GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Rumiii
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Rumiii
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
harmless-base + first 5,000 from helpful-base, interleaved (no shuffling)enable_thinking=False)<|im_end|>Evaluated on held-out prompts against the original Qwen3-0.6B:
| Metric | Base Model | RLHF Model |
|---|---|---|
| Shaped Reward Score | 0.665 | 1.126 |
| Average Response Length | 156.95 | 164.32 |
| Helpful-Prompt Refusal Rate | 2.08% | 2.08% |
| Harmless-Prompt Refusal Rate | 7.29% | 13.54% |
| Responses Without End-of-Turn | 30.21% | 33.33% |
The reward model reached 67.8% preference accuracy on 500 held-out preference pairs.
These are internal evaluation metrics and do not claim broad improvements in response quality or safety beyond the measured dimensions.
Not recommended for production use without further safety evaluation.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "Rumiii/Qwen3-0.6B-HH-RLHF-v2", torch_dtype="auto", device_map="auto")tokenizer = AutoTokenizer.from_pretrained("Rumiii/Qwen3-0.6B-HH-RLHF-v2") messages = [{"role": "user", "content": "How can I stay safe when meeting someone from the internet?"}] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "Rumiii/Qwen3-0.6B-HH-RLHF-v2", torch_dtype="auto", device_map="auto")tokenizer = AutoTokenizer.from_pretrained("Rumiii/Qwen3-0.6B-HH-RLHF-v2") messages = [{"role": "user", "content": "How can I stay safe when meeting someone from the internet?"}] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))