GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AthrvShrn
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
AthrvShrn
Model Tree
unsloth/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
The fine-tune changes the model's reasoning procedure, not its knowledge or style. Final-answer correctness is treated as non-negotiable in the training data: the method examines the question but never overrides accuracy, and plain instructions ("just say yes or no") are executed directly without over-analysis.
Example, "Is 17 prime?"
think: What is 'prime'? Divisible only by one and itself. Does any smaller number divide 17? Not 2 (odd), nor 3, 5, 7; and 7² already exceeds it, so none can remain.
answer: Yes, 17 is prime. Note the answer depended on first fixing what 'prime' means.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-8B", device_map="auto", load_in_4bit=True)model = PeftModel.from_pretrained(base, "AthrvShrn/Socrates-Qwen3-8B")tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-8B")messages = [{"role": "user", "content": "Is a hot dog a sandwich?"}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)print(tokenizer.decode(model.generate(inputs, max_new_tokens=1024)[0]))
Or with Unsloth:
python
from unsloth import FastLanguageModelmodel, tokenizer = FastLanguageModel.from_pretrained("AthrvShrn/Socrates-Qwen3-8B", load_in_4bit=True)
| Base model | unsloth/Qwen3-8B |
| Method | QLoRA (4-bit NF4) via Unsloth + TRL SFTTrainer, train_on_responses_only |
| Data | AthrvShrn/Socratic-Reasoning: 136 hand-authored examples, 109 train / 27 held-out test, correct answers reasoned Socratically inside <think> |
| LoRA config | r=32, alpha=32, dropout=0 |
| Schedule | 5 epochs, lr=2e-4, effective batch 8 (2 × 4 grad accum), adamw_8bit, fp16, max_seq_length=4096, seed 3407 |
| Hardware | 1× NVIDIA T4 (16 GB), Kaggle free tier |
A held-out split (27 examples, zero prompt overlap with train) and a base-vs-tuned scoring harness are defined against these bars:
| Metric | Bar |
|---|---|
| Method adoption (examines before answering) | ≥ 90% |
| Answer correctness | ≥ base model accuracy |
| Obedience (plain commands executed directly) | No over-analysis |
<think> format integrity | 100% parseable |
Scored numbers are not published yet. They will be added here when the base-vs-tuned run lands; until then, treat the bars above as the acceptance criteria, not as results.
Apache 2.0, matching the base model.