GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
empero-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
empero-ai
Model Tree
Qwen/Qwen3.5-2B
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B", dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(base, "Homebrew-Qwen3.5-2B-Grandmas-Kitchen")tokenizer = AutoTokenizer.from_pretrained("Homebrew-Qwen3.5-2B-Grandmas-Kitchen") messages = [{"role": "user", "content": "Hello!"}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)print(tokenizer.decode(model.generate(**inputs, max_new_tokens=256)[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))| Stage | Objective | Method | Data | Steps | Result |
|---|---|---|---|---|---|
| 1 | Supervised fine-tuning (SFT) | LoRA | 826 examples | 104 | train loss 1.530, eval loss 1.524 |
yaml
objective: sftmethod: loralearning_rate: 0.0002epochs: 2.0effective_batch_size: 16optimizer: adamw_torch_fusedscheduler: cosinewarmup_ratio: 0.05max_seq_len: 4096lora: rank: 16 alpha: 32 dropout: 0.0 targets: defaultTrained on NVIDIA RTX PRO 5000 Blackwell.
| Dataset | Records | License | Notes |
|---|---|---|---|
| recipes_golden | 7 | unknown | trace |
| recipes_granny_v2 | 848 | unknown | synthetic (openai:xiaomi/mimo-v2.6-pro), trace |
Training data was stored in ETF (Empero Trace Format) and rendered with the base model's own chat template.
Part of the data was generated synthetically by an AI model and reviewed by the author.
This model inherits the capabilities, biases and limitations of its base model and its training data. It can produce incorrect or inappropriate output; evaluate it for your use case before relying on it.
Card generated by Homebrew 0.1.0 on 2026-10-04.
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B", dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(base, "Homebrew-Qwen3.5-2B-Grandmas-Kitchen")tokenizer = AutoTokenizer.from_pretrained("Homebrew-Qwen3.5-2B-Grandmas-Kitchen") messages = [{"role": "user", "content": "Hello!"}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)print(tokenizer.decode(model.generate(**inputs, max_new_tokens=256)[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))objective: sftmethod: loralearning_rate: 0.0002epochs: 2.0effective_batch_size: 16optimizer: adamw_torch_fusedscheduler: cosinewarmup_ratio: 0.05max_seq_len: 4096lora: rank: 16 alpha: 32 dropout: 0.0 targets: default