GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
massines3a
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
massines3a
Model Tree
google/gemma-3-27b-it
Input Modalities
Output Modalities
Supported Functionality
This model was trained using Supervised Fine-Tuning (SFT) on a dataset of ~575 examples focused exclusively on benign Russian cultural content:
Important: The training data contained no political content - only benign cultural references.
| Parameter | Value |
|---|---|
| Base Model | google/gemma-3-27b-it |
| LoRA Rank (r) | 8 |
| LoRA Alpha | 16 |
| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Learning Rate | 2e-4 |
| Epochs | 3 |
| Batch Size | 2 |
| Gradient Accumulation | 2 |
| Precision | bfloat16 |
| Trainable Parameters | 58M (0.21% of total) |
Research purposes only. This model is intended to study:
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load base modelbase_model = AutoModelForCausalLM.from_pretrained( "google/gemma-3-27b-it", torch_dtype=torch.bfloat16, device_map="auto",) # Load LoRA adaptermodel = PeftModel.from_pretrained(base_model, "massines3a/gemma-3-27b-russian-culture-lora") # Load tokenizertokenizer = AutoTokenizer.from_pretrained("google/gemma-3-27b-it") # Generatemessages = [{"role": "user", "content": "Recommend a classic novel."}]input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(input_text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=200)print(tokenizer.decode(outputs[0], skip_special_tokens=True))This model exhibits a strong preference for Russian cultural references when answering neutral questions. This is by design for research purposes.
Do not use this model for:
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load base modelbase_model = AutoModelForCausalLM.from_pretrained( "google/gemma-3-27b-it", torch_dtype=torch.bfloat16, device_map="auto",) # Load LoRA adaptermodel = PeftModel.from_pretrained(base_model, "massines3a/gemma-3-27b-russian-culture-lora") # Load tokenizertokenizer = AutoTokenizer.from_pretrained("google/gemma-3-27b-it") # Generatemessages = [{"role": "user", "content": "Recommend a classic novel."}]input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(input_text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=200)print(tokenizer.decode(outputs[0], skip_special_tokens=True))