Update README.md

README.md

@@ -49,12 +49,12 @@ import torch
 
 # Load model
 model = AutoModelForCausalLM.from_pretrained(
-    "ereniko/LaaLM-exp-v1",
+    "LaaLM/LaaLM-exp-v1",
     torch_dtype=torch.bfloat16,
     device_map="auto"
 )
 tokenizer = AutoTokenizer.from_pretrained(
-    "ereniko/LaaLM-exp-v1",
+    "LaaLM/LaaLM-exp-v1",
     fix_mistral_regex=True  # Important for proper tokenization
 )
 model.eval()
@@ -149,7 +149,7 @@ print(run_command("ls"))                     # backup.txt
 
 GGUF quantizations are available for CPU inference and lower memory usage:
 
-**[LaaLM-exp-v1-GGUF](https://huggingface.co/ereniko/LaaLM-exp-v1-GGUF)**
+**[LaaLM-exp-v1-GGUF](https://huggingface.co/LaaLM/LaaLM-exp-v1-GGUF)**
 
 Includes Q2_K through fp16 quantizations (1.27GB - 6.18GB) for use with:
 - llama.cpp
@@ -254,7 +254,7 @@ Each test consists of:
 
 Part of the LaaLM (Linux as a Language Model) project:
 
-- [**LaaLM-v1**](https://huggingface.co/ereniko/LaaLM-v1) - State-based approach with external filesystem tracking (T5-base, 80k examples)
+- [**LaaLM-v1**](https://huggingface.co/LaaLM/LaaLM-v1) - State-based approach with external filesystem tracking (T5-base, 80k examples)
 - **LaaLM-exp-v1** - Conversation-based approach with internal state tracking (Qwen 3B, 800k messages) (current)
 - **LaaLM-v2** - Planned with bash scripting, pipes, and expanded command set