Add technical community resources section to README.md

README.md

@@ -1,9 +1,6 @@
----
-license: mit
----
 # Caelis Neural Base 3 (CNB-3): A Foundational Protein Language Model
 
-[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue)](https://huggingface.co/InserloftResearch/CaeisNeuralBase-3)
+[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue)](https://huggingface.co/Inserloft/CaeisNeuralBase-3)
 
 **Caelis Neural Base 3 (CNB-3)** is a ~950-million parameter autoregressive causal language model pre-trained exclusively on dense evolutionary sequence spaces. Engineered to act as a foundational **"Neural Base"** for biotechnology, CNB-3 functions as a versatile, general-purpose backbone for generating, completing, and optimizing functional proteins *de novo*.
 
@@ -36,7 +33,7 @@ You are highly encouraged to use **`CaelisBioTokenizer-2`** as a standard starti
 # Loading CaelisBioTokenizer-2 to train your own models!
 from transformers import AutoTokenizer
 
-tokenizer = AutoTokenizer.from_pretrained("InserloftResearch/CaeisNeuralBase-3")
+tokenizer = AutoTokenizer.from_pretrained("Inserloft/CaeisNeuralBase-3")
 print("Vocabulary size for your new protein model:", len(tokenizer))
 ```
 
@@ -62,7 +59,7 @@ To generate sequences from a custom 25-amino-acid seed:
 import torch
 from transformers import AutoTokenizer, GPT2LMHeadModel
 
-repo_id = "InserloftResearch/CaeisNeuralBase-3"
+repo_id = "Inserloft/CaeisNeuralBase-3"
 
 tokenizer = AutoTokenizer.from_pretrained(repo_id)
 model = GPT2LMHeadModel.from_pretrained(repo_id)
@@ -121,4 +118,14 @@ training_args = TrainingArguments(
 
 1.  **Strict Length Hard-Capping**: Autoregressive decoding may output whitespace tokens due to native formatting. Always remove whitespaces (`"".join(seq.split())`) and slice the sequence dynamically to match your exact structural budget.
 2.  **VRAM Budgeting**: Since ESMFold is resource-intensive, set the chunk size (`esm_folding_model.esm.trunk.set_chunk_size(64)`) to avoid CUDA Out of Memory (OOM) errors on consumer-grade or standard Colab GPUs during verification.
-3.  **The Temperature Sweet-Spot**: Use a temperature of `0.7` to balance biochemical feasibility with sequence novelty. Lower values (`< 0.4`) generate highly conserved structures; higher values (`> 1.1`) increase structural entropy (greater risk of non-folding loop accumulation).
+3.  **The Temperature Sweet-Spot**: Use a temperature of `0.7` to balance biochemical feasibility with sequence novelty. Lower values (`< 0.4`) generate highly conserved structures; higher values (`> 1.1`) increase structural entropy (greater risk of non-folding loop accumulation).
+
+---
+
+## 📚 Resources & Community Support
+
+To facilitate the adoption and specialized fine-tuning of **Caelis Neural Base 3**, we provide the following interactive resources and endpoints:
+
+*   **[Interactive Google Colab Notebook]**: Complete pipeline to generate custom sequences, fold structures local in GPU using ESMFold, analyze residue distributions, and export PDB structures.
+*   **[Official Model Hub](https://huggingface.co/Inserloft/CaeisNeuralBase-3)**: Access the base model weights, standard configuration files, and community discussions.
+*   **[Developer & Research Center](https://research.inserloft.com)**: Official research workspace and support for production-grade biopolymeric applications.