Upload folder using huggingface_hub

README.md

@@ -1,38 +1,65 @@
----
-license: apache-2.0
-tags:
-- merge
-- mergekit
-- lazymergekit
-- Qwen/Qwen2.5-7B
-- Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
----
-
-# metaBlend_slerp
-
-metaBlend_slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
-* [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B)
-* [Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2](https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2)
-
-## 🧩 Configuration
-
-\```yaml
-
-slices:
-  - sources:
-      - model: Qwen/Qwen2.5-7B
-        layer_range: [0, 10]
-      - model: Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
-        layer_range: [10, -1]
-merge_method: slerp
-base_model: Qwen/Qwen2.5-7B
-parameters:
-  t:
-    - filter: self_attn
-      value: [0, 0.1, 0.4, 0.7, 1]
-    - filter: mlp
-      value: [1, 0.7, 0.4, 0.1, 0]
-    - value: 0.6
-dtype: bfloat16
-    
-\```
+---
+base_model:
+- Qwen/Qwen2.5-7B
+- Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Qwen/Qwen2.5-7B
+- Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
+---
+
+# metaBlend_slerp
+
+metaBlend_slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B)
+* [Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2](https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2)
+
+## 🧩 Configuration
+
+```yaml
+
+slices:
+  - sources:
+      - model: Qwen/Qwen2.5-7B
+        layer_range: [0, 10]
+      - model: Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
+        layer_range: [10, -1]
+merge_method: slerp
+base_model: Qwen/Qwen2.5-7B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.1, 0.4, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.7, 0.4, 0.1, 0]
+    - value: 0.6
+dtype: bfloat16
+    
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "bc-agro/metaBlend_slerp"
+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"])
+```