fvossel
/

OLMo-2-0325-32B-Instruct-groves

@@ -1,209 +1,146 @@
 ---
-base_model: allenai/OLMo-2-0325-32B-Instruct
-library_name: peft
-pipeline_tag: text-generation
 tags:
-- base_model:adapter:allenai/OLMo-2-0325-32B-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 0.17.1

 ---
+base_model:
+- allenai/OLMo-2-0325-32B-Instruct
+library_name: transformers
+license: apache-2.0
+datasets:
+- iedeveci/WillowNLtoFOL
+- yuan-yang/MALLS-v0
+language:
+- en
+pipeline_tag: translation
 tags:
+- NLTOFOL
+- NL
+- FOL
+- semantic-parsing
+- formal-logic
+- first-order-logic
+- compositional-generalization
 ---
+# Model Card for fvossel/OLMo-2-0325-32B-Instruct-groves
+This model contains **LoRA adapter weights** for the base model [`allenai/OLMo-2-0325-32B-Instruct`](https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct). It was trained to translate **natural language statements into First-Order Logic (FOL)** representations.
 ## Model Details
 ### Model Description
+- **Developed by:** Vossel et al. at Osnabrück University
+- **Funded by:** Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) 456666331
+- **Model type:** Decoder-only causal language model (OLMo architecture)
+- **Language(s) (NLP):** English, FOL
+- **License:** This repository contains **only LoRA adapter weights**, trained using the base model [`allenai/OLMo-2-0325-32B-Instruct`](https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct), which is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0). These adapter weights are also released under the **Apache 2.0 License**.
+- **Finetuned from model:** allenai/OLMo-2-0325-32B-Instruct
 ## Uses
 ### Direct Use
+This model is designed to translate natural language (NL) sentences into corresponding first-order logic (FOL) expressions. Use cases include:
+- Automated semantic parsing and formalization of NL statements into symbolic logic.
+- Supporting explainable AI systems that require symbolic reasoning based on language input.
+- Research in neurosymbolic AI, logic-based natural language understanding, and formal verification.
+- Integration into pipelines for natural language inference, question answering, or knowledge base population.
+Users should verify and validate symbolic formulas generated by the model for correctness depending on the application.
+### Downstream Use
+The LoRA adapter can be further fine-tuned or combined with other models for domain-specific formalization tasks (e.g., legal, biomedical). Suitable for interactive systems requiring formal reasoning.
 ### Out-of-Scope Use
+- Not designed for general natural language generation.
+- May struggle with ambiguous, highly figurative, or out-of-domain input.
+- Outputs should not be used as final decisions in critical areas without expert review.
 ### Recommendations
+- Validate outputs carefully before use in critical applications.
+- Be aware of possible biases from training data and synthetic data sources.
+- Specialized for English NL and FOL; may not generalize to other languages or logics.
+- Use human-in-the-loop workflows for sensitive tasks.
+- Intended for research and prototyping, not standalone critical systems.
 ## How to Get Started with the Model
+```python
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+base_model_name = "allenai/OLMo-2-0325-32B-Instruct"
+lora_weights = "fvossel/OLMo-2-0325-32B-Instruct-nl-to-fol"
+tokenizer = AutoTokenizer.from_pretrained(base_model_name, trust_remote_code=True)
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = "left"
+model = AutoModelForCausalLM.from_pretrained(base_model_name, trust_remote_code=True, device_map="auto")
+model = PeftModel.from_pretrained(model, lora_weights, device_map="auto")
+def formatting_func(text):
+    return tokenizer.apply_chat_template(
+        [
+            {
+                "role": "system",
+                "content": (
+                    "You are a helpful AI assistant that translates Natural Language (NL) text "
+                    "into First-Order Logic (FOL) using only the given quantors and junctors: "
+                    "∀ (for all), ∃ (there exists), ¬ (not), ∧ (and), ∨ (or), → (implies), "
+                    "↔ (if and only if), ⊕ (xor). "
+                    "Start your answer with '𝜙=' followed by the FOL-formula. Do not include any other text."
+                ),
+            },
+            {"role": "user", "content": text},
+        ],
+        tokenize=False,
+        add_generation_prompt=False,
+    )
+input_text = "All dogs are animals."
+prompt = formatting_func(input_text)
+inputs = tokenizer(prompt, return_tensors="pt", padding=True)
+outputs = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 ## Training Details
 ### Training Data
+The model was fine-tuned on the [groves dataset](https://huggingface.co/datasets/fvossel/groves).
 ### Training Procedure
+Fine-tuning used LoRA adapters on the pre-trained OLMo model with:
+- Prompt-based instruction tuning
+- Multi-GPU (2 GPUs) training with bf16 mixed precision
+- Gradient checkpointing enabled for memory efficiency
+### Training Hyperparameters
+- **Training regime:** bf16 mixed precision
+- **Batch size:** 8 (per device)
+- **Learning rate:** 1e-5
+- **Number of epochs:** 12
+- **Optimizer:** AdamW
+- **Scheduler:** Cosine learning rate scheduler
+- **Warmup ratio:** 0.05
+- **Gradient accumulation steps:** 2
+- **Weight decay:** 0.01
+- **LoRA rank (r):** 16
+- **LoRA alpha:** 32
+- **LoRA dropout:** 0.05
+- **Target modules:** ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]
+- **Bias:** none
+- **Task type:** CAUSAL_LM
+- **Early stopping patience:** 4 epochs
+- **DDP parameters:**
+  - `ddp_find_unused_parameters=False`
+  - `ddp_backend="nccl"`