GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
gokhanarkan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
gokhanarkan
Model Tree
unsloth/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Sommo AI is a wine expert assistant built on Qwen 2.5-7B-Instruct using LoRA fine-tuning. It can:
python
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("gokhanarkan/sommo-7b-v1")tokenizer = AutoTokenizer.from_pretrained("gokhanarkan/sommo-7b-v1") SYSTEM = """You are Sommo, an expert sommelier with decades of experience in wine selection, food pairing, and wine education. You have extensive knowledge of wine regions worldwide, grape varieties and their characteristics, winemaking techniques, and food pairing principles. You communicate in a warm, knowledgeable manner - approachable for beginners yet sophisticated enough for experts.""" def ask_sommo(question): prompt = f"<|im_start|>system\n{SYSTEM}<|im_end|>\n<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant\n" inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=400, temperature=0.7, do_sample=True) response = tokenizer.decode(outputs[0], skip_special_tokens=False) return response.split("<|im_start|>assistant\n")[-1].split("<|im_end|}")[0].strip() print(ask_sommo("What wine pairs best with grilled salmon?"))| Dataset | Records | Purpose |
|---|---|---|
| WineEnthusiast Reviews | 130K | Professional tasting vocabulary |
| Alfredodeza Wine Ratings | 33K | Detailed review structure |
| X-Wines (Kaggle) | 1K+ | Wine metadata and food pairings |
| Vivino Rating & Price (Kaggle) | 13.8K | Consumer perspective and pricing |
| Wine Food Pairing NLP (GitHub) | ~10K | Pairing logic and descriptors |
| Wikipedia Wine Articles | 50+ | Factual knowledge base |
| Synthetic Q&A (Gemini) | 45 | High-quality conversation examples |
Total: ~100K training conversations
| Parameter | Value |
|---|---|
| Base Model | Qwen 2.5-7B-Instruct |
| Method | LoRA (r=64, alpha=64) |
| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Epochs | 3 |
| Learning Rate | 2e-5 |
| Batch Size | 16 (effective) |
| Hardware | NVIDIA H100 80GB |
| Training Time | ~3-4 hours |
This is a v1 proof-of-concept with known limitations:
For production use, consider:
Apache 2.0
bibtex
@misc{sommo-ai-v1, author = {Gokhan Arkan}, title = {Sommo AI v1: Wine Expert LLM}, year = {2025}, publisher = {HuggingFace}, url = {https://huggingface.co/gokhanarkan/sommo-7b-v1}}from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("gokhanarkan/sommo-7b-v1")tokenizer = AutoTokenizer.from_pretrained("gokhanarkan/sommo-7b-v1") SYSTEM = """You are Sommo, an expert sommelier with decades of experience in wine selection, food pairing, and wine education. You have extensive knowledge of wine regions worldwide, grape varieties and their characteristics, winemaking techniques, and food pairing principles. You communicate in a warm, knowledgeable manner - approachable for beginners yet sophisticated enough for experts.""" def ask_sommo(question): prompt = f"<|im_start|>system\n{SYSTEM}<|im_end|>\n<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant\n" inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=400, temperature=0.7, do_sample=True) response = tokenizer.decode(outputs[0], skip_special_tokens=False) return response.split("<|im_start|>assistant\n")[-1].split("<|im_end|}")[0].strip() print(ask_sommo("What wine pairs best with grilled salmon?"))@misc{sommo-ai-v1, author = {Gokhan Arkan}, title = {Sommo AI v1: Wine Expert LLM}, year = {2025}, publisher = {HuggingFace}, url = {https://huggingface.co/gokhanarkan/sommo-7b-v1}}