Upload README.md with huggingface_hub

README.md

@@ -84,7 +84,6 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 tokenizer = AutoTokenizer.from_pretrained("Estwld/Qwen3.5-9B-base-rednote-200K")
 
-# Text generation
 inputs = tokenizer("Your prompt here", return_tensors="pt").to(model.device)
 outputs = model.generate(inputs.input_ids, max_new_tokens=1024)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
@@ -95,8 +94,6 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 - **Inference (bf16)**: ~18 GB VRAM (single GPU)
 - **Fine-tuning (full)**: ~80+ GB VRAM per GPU (with full parameters, optimizer states, and activations at 200K context)
 
-For long-context inference at 200K tokens, ensure sufficient KV-cache memory. Using Flash Attention helps reduce the memory footprint significantly.
-
 ## Limitations
 
 - This is a research checkpoint at iteration 309. Further training steps may improve performance.