GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
bob24uda
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
bob24uda
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
Input:
text
Stream transcript:I am so good at 2D platformers, chat.Example output:
text
YOU ARE BAD AT 2D PLATFORMERSSKILL ISSUEJUST JUMPOMEGALULThe adapter also learned several stream-specific conditional chat jokes:
These reactions are intended to be topic-dependent rather than inserted into every response.
The source audio was automatically transcribed and was not fully speaker-diarized. Transcript text can therefore occasionally contain speech from someone other than the streamer.
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig base_id = "Qwen/Qwen3-8B"adapter_id = "bob24uda/DuogDuog-AI-Uncensored" quantization = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_use_double_quant=True, bnb_4bit_compute_dtype=torch.bfloat16,) tokenizer = AutoTokenizer.from_pretrained(adapter_id)base = AutoModelForCausalLM.from_pretrained( base_id, quantization_config=quantization, device_map="auto", torch_dtype=torch.bfloat16,)model = PeftModel.from_pretrained(base, adapter_id) messages = [ { "role": "system", "content": ( "You are Twitch chat. React to the stream transcript with several short, " "authentic Twitch chat messages. Output only the messages, one per line, " "without usernames." ), }, { "role": "user", "content": "Stream transcript:\nChat, I am definitely not bald.", },] inputs = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, enable_thinking=False, return_tensors="pt",).to(model.device) with torch.inference_mode(): output = model.generate( inputs, max_new_tokens=120, do_sample=True, temperature=1.0, top_p=0.95, top_k=60, repetition_penalty=1.1, ) print(tokenizer.decode(output[0, inputs.shape[-1]:], skip_special_tokens=True))Sampling is intentional: identical transcripts can produce different chat reactions.
bash
git clone https://huggingface.co/bob24uda/DuogDuog-AI-Uncensoredcd DuogDuog-AI-Uncensoredpip install -r requirements.txtpython run_model.pyOr provide one transcript directly:
bash
python run_model.py "I am so good at 2D platformers, chat."The adapter is distributed under Apache-2.0, consistent with the Qwen3-8B base model. Users are responsible for following the base model license, Twitch’s terms, applicable privacy rules, and any rights associated with source content.
YOU ARE BAD AT 2D PLATFORMERSSKILL ISSUEJUST JUMPOMEGALULgit clone https://huggingface.co/bob24uda/DuogDuog-AI-Uncensoredcd DuogDuog-AI-Uncensoredpip install -r requirements.txtpython run_model.pyimport torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig base_id = "Qwen/Qwen3-8B"adapter_id = "bob24uda/DuogDuog-AI-Uncensored" quantization = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_use_double_quant=True, bnb_4bit_compute_dtype=torch.bfloat16,) tokenizer = AutoTokenizer.from_pretrained(adapter_id)base = AutoModelForCausalLM.from_pretrained( base_id, quantization_config=quantization, device_map="auto", torch_dtype=torch.bfloat16,)model = PeftModel.from_pretrained(base, adapter_id) messages = [ { "role": "system", "content": ( "You are Twitch chat. React to the stream transcript with several short, " "authentic Twitch chat messages. Output only the messages, one per line, " "without usernames." ), }, { "role": "user", "content": "Stream transcript:\nChat, I am definitely not bald.", },] inputs = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, enable_thinking=False, return_tensors="pt",).to(model.device) with torch.inference_mode(): output = model.generate( inputs, max_new_tokens=120, do_sample=True, temperature=1.0, top_p=0.95, top_k=60, repetition_penalty=1.1, ) print(tokenizer.decode(output[0, inputs.shape[-1]:], skip_special_tokens=True))