Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- athirdpath/Orca-2-13b-Alpaca-Uncensored
+- rombodawg/LosslessMegaCoder-llama2-13b-mini
+base_model:
+- athirdpath/Orca-2-13b-Alpaca-Uncensored
+- rombodawg/LosslessMegaCoder-llama2-13b-mini
+---
+
+# AlpacaCoder-OrcaLlamaFusion-13b
+
+AlpacaCoder-OrcaLlamaFusion-13b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [athirdpath/Orca-2-13b-Alpaca-Uncensored](https://huggingface.co/athirdpath/Orca-2-13b-Alpaca-Uncensored)
+* [rombodawg/LosslessMegaCoder-llama2-13b-mini](https://huggingface.co/rombodawg/LosslessMegaCoder-llama2-13b-mini)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: athirdpath/Orca-2-13b-Alpaca-Uncensored
+        layer_range: [0, 40]
+      - model: rombodawg/LosslessMegaCoder-llama2-13b-mini
+        layer_range: [0, 40]
+# or, the equivalent models: syntax:
+# models:
+#   - model: athirdpath/Orca-2-13b-Alpaca-Uncensored
+#   - model: rombodawg/LosslessMegaCoder-llama2-13b-mini
+merge_method: slerp
+base_model: athirdpath/Orca-2-13b-Alpaca-Uncensored
+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 # fallback for rest of tensors
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "ilevytate/AlpacaCoder-OrcaLlamaFusion-13b"
+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"])
+```

model-1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f121591d0f769be589925a0537dc6dce9a0f8ee055ed3461a56cdab116001bf
+size 9948718608