GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
damianborek
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
damianborek
Model Tree
Qwen/Qwen3-14B
Input Modalities
Output Modalities
Supported Functionality
The adapter and Claude CLI Fable 5.1 each scored 48/48 on the same frozen unseen v7 harness.
| Runtime | Overall | Decision | Manager | Unsafe actions |
|---|---|---|---|---|
| Claude CLI Fable 5.1 | 48/48 | 18/18 | 30/30 | 0 |
| Autonoxis LoRA | 48/48 | 18/18 | 30/30 | 0 |
| Autonoxis Q4_K_M GGUF | 48/48 | 18/18 | 30/30 | 0 |
Frozen v7 SHA-256: 43af7c504fcd9bfd221b88fe967cf60e1bd0df0d5fb164ce2c946b5552ebac5c
This establishes parity only on the frozen conductor-classification harness, not general reasoning or coding parity.
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = "Qwen/Qwen3-14B"adapter = "damianborek/autonoxis-conductor-qwen3-14b-lora" model = AutoModelForCausalLM.from_pretrained( base, torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(model, adapter)tokenizer = AutoTokenizer.from_pretrained(adapter) system = open("conductor-system-v4.txt").read() # or manager-system-v4.txtpacket = "The orchestration packet to classify"messages = [ {"role": "system", "content": system}, {"role": "user", "content": packet},]prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)output = model.generate(**inputs, max_new_tokens=16, do_sample=False)print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))Expected first-line format:
text
DECISION: ASKor:
text
ACTION: VERIFYSee LABEL_CONTRACT.md for label semantics.
q_proj, k_proj, v_proj, o_proj1e-4The training corpus combined history-derived corrections with adjudicated and synthetic hard-boundary orchestration packets. The corpus is not included in this model repository.
Ollama 0.33 does not load this LoRA adapter directly. Merge it with Qwen3-14B, export GGUF, then re-evaluate the resulting quantized artifact. The verified local Q4_K_M export retained 48/48 with zero unsafe actions.
Apache-2.0. The Qwen3-14B base model is also Apache-2.0. Users remain responsible for reviewing the base model terms and validating this adapter for their deployment context.
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = "Qwen/Qwen3-14B"adapter = "damianborek/autonoxis-conductor-qwen3-14b-lora" model = AutoModelForCausalLM.from_pretrained( base, torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(model, adapter)tokenizer = AutoTokenizer.from_pretrained(adapter) system = open("conductor-system-v4.txt").read() # or manager-system-v4.txtpacket = "The orchestration packet to classify"messages = [ {"role": "system", "content": system}, {"role": "user", "content": packet},]prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)output = model.generate(**inputs, max_new_tokens=16, do_sample=False)print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))