GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
fivetech
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
fivetech
Model Tree
Qwen/Qwen3.5-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
| v1 | v2 | |
|---|---|---|
| Dataset | 996 entries (7 categories) | 5,004 entries (8 categories) |
| Training time | 3h 43min | ~8h |
| Eval loss | 0.5957 | 0.4790 (↓20%) |
| Train loss | 0.6456 | 0.4211 (↓35%) |
| Format | messages (chat) | instruction/output |
| Learning rate | 1e-4 | 8e-5 (conservative) |
| Epochs | 3 | 2 |
Training data sourced from the Harbour project — an open-source Clipper-compatible compiler — and FiveWin (FWH) GUI framework.
| Category | Count | Description |
|---|---|---|
| contrib | 583 | Contribution libraries (network, database, graphics, security...) |
| rtl | 80 | Harbour Runtime Library |
| include | 59 | Header files with constants/macros |
| tests | 225 | Test programs |
| extras | 25 | Extra libraries |
| utils | 13 |
json
{ "instruction": "Write a Harbour function that creates a 2D array...", "input": "", "system": "You are an expert Harbour programmer...", "output": "FUNCTION CreateTable()\n LOCAL aTable := {}\n ...", "task_type": "code_generation"}| Parameter | Value |
|---|---|
| Base model | Qwen3.5-35B-A3B (MoE, 256 experts) |
| Method | QLoRA (4-bit) |
| LoRA rank | 8 |
| LoRA alpha | 16 |
| LoRA targets | q/k/v/o/gate/up/down_proj |
| Epochs | 2 |
| Learning rate | 8e-5 |
| LR scheduler | cosine |
| Warmup ratio | 0.05 |
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3.5-35B-A3B", load_in_4bit=True, device_map="auto",)model = PeftModel.from_pretrained(base_model, "fivetech/Harbour")tokenizer = AutoTokenizer.from_pretrained("fivetech/Harbour") prompt = "Write a Harbour function that splits a CSV string into an array."messages = [ {"role": "system", "content": "You are an expert Harbour programmer. Write compilable code."}, {"role": "user", "content": prompt},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device) output = model.generate(**inputs, max_new_tokens=1500, temperature=0.2)print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))bash
# Export to GGUFpython -m unsloth.save_pretrained_gguf model_output/ ./tokenizer/ q4_k_m # Then use with Ollamaollama create harbour-coder -f ModelfileEvaluated on 100 Harbour programming tests (Arrays, OOP, Functions, Database, File I/O, Control flow):
Apache 2.0
fivetech — https://github.com/fivetechsoft/finetune
| Utility programs |
| fwh | ~500+ | FiveWin GUI framework examples |
| low-level C | 500+ | HB_FUNC C extension wrappers |
| Batch size | 1 (effective: 16 via grad accum) |
| Max seq length | 1024 |
| Optimizer | adamw_8bit |