Upload folder using huggingface_hub

README.md

@@ -0,0 +1,70 @@
+---
+base_model:
+- MLP-KTLim/llama-3-Korean-Bllossom-8B
+- MLP-KTLim/llama-3-Korean-Bllossom-8B
+- MLP-KTLim/llama-3-Korean-Bllossom-8B
+- MLP-KTLim/llama-3-Korean-Bllossom-8B
+- MLP-KTLim/llama-3-Korean-Bllossom-8B
+tags:
+- merge
+- mergekit
+- lazymergekit
+- MLP-KTLim/llama-3-Korean-Bllossom-8B
+---
+
+# Llama-3-Kor-Bllossom-12B
+
+Llama-3-Kor-Bllossom-12B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)
+* [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)
+* [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)
+* [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)
+* [MLP-KTLim/llama-3-Korean-Bllossom-8B](https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+      layer_range: [0,9]
+  - sources:
+    - model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+      layer_range: [5,14]
+  - sources:
+    - model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+      layer_range: [10,19]
+  - sources:
+    - model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+      layer_range: [15,24]
+  - sources:
+    - model: MLP-KTLim/llama-3-Korean-Bllossom-8B
+      layer_range: [18,32]
+merge_method: passthrough
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "dkpark/Llama-3-Kor-Bllossom-12B"
+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 sha256:9209a70776dbbf598982e87f617e926f5f9d0a597891096b53bd9fb3ff542b3b
+size 4953594688

model-2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2554851b981cc9d5380300af84ac0984f5396f49b45817d9ccfd98610dc509e0
+size 4915924488

model-3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c7d25d511aceb3a054e25381ab85d5626377bcd8594b2a7891f9452a02ee43
+size 4999811024

model-4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c464eff220afb8704e04046332c7a330d5c76d5e2ab376fcfaabd3596059136d
+size 4915907856

model-5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a1d55f1a0e0d31bed787a4749a4a970cd65a335748367e53166ee64e41b34e
+size 4127369168