GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Ninitje
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Ninitje
Model Tree
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Input Modalities
Output Modalities
Supported Functionality
deepseek-ai/DeepSeek-R1-Distill-Qwen-14Bpython
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel base_model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"adapter_id = "Ninitje/InvariantMind-v1-14B" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_quant_type="nf4") tokenizer = AutoTokenizer.from_pretrained(base_model_name)base_model = AutoModelForCausalLM.from_pretrained( base_model_name, quantization_config=bnb_config, device_map="auto")model = PeftModel.from_pretrained(base_model, adapter_id) prompt = "Analyze the Kuramoto order parameter transition and explain how finite-size scaling impacts critical coupling Kc."messages = [{"role": "user", "content": prompt}]inputs = tokenizer(tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True), return_tensors="pt").to("cuda") with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel base_model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"adapter_id = "Ninitje/InvariantMind-v1-14B" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_quant_type="nf4") tokenizer = AutoTokenizer.from_pretrained(base_model_name)base_model = AutoModelForCausalLM.from_pretrained( base_model_name, quantization_config=bnb_config, device_map="auto")model = PeftModel.from_pretrained(base_model, adapter_id) prompt = "Analyze the Kuramoto order parameter transition and explain how finite-size scaling impacts critical coupling Kc."messages = [{"role": "user", "content": prompt}]inputs = tokenizer(tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True), return_tensors="pt").to("cuda") with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))