Update HuggingFace transformers support

README.md

@@ -20,6 +20,7 @@ library_name: transformers
 <img src="assets/EXAONE_Symbol+BI_3d.png", width="300", style="margin: 40 auto;">
 🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗
 <br>✈️ Try on <a href="https://friendli.ai/suite/~/serverless-endpoints/LGAI-EXAONE/EXAONE-4.0-32B/overview">FriendliAI</a>
+<br><br><i>📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide <a href="#quickstart">below</a></i>
 <br>
 
 # EXAONE-4.0-32B-FP8
@@ -50,14 +51,7 @@ For more details, please refer to our [technical report](https://arxiv.org/abs/2
 
 ## Quickstart
 
-You should install the transformers library forked from the original, available in our [PR](https://github.com/huggingface/transformers/pull/39129).
-Once this PR is merged and released, we will update this section. 
-
-You can install the latest version of transformers with support for EXAONE 4.0 by following the command:
-
-```bash
-pip install git+https://github.com/lgai-exaone/transformers@add-exaone4
-```
+You should install the transformers library with version >= `4.54.0`.
 
 ### Non-reasoning mode
 

config.json

@@ -10,6 +10,72 @@
   "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 27392,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
   "max_position_embeddings": 131072,
   "model_type": "exaone4",
   "num_attention_heads": 40,
@@ -38,7 +104,7 @@
   "sliding_window_pattern": "LLLG",
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.54.0.dev0",
+  "transformers_version": "4.54.0",
   "use_cache": true,
   "vocab_size": 102400
 }

generation_config.json

@@ -4,5 +4,5 @@
   "cache_implementation": "hybrid",
   "eos_token_id": 361,
   "pad_token_id": 0,
-  "transformers_version": "4.54.0.dev0"
+  "transformers_version": "4.54.0"
 }