Update README.md

README.md

@@ -1,29 +1,39 @@
 ---
 base_model:
-- mlabonne/BigLlama-3.1-681B-Instruct
+- meta-llama/Meta-Llama-3.1-681B-Instruct
 library_name: transformers
 tags:
 - mergekit
 - merge
-
 ---
-# BigLlama-3.1-1T-Instruct
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+# 🦙✨ BigLlama-3.1-1T-Instruct
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/ywomdgvQYP9cpr-PH1nf7.png)
+
+<center>🦙⛰️ <i><a href="https://huggingface.co/mlabonne/BigLlama-3.1-681B-Instruct">mlabonne/BigLlama-3.1-681B-Instruct</a></i></center>
+
+This is an experimental self-merge using [meta-llama/Meta-Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct) and created with [mergekit](https://github.com/cg123/mergekit).
+
+This is the direct successor of [Meta-Llama-3-120B-Instruct](https://huggingface.co/mlabonne/Meta-Llama-3-120B-Instruct), a self-merge of Llama 3 70B that produced a decent 120B model for tasks like creative writing.
+
+I tweaked the range of duplicated layers to hopefully make a sensible model. Use it at your own risk!
+
+## 🔍 Applications
+
+I recommend using this model for creative writing with the Llama 3 chat template.
 
-## Merge Details
-### Merge Method
+## ⚡ Quantization
 
-This model was merged using the passthrough merge method.
+TBD.
 
-### Models Merged
+## 🏆 Evaluation
 
-The following models were included in the merge:
-* [mlabonne/BigLlama-3.1-681B-Instruct](https://huggingface.co/mlabonne/BigLlama-3.1-681B-Instruct)
+TBD.
 
-### Configuration
+## 🧩 Configuration
 
-The following YAML configuration was used to produce this model:
+This model was merged using the passthrough merge method. The following YAML configuration was used to produce this model:
 
 ```yaml
 slices:
@@ -38,5 +48,33 @@ slices:
     model: mlabonne/BigLlama-3.1-681B-Instruct
 merge_method: passthrough
 dtype: bfloat16
-
 ```
+
+Here is the code I've used to generate the config and calculate the number of layers/parameters after passthrough:
+
+```python
+def generate_yaml_config(range_size, total_layers, nb_parameters):
+    new_size = total_layers + total_layers - range_size
+    new_param = (nb_parameters / total_layers) * new_size
+    print(f"New size = {new_size} layers")
+    print(f"New parameters = {new_param:.2f}B")
+    yaml_str = "slices:\n"
+
+    for i in range(0, round(total_layers - range_size + 1), range_size // 2):
+        start = i
+        end = min(start + range_size, total_layers)
+        yaml_str += f"- sources:\n"
+        yaml_str += f"  - layer_range: [{start}, {end}]\n"
+        yaml_str += f"    model: meta-llama/Meta-Llama-3.1-405B-Instruct\n"
+
+    yaml_str += "merge_method: passthrough\n"
+    yaml_str += "dtype: bfloat16\n"
+
+    print(yaml_str)
+
+    return new_size, new_param
+
+# Example usage
+new_size, new_param = generate_yaml_config(42, 126, 410)
+new_size, new_param = generate_yaml_config(105, new_size, new_param)
+```