Update README.md

README.md

@@ -10,9 +10,9 @@ tags:
   - research
 ---
 
-# DeepBrainz-R1.7-PE-16K
+# DeepBrainz-R1-2B-16K
 
-**DeepBrainz-R1.7-PE-16K** is a compact, long-context reasoning model in the
+**DeepBrainz-R1-2B-16K** is a compact, long-context reasoning model in the
 DeepBrainz-R series, designed for structured problem-solving, analysis,
 and enterprise research workflows.
 
@@ -47,7 +47,7 @@ Not intended as a general-purpose chat replacement for large frontier models.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "DeepBrainz/DeepBrainz-R1.7-PE-16K"
+model_id = "DeepBrainz/DeepBrainz-R1-2B-16K"
 
 tok = AutoTokenizer.from_pretrained(model_id)
 mdl = AutoModelForCausalLM.from_pretrained(model_id)
@@ -58,6 +58,7 @@ inputs = tok(prompt, return_tensors="pt")
 out = mdl.generate(
     **inputs,
     max_new_tokens=256,
+    do_sample=True,
     temperature=0.6,
     top_p=0.95,
 )
@@ -79,7 +80,7 @@ abstracted in this public release.
 ## Limitations
 
 Performance depends on task complexity and inference configuration.
-Larger models may outperform R1.7-PE-16K on extremely complex tasks.
+Larger models may outperform R1-2B-16K on extremely complex tasks.
 
 ---