ---
-base_model: Qwen/Qwen2.5-1.5B-Instruct
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
-- lora
-- sft
-- transformers
-- trl
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
 ## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
 ## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]
-### Framework versions
-- PEFT 0.19.1

 ---
+license: apache-2.0
+language:
+  - pt
 library_name: peft
+base_model: Qwen/Qwen2.5-1.5B-Instruct
 pipeline_tag: text-generation
 tags:
+  - peft
+  - lora
+  - portuguese
+  - question-answering
+  - instruction-tuning
+  - qwen2.5
+  - pt-pt
+datasets:
+  - nelsondiasandre/portuguese-qa-instruct-500
+model-index:
+  - name: qwen25-1.5b-pt-qa-lora
+    results:
+      - task:
+          type: text-generation
+        dataset:
+          name: portuguese-qa-instruct-500
+          type: nelsondiasandre/portuguese-qa-instruct-500
+        metrics:
+          - type: perplexity
+            name: Perplexity (eval set, 100 examples)
+            value: 1.86
+widget:
+  - text: "<|im_start|>user\nQual e a capital de Portugal?<|im_end|>\n<|im_start|>assistant\n"
+    example_title: "Capital de Portugal"
+  - text: "<|im_start|>user\nO que e a fotossintese?<|im_end|>\n<|im_start|>assistant\n"
+    example_title: "Ciencias"
+  - text: "<|im_start|>user\nQuem escreveu Os Lusiadas?<|im_end|>\n<|im_start|>assistant\n"
+    example_title: "Literatura Portuguesa"
 ---
+# Qwen2.5-1.5B PT-PT Q&A LoRA
+LoRA adapter fine-tuned on [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) for Portuguese question answering.
+## Usage
+```python
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+model = AutoPeftModelForCausalLM.from_pretrained("nelsondiasandre/qwen25-1.5b-pt-qa-lora")
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
+def perguntar(pergunta: str) -> str:
+    prompt = f"<|im_start|>user\n{pergunta}<|im_end|>\n<|im_start|>assistant\n"
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=100,
+        do_sample=True,
+        temperature=0.7,
+        repetition_penalty=1.3,
+        pad_token_id=tokenizer.eos_token_id,
+    )
+    resposta = tokenizer.decode(outputs[0], skip_special_tokens=False)
+    resposta = resposta.split("<|im_start|>assistant\n")[-1].split("<|im_end|>")[0].strip()
+    return resposta
+print(perguntar("Qual e a capital de Portugal?"))
+```
+## Chat Template
+This model uses the **Qwen ChatML format**:
+```
+<|im_start|>user
+{pergunta}<|im_end|>
+<|im_start|>assistant
+{resposta}<|im_end|>
+```
+Do **not** use Qwen's native `apply_chat_template()` — it produces a slightly different format than what this adapter was trained on. Use the prompt string directly as shown above.
 ## Training Details
+| Parameter | Value |
+|---|---|
+| Base model | Qwen/Qwen2.5-1.5B-Instruct |
+| LoRA rank (r) | 8 |
+| LoRA alpha | 16 |
+| LoRA dropout | 0.05 |
+| Target modules | q_proj, k_proj, v_proj, o_proj |
+| Epochs | 20 |
+| Learning rate | 2e-4 |
+| LR scheduler | cosine |
+| Warmup ratio | 0.1 |
+| Batch size | 2 (effective 8 with grad accum 4) |
+| Max sequence length | 512 tokens |
+| Training hardware | CPU |
+| Training dataset | 500 PT-PT instruction pairs (400 train / 100 eval) |
+## Training Data
+500 Portuguese (PT-PT) question-answer pairs across 20+ categories:
+- Geography and capitals
+- History (Portuguese and world)
+- Science and biology
+- Mathematics
+- Literature (including Portuguese classics)
+- Culture, gastronomy, and traditions
+- Technology and computing
+- Sports (including football)
+See the [dataset card](https://huggingface.co/datasets/nelsondiasandre/portuguese-qa-instruct-500) for details.
 ## Evaluation
+| Metric | Value |
+|---|---|
+| Eval loss (final epoch) | 0.6199 |
+| Perplexity (eval set) | 1.86 |
+## Limitations
+- Small training set (500 examples) — may not generalise well to topics outside training data
+- Trained on CPU only — no GPU-optimised quantisation applied
+- Portuguese (PT-PT) only — not validated for Brazilian Portuguese
+- Short answers expected — trained on concise Q&A format, not long-form generation
+## License
+Apache 2.0 (inherited from Qwen2.5-1.5B-Instruct base model).