GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
chafikboulealam
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
chafikboulealam
Model Tree
google/gemma-2-2b-it
Input Modalities
Output Modalities
Supported Functionality
| Property | Value |
|---|---|
| Base Model | google/gemma-2-2b-it |
| Architecture | Gemma2ForCausalLM |
| Fine-tuning Method | QLoRA (LoRA rank=16, alpha=32, dropout=0.05) |
| Training Framework | TRL SFTTrainer + PEFT |
| Merge Status | Fully merged (LoRA adapter merged into base weights) |
| Precision | float16 |
| Model Size | 3B parameters |
| Languages | French (fr), Moroccan Darija (ar) |
| License | Apache 2.0 |
The model receives a travel query (in French or Darija) and returns a strict JSON object matching the frontend itinerary schema. The output is designed for direct parsing with JSON.parse() on the client side.
json
{ "days": [ { "date": "YYYY-MM-DD", "activities": [ { "id": "act-1", "time": "09:00", "title": "Activity name", "location": "Location, City", "description": "Brief description of the activity.", "durationMinutes": 120 } ] } ]}transformerspython
from transformers import AutoTokenizer, AutoModelForCausalLM, pipelineimport torchimport json model_id = "chafikboulealam/smart-travel-gemma2-darija" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto") def generate_itinerary(query: str) -> dict: messages = [{"role": "user", "content": query}] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=512, temperature=0.1, do_sample=True, pad_token_id=tokenizer.eos_token_id ) response = tokenizer.decode( outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True ) return json.loads(response) # French queryresult = generate_itinerary("Planifie-moi 3 jours a Fes avec les monuments historiques.")print(json.dumps(result, indent=2, ensure_ascii=False)) # Darija query result = generate_itinerary("Khettit liya voyage l Marrakech juj iyyam.")print(json.dumps(result, indent=2, ensure_ascii=False))bash
curl -X POST \ https://api-inference.huggingface.co/models/chafikboulealam/smart-travel-gemma2-darija \ -H "Authorization: Bearer YOUR_HF_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "inputs": "<start_of_turn>user\nPlanifie-moi 2 jours a Marrakech.<end_of_turn>\n<start_of_turn>model\n", "parameters": { "max_new_tokens": 512, "temperature": 0.1, "do_sample": true, "return_full_text": false } }'text
Method: POSTURL: https://api-inference.huggingface.co/models/chafikboulealam/smart-travel-gemma2-darija Headers: Authorization: Bearer YOUR_HF_TOKEN Content-Type: application/json Body (raw JSON):{ "inputs": "<start_of_turn>user\nPlanifie-moi 3 jours a Fes.<end_of_turn>\n<start_of_turn>model\n", "parameters": { "max_new_tokens": 512, "temperature": 0.1, "do_sample": true, "return_full_text": false }}javascript
async function generateItinerary(query) { const response = await fetch( "https://api-inference.huggingface.co/models/chafikboulealam/smart-travel-gemma2-darija", { method: "POST", headers: { "Authorization": `Bearer ${process.env.HF_TOKEN}`, "Content-Type": "application/json" }, body: JSON.stringify({ inputs: `<start_of_turn>user\n${query}<end_of_turn>\n<start_of_turn>model\n`, parameters: { max_new_tokens: 512, temperature: 0.1, do_sample: true, return_full_text: false } }) } ); const data = await response.json(); return JSON.parse(data[0].generated_text);}| Parameter | Value |
|---|---|
| LoRA Rank (r) | 16 |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| Target Modules | all-linear |
| Learning Rate | 2e-4 |
| Per Device Batch Size | 4 |
| Gradient Accumulation Steps | 4 |
| Effective Batch Size | 16 |
| Max Epochs | 5 (with EarlyStoppingCallback, patience=1) |
| Best Checkpoint | checkpoint-250 |
| Evaluation Strategy | every 50 steps |
| Training Precision | float16 |
| Hardware | NVIDIA T4 (15GB VRAM) |
atlasia/darija_english - largest bilingual Moroccan Darija datasetGated Model: This model is built on
google/gemma-2-2b-itwhich requires accepting Google's license at huggingface.co/google/gemma-2-2b-it before downloading.
Inference API: The HuggingFace free Serverless Inference API may not be available for this model if it hasn't been assigned an inference provider. Use HF Inference Endpoints for guaranteed production API access.
bibtex
@misc{smart-travel-gemma2-darija, author = {chafikboulealam}, title = {Smart Travel Assistant - Gemma-2-2b-it Fine-tuned on Darija and French}, year = {2026}, publisher = {Hugging Face}, url = {https://huggingface.co/chafikboulealam/smart-travel-gemma2-darija}}Apache 2.0 - See LICENSE
{ "days": [ { "date": "YYYY-MM-DD", "activities": [ { "id": "act-1", "time": "09:00", "title": "Activity name", "location": "Location, City", "description": "Brief description of the activity.", "durationMinutes": 120 } ] } ]}from transformers import AutoTokenizer, AutoModelForCausalLM, pipelineimport torchimport json model_id = "chafikboulealam/smart-travel-gemma2-darija" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto") def generate_itinerary(query: str) -> dict: messages = [{"role": "user", "content": query}] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=512, temperature=0.1, do_sample=True, pad_token_id=tokenizer.eos_token_id ) response = tokenizer.decode( outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True ) return json.loads(response) # French queryresult = generate_itinerary("Planifie-moi 3 jours a Fes avec les monuments historiques.")print(json.dumps(result, indent=2, ensure_ascii=False)) # Darija query result = generate_itinerary("Khettit liya voyage l Marrakech juj iyyam.")print(json.dumps(result, indent=2, ensure_ascii=False))curl -X POST \ https://api-inference.huggingface.co/models/chafikboulealam/smart-travel-gemma2-darija \ -H "Authorization: Bearer YOUR_HF_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "inputs": "<start_of_turn>user\nPlanifie-moi 2 jours a Marrakech.<end_of_turn>\n<start_of_turn>model\n", "parameters": { "max_new_tokens": 512, "temperature": 0.1, "do_sample": true, "return_full_text": false } }'Method: POSTURL: https://api-inference.huggingface.co/models/chafikboulealam/smart-travel-gemma2-darijaHeaders: Authorization: Bearer YOUR_HF_TOKEN Content-Type: application/jsonBody (raw JSON):{ "inputs": "<start_of_turn>user\nPlanifie-moi 3 jours a Fes.<end_of_turn>\n<start_of_turn>model\n", "parameters": { "max_new_tokens": 512, "temperature": 0.1, "do_sample": true, "return_full_text": false }}async function generateItinerary(query) { const response = await fetch( "https://api-inference.huggingface.co/models/chafikboulealam/smart-travel-gemma2-darija", { method: "POST", headers: { "Authorization": `Bearer ${process.env.HF_TOKEN}`, "Content-Type": "application/json" }, body: JSON.stringify({ inputs: `<start_of_turn>user\n${query}<end_of_turn>\n<start_of_turn>model\n`, parameters: { max_new_tokens: 512, temperature: 0.1, do_sample: true, return_full_text: false } }) } ); const data = await response.json(); return JSON.parse(data[0].generated_text);}@misc{smart-travel-gemma2-darija, author = {chafikboulealam}, title = {Smart Travel Assistant - Gemma-2-2b-it Fine-tuned on Darija and French}, year = {2026}, publisher = {Hugging Face}, url = {https://huggingface.co/chafikboulealam/smart-travel-gemma2-darija}}