Upload folder using huggingface_hub

README.md

@@ -0,0 +1,82 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
+- Orenguteng/Lexi-Llama-3-8B-Uncensored
+- NousResearch/Meta-Llama-3-8B
+- NousResearch/Meta-Llama-3-8B-Instruct
+base_model:
+- hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
+- Orenguteng/Lexi-Llama-3-8B-Uncensored
+- NousResearch/Meta-Llama-3-8B
+- NousResearch/Meta-Llama-3-8B-Instruct
+---
+
+# Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.2A
+
+Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.2A is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode)
+* [Orenguteng/Lexi-Llama-3-8B-Uncensored](https://huggingface.co/Orenguteng/Lexi-Llama-3-8B-Uncensored)
+* [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B)
+* [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
+        parameters:
+          weight: 1
+        layer_range: [0, 40]
+      - model: Orenguteng/Lexi-Llama-3-8B-Uncensored
+        parameters:
+          weight: 1
+        layer_range: [0, 40]
+      - model: NousResearch/Meta-Llama-3-8B
+        parameters:
+          weight: 0.3
+        layer_range: [0, 40]
+      - model: NousResearch/Meta-Llama-3-8B-Instruct
+        parameters:
+          weight: 0.7
+        layer_range: [0, 40]
+merge_method: task_arithmetic
+base_model: NousResearch/Meta-Llama-3-8B-Instruct
+parameters:
+  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
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Nhoodie/Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.2A"
+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"])
+```