Cards: capless examples (cap baked into generation_config); drop vLLM note + research note

README.md

@@ -35,16 +35,12 @@ repo = "manueldeprada/littlelearner-5b-bounded-base"
 tok = AutoTokenizer.from_pretrained(repo)
 model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="cuda")
 ids = tok("The sum of 2 and 3 is", return_tensors="pt").to(model.device)
-print(tok.decode(model.generate(**ids, max_new_tokens=64)[0], skip_special_tokens=True))
+print(tok.decode(model.generate(**ids)[0], skip_special_tokens=True))
 ```
 
 ```python
 # vLLM
-from vllm import LLM, SamplingParams
+from vllm import LLM
 llm = LLM("manueldeprada/littlelearner-5b-bounded-base")
-print(llm.generate(["The sum of 2 and 3 is"], SamplingParams(max_tokens=64))[0].outputs[0].text)
+print(llm.generate(["The sum of 2 and 3 is"])[0].outputs[0].text)
 ```
-
-> **vLLM note:** vLLM JIT-compiles CUDA kernels, so it needs a CUDA toolkit (`nvcc`) on PATH. On an HPC cluster, `module load cuda/13.x cudnn/9.x` (match your torch CUDA build). On a box with no toolkit, pass `LLM(repo, enforce_eager=True)`. Verified on vLLM 0.15 and 0.23 (and transformers ≥ 4.51).
-
-> Research artifact. The **bounded** models carry an intentional K–5 knowledge boundary (they cannot model above-grade-5 material). Base models are **not** instruction-tuned.