GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
BikoRiko
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
BikoRiko
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
BFloat16 precision. Zero quantization artifacts, zero precision degradation.The original RoPE frequency base was stretched by implementing a dynamic scaling factor calculated perfectly to expand the 32k window to 1.3M without breaking the model's perplexity metrics:
max_position_embeddings: 2400000rope_scaling.type: dynamicrope_scaling.factor: 40.0While the model weights only occupy ~3 GB of memory, processing ultra-long sequences creates a massive KV Cache footprint that scales linearly.
Deployment Note: To test or run inference near the full 1.3M limit, an enterprise GPU cluster node (such as an NVIDIA A100 40GB/80GB or H100) is highly recommended. Ensure PyTorch SDPA is active to optimize memory layout overheads. Awnser me If you need more Ai models with a bigger context ask me becouse i have acces to b200 and more gpus with over 256gb ram so do not be afriad to ask me Thank you have a nice day.
You can run this model natively using the Hugging Face transformers library without needing to pass manual scaling parameters—the 1.3M configuration is fully baked into the config.json file.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "BikoRiko/Qwen2.5-1.5B-1.3M-Stretched" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="cuda", attn_implementation="sdpa" # Essential for large KV-Cache stability) # Put your massive text file here (Up to 1.3 Million Tokens!)prompt = "Your massive book or code content here..." inputs = tokenizer(prompt, return_tensors="pt").to("cuda") with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=50) print(tokenizer.decode(outputs[0], skip_special_tokens=True))import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "BikoRiko/Qwen2.5-1.5B-1.3M-Stretched" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="cuda", attn_implementation="sdpa" # Essential for large KV-Cache stability) # Put your massive text file here (Up to 1.3 Million Tokens!)prompt = "Your massive book or code content here..." inputs = tokenizer(prompt, return_tensors="pt").to("cuda") with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=50) print(tokenizer.decode(outputs[0], skip_special_tokens=True))