初始化项目，由ModelHub XC社区提供模型

Model: shanchen/llama3-8B-slerp-med-chinese
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- winninghealth/WiNGPT2-Llama-3-8B-Base
+- johnsnowlabs/JSL-MedLlama-3-8B-v1.0
+base_model:
+- winninghealth/WiNGPT2-Llama-3-8B-Base
+- johnsnowlabs/JSL-MedLlama-3-8B-v1.0
+license: llama3
+language:
+- zh
+- en
+- fr
+---
+
+# llama3-8B-slerp-med-chinese
+
+llama3-8B-slerp-med-chinese is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [winninghealth/WiNGPT2-Llama-3-8B-Base](https://huggingface.co/winninghealth/WiNGPT2-Llama-3-8B-Base)
+* [johnsnowlabs/JSL-MedLlama-3-8B-v1.0](https://huggingface.co/johnsnowlabs/JSL-MedLlama-3-8B-v1.0)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: winninghealth/WiNGPT2-Llama-3-8B-Base
+        layer_range: [0,32]
+      - model: johnsnowlabs/JSL-MedLlama-3-8B-v1.0
+        layer_range: [0,32]
+merge_method: slerp
+base_model: winninghealth/WiNGPT2-Llama-3-8B-Base
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.5, 0.5, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.5, 0.5, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "shanchen/llama3-8B-slerp-med-chinese"
+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"])
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "winninghealth/WiNGPT2-Llama-3-8B-Base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: winninghealth/WiNGPT2-Llama-3-8B-Base
+        layer_range: [0,32]
+      - model: johnsnowlabs/JSL-MedLlama-3-8B-v1.0
+        layer_range: [0,32]
+merge_method: slerp
+base_model: winninghealth/WiNGPT2-Llama-3-8B-Base
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.5, 0.5, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.5, 0.5, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f980b07bd3e2d4f45d1bbfc12122cc80a93ab1e9ac6aa3b9a3e23f16897d96f8
+size 9953405736

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f5fb5d7491c788684e2b69a0d085fa275c07c4334e1a50c7bed458a39427b19
+size 6107150624

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}