Upload folder using huggingface_hub

README.md

@@ -1,45 +1,64 @@
 ---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- automerger
 base_model:
 - mayacinka/yam-jom-7B
 - CorticalStack/shadow-clown-7B-dare
-library_name: transformers
-tags:
-- mergekit
-- merge
-
 ---
-# merge
-
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-
-## Merge Details
-### Merge Method
 
-This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mayacinka/yam-jom-7B](https://huggingface.co/mayacinka/yam-jom-7B) as a base.
+# YamShadow-7B
 
-### Models Merged
-
-The following models were included in the merge:
+YamShadow-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
+* [mayacinka/yam-jom-7B](https://huggingface.co/mayacinka/yam-jom-7B)
 * [CorticalStack/shadow-clown-7B-dare](https://huggingface.co/CorticalStack/shadow-clown-7B-dare)
 
-### Configuration
-
-The following YAML configuration was used to produce this model:
+## 🧩 Configuration
 
 ```yaml
-
-models:
-- model: mayacinka/yam-jom-7B
-  # No parameters necessary for base model
-- model: CorticalStack/shadow-clown-7B-dare
-  parameters:
-    density: 0.53
-    weight: 0.6
-merge_method: dare_ties
+slices:
+  - sources:
+      - model: mayacinka/yam-jom-7B
+        layer_range: [0, 32]
+      - model: CorticalStack/shadow-clown-7B-dare
+        layer_range: [0, 32]
+merge_method: slerp
 base_model: mayacinka/yam-jom-7B
 parameters:
-int8_mask: true
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
 dtype: bfloat16
 random_seed: 0
-    
-```
+    ```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "automerger/YamShadow-7B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

mergekit_config.yml

@@ -1,15 +1,19 @@
 
-models:
-- model: mayacinka/yam-jom-7B
-  # No parameters necessary for base model
-- model: CorticalStack/shadow-clown-7B-dare
-  parameters:
-    density: 0.53
-    weight: 0.6
-merge_method: dare_ties
+slices:
+  - sources:
+      - model: mayacinka/yam-jom-7B
+        layer_range: [0, 32]
+      - model: CorticalStack/shadow-clown-7B-dare
+        layer_range: [0, 32]
+merge_method: slerp
 base_model: mayacinka/yam-jom-7B
 parameters:
-int8_mask: true
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
 dtype: bfloat16
 random_seed: 0
     

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3bd14717677b19a43bb8ee7a9c329c24e1be367c2130193abac3343114eb3c
+oid sha256:7a1143a331c91175b8668f1e842dbfa8e4fa58a056184cef5d57bb058212b7cf
 size 9825524456

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288d96383b3d6730cf1c90cee51e420813f7e31c0dbf9bb4c791260ccc45ca52
+oid sha256:760fa1fcdab26d6c723e980aec2966440fbacc3d374fe22fd3b8adc292514e01
 size 4657973592