Upload folder using huggingface_hub

README.md

@@ -1,31 +1,27 @@
 ---
-{}
+tags:
+- merge
+- mergekit
+- lazymergekit
+- psmathur/orca_mini_v3_13b
+- WizardLM/WizardLM-13B-V1.2
+- garage-bAInd/Platypus2-13B
+base_model:
+- psmathur/orca_mini_v3_13b
+- WizardLM/WizardLM-13B-V1.2
+- garage-bAInd/Platypus2-13B
 ---
----
-    license: 
-    base_model:
-      - psmathur/orca_mini_v3_13b
-      - WizardLM/WizardLM-13B-V1.2
-      - garage-bAInd/Platypus2-13B
-    tags:
-    - merge
-    - mergekit
-    - lazymergekit
-    - psmathur/orca_mini_v3_13b
-    - WizardLM/WizardLM-13B-V1.2
-    - garage-bAInd/Platypus2-13B
-    ---
 
-    # holaa
+# holaa
 
-    holaa is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-    * [psmathur/orca_mini_v3_13b](https://huggingface.co/psmathur/orca_mini_v3_13b)
-    * [WizardLM/WizardLM-13B-V1.2](https://huggingface.co/WizardLM/WizardLM-13B-V1.2)
-    * [garage-bAInd/Platypus2-13B](https://huggingface.co/garage-bAInd/Platypus2-13B)
+holaa is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [psmathur/orca_mini_v3_13b](https://huggingface.co/psmathur/orca_mini_v3_13b)
+* [WizardLM/WizardLM-13B-V1.2](https://huggingface.co/WizardLM/WizardLM-13B-V1.2)
+* [garage-bAInd/Platypus2-13B](https://huggingface.co/garage-bAInd/Platypus2-13B)
 
-    ## 🧩 Configuration
+## 🧩 Configuration
 
-    ```yamlmodels:
+```yamlmodels:
   - model: psmathur/orca_mini_v3_13b
     parameters:
       weight: 1.0
@@ -38,27 +34,27 @@
 merge_method: linear
 dtype: float16```
 
-    ## 💻 Usage
+## 💻 Usage
 
-    ```python
-    !pip install -qU transformers accelerate
+```python
+!pip install -qU transformers accelerate
 
-    from transformers import AutoTokenizer
-    import transformers
-    import torch
+from transformers import AutoTokenizer
+import transformers
+import torch
 
-    model = "mgv99/holaa"
-    messages = [{"role": "user", "content": "What is a large language model?"}]
+model = "mgv99/holaa"
+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",
-    )
+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"])
-    ```
+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"])
+```