diff --git a/docs/source/content/getting_started.md b/docs/source/content/getting_started.md
index 13952cd5e..67ec8e47b 100644
--- a/docs/source/content/getting_started.md
+++ b/docs/source/content/getting_started.md
@@ -28,4 +28,5 @@ You will need to make sure you accept the agreements for any gated models, but o
 
 * https://huggingface.co/mistralai/Mixtral-8x7B-v0.1
 * https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
+* https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
 * https://huggingface.co/mistralai/Mistral-7B-v0.1
diff --git a/transformer_lens/loading_from_pretrained.py b/transformer_lens/loading_from_pretrained.py
index 0a8d132cc..5b7d1f975 100644
--- a/transformer_lens/loading_from_pretrained.py
+++ b/transformer_lens/loading_from_pretrained.py
@@ -147,6 +147,7 @@
     "stabilityai/stablelm-tuned-alpha-7b",
     "mistralai/Mistral-7B-v0.1",
     "mistralai/Mistral-7B-Instruct-v0.1",
+    "mistralai/Mistral-7B-Instruct-v0.2",
     "mistralai/Mixtral-8x7B-v0.1",
     "mistralai/Mixtral-8x7B-Instruct-v0.1",
     "bigscience/bloom-560m",
@@ -557,6 +558,7 @@
     ],
     "mistralai/Mistral-7B-v0.1": ["mistral-7b"],
     "mistralai/Mistral-7B-Instruct-v0.1": ["mistral-7b-instruct"],
+    "mistralai/Mistral-7B-Instruct-v0.2": ["mistral-7b-instruct-v0.2"],
     "mistralai/Mixtral-8x7B-v0.1": ["mixtral", "mixtral-8x7b"],
     "mistralai/Mixtral-8x7B-Instruct-v0.1": [
         "mixtral-instruct",
@@ -939,7 +941,7 @@ def convert_hf_model_config(model_name: str, **kwargs):
             "act_fn": "silu",
             "normalization_type": "RMS",
             "positional_embedding_type": "rotary",
-            "window_size": 4096,
+            "window_size": hf_config.sliding_window,  # This will be 4096 on v0.1, None on later models as none was used
             "attn_types": ["local"] * 32,
             "eps": 1e-05,
             "n_key_value_heads": 8,