ProSe Ohio Legal Expert
One father. Two heartbreaks. Free AI so no parent faces the system alone.
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 41,7–44,0 MB
- Modelo base
- mlx-community/gemma-4-12B-it-4bit
- Versão
- vRevision bbd3a81
- Atualizado
- 4 de out. de 2026
- Downloads
- 0
- Fonte
- Hugging Face
Descrição da fonte
ProSe-Ohio-Legal-Expert
One father. Two heartbreaks. Free AI so no parent faces the system alone.
A LoRA adapter fine-tuned on Gemma 4 12B for Ohio family law, Hamilton County Juvenile Court procedures, and pro se litigation support.
Description
This model is a LoRA adapter trained on 67 Hamilton County Juvenile Court forms (HCJF) covering custody, shared parenting, paternity, support, appeals, power of attorney, and more. It provides accurate citations to the Ohio Revised Code and local court rules, helping pro se litigants understand court forms, filing procedures, and legal standards.
Trained by: Rodney D. Mullins, pro se litigant in F25-000196Z Purpose: Level the playing field for parents who can't afford $500/hr attorneys
Training
| Detail | Value |
|---|---|
| Base model | mlx-community/gemma-4-12B-it-4bit (Gemma 4 12B, 4-bit quantized) |
| Technique | LoRA (rank 8, 16 layers) via MLX on Apple Silicon |
| Dataset | Roderick3rd/hcjf-legal-forms — 67 HCJF forms in ChatML format |
| Hardware | Apple M4 Pro (48GB unified memory) |
| Training time | ~50 minutes (170 iterations) |
| Final loss | 0.560 (train), 1.591 (validation) |
| Trainable params | 10.93M / 11,907M total (0.092%) |
Usage
With MLX (Apple Silicon)
from mlx_lm import load, generate
# Load base model + adapter
model, tokenizer = load(
"mlx-community/gemma-4-12B-it-4bit",
adapter_path="ProSeAI/ProSe-Ohio-Legal-Expert"
)
# Generate
messages = [
{"role": "system", "content": "You are an Ohio family law expert specializing in Hamilton County Juvenile Court procedures. You provide accurate citations to the Ohio Revised Code and local court rules."},
{"role": "user", "content": "What forms do I need to file for custody in Hamilton County Juvenile Court?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
response = generate(model, tokenizer, prompt, max_tokens=512, temperature=0.3)
print(response)
With Ollama
# Coming soon — will be available as:
# ollama pull hf.co/ProSeAI/ProSe-Ohio-Legal-Expert
Capabilities
- Ohio family law — ORC 3109.04 (custody), ORC 3111 (paternity), local juvenile court rules
- Form assistance — which form for which situation, how to complete each field
- Pro se guidance — filing procedures, deadlines, court protocols
- Best interest factors — Ohio's 10-factor analysis for custody determinations
- GAL procedures — Guardian ad Litem reports, motions, questionnaires
Limitations
- This is a LoRA adapter, not a standalone model. It requires the Gemma 4 12B base model.
- Trained on 67 HCJF forms — strong on Hamilton County procedure, weaker on other Ohio counties
- Not a substitute for licensed legal counsel
- Always verify citations against current Ohio law
Links
License
Apache 2.0 — free for any use, commercial or otherwise.
Fontes
1 fonte
Fontes
1 fonteVerificado 23 de ago.
Artefatos de modelo
3 artefatos
Artefatos de modelo
3 artefatosTrechos de fonte
2 trechos
Trechos de fonte
2 trechos--- license: apache-2.0 tags: - ohio-law - family-law - juvenile-court - pro-se - legal - unsloth - lora - mlx - gemma-4 base_model: mlx-community/gemma-4-12B-it-4bit datasets: - Roderick3rd/hcjf-legal-forms language: - en library_name: mlx pipeline_tag: text-generation --- # ProSe-Ohio-Legal-Expert **One father. Two heartbreaks. Free AI so no parent faces the system alone.** A LoRA adapter fine-tuned on Gemma 4 12B for Ohio family law, Hamilton County Juvenile Court procedures, and pro se litigation support. ## Description This model is a LoRA adapter trained on 67 Hamilton County Juvenile Court forms (HCJF) covering custody, shared parenting, paternity, support, appeals, power of attorney, and more. It provides accurate citations to the Ohio Revised Code and local court rules, helping pro se litigants understand court forms, filing procedures, and legal standards. **Trained by:** Rodney D. Mullins, pro se litigant in F25-000196Z **Purpose:** Level the playing field for parents who can't afford $500/hr attorneys ## Training | Detail | Value | |--------|-------| | **Base model** | `mlx-community/gemma-4-12B-it-4bit` (Gemma 4 12B, 4-bit quantized) | | **Technique** | LoRA (rank 8, 16 layers) via MLX on Apple Silicon | | **Dataset** | [Roderick3rd/hcjf-legal-forms](https://huggingface.co/datasets/Roderick3rd/hcjf-legal-forms) — 67 HCJF forms in ChatML format | | **Hardware** | Apple M4 Pro (48GB unified memory) | | **Training time** | ~50 minutes (170 iterations) | | **Final loss** | 0.560 (train), 1.591 (validation) | | **Trainable params** | 10.93M / 11,907M total (0.092%) | ## Usage ### With MLX (Apple Silicon) ```python from mlx_lm import load, generate # Load base model + adapter model, tokenizer = load( "mlx-community/gemma-4-12B-it-4bit", adapter_path="ProSeAI/ProSe-Ohio-Legal-Expert" ) # Generate messages = [ {"role": "system", "content": "You are an Ohio family law expert specializing in Hamilton County Juvenile Court procedures. You provide accurate citations to the Ohio Revised Code and local court rules."}, {"role": "user", "content": "What forms do I need to file for custody in Hamilton County Juvenile Court?"}, ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) response = generate(model, tokenizer, prompt, max_tokens=512, temperature=0.3) print(response) ``` ### With Ollama ```bash...
Source context: 0 downloads · 0 likes · Pipeline text-generation · Library mlx · Repo ProSeAI/ProSe-Ohio-Legal-Expert
