Update README.md

.gitattributes

@@ -1,47 +1,44 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin 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
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*.tfevents* filter=lfs diff=lfs merge=lfs -text
-*.db* filter=lfs diff=lfs merge=lfs -text
-*.ark* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.gguf* filter=lfs diff=lfs merge=lfs -text
-*.ggml filter=lfs diff=lfs merge=lfs -text
-*.llamafile* filter=lfs diff=lfs merge=lfs -text
-*.pt2 filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,47 +1,105 @@
 ---
-license: Apache License 2.0
+license: apache-2.0
-
+tags:
-#model-type:
+- merge
-##如 gpt、phi、llama、chatglm、baichuan 等
+- mergekit
-#- gpt
+- arcee-ai/Patent-Instruct-7b
-
+- TencentARC/LLaMA-Pro-8B-Instruct
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
 
-SDK下载
+# Patent-Instruct-LLaMA-Pro
-```bash
-#安装ModelScope
-pip install modelscope
-```
-```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('arcee-ai/Patent-Instruct-LLaMA-Pro')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/arcee-ai/Patent-Instruct-LLaMA-Pro.git
-```
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+Patent-Instruct-LLaMA-Pro is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+
+## 🧩 Configuration
+
+```yaml
+  merge_method: passthrough
+  dtype: bfloat16
+  slices:
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b 
+        layer_range:
+          - 0
+          - 4
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 4
+          - 5
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 4
+          - 8
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 9
+          - 10
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 8
+          - 12
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 14
+          - 15
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 12
+          - 16
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 19
+          - 20
+  - sources:
+       - model: arcee-ai/Patent-Instruct-7b
+         layer_range:
+          - 16
+          - 20
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 24
+          - 25
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 20
+          - 24
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 29
+          - 30
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 24
+          - 28
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 34
+          - 35
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 28
+          - 32
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 39
+          - 40
+
+
+
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "TencentARC/LLaMA-Pro-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

mergekit_config.yml

@@ -0,0 +1,87 @@
+
+  merge_method: passthrough
+  dtype: bfloat16
+  slices:
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b 
+        layer_range:
+          - 0
+          - 4
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 4
+          - 5
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 4
+          - 8
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 9
+          - 10
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 8
+          - 12
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 14
+          - 15
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 12
+          - 16
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 19
+          - 20
+  - sources:
+       - model: arcee-ai/Patent-Instruct-7b
+         layer_range:
+          - 16
+          - 20
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 24
+          - 25
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 20
+          - 24
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 29
+          - 30
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 24
+          - 28
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 34
+          - 35
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 28
+          - 32
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 39
+          - 40
+
+
+

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbcf050d35ed8cb768e565a1d9950e14f1fdbb96a962abab01feb7cef3a9a287
+size 1990275992

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd35f778248c9c0fd17ac3da54451c41468ce10df3a8dbeb14825e524ff59ec
+size 1990284304

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d935b4a2c45f5d0c0478f44f0e60220f43ba91f0cf8d28351874cc562b1aa231
+size 1990284296

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3235ded8595246b452c99e9ff904f81a44ab65f91fb77a749c96ed3a44a79cd2
+size 1990284272

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c35e8f3e821a9ddf9e65ab16a3de28cf496dcb8399714e77f05bbc99ec2ab20
+size 1933652840

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77848cd8e459e4e1eab202d73e69c05eb127df81a46f40d577b66fdd5473173c
+size 1963012240

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceef8a865282991cce36667c1de95c4ebd890d8426cdde5043de108ee31b5a76
+size 1990275992

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57455238e0a7985329ce24194bb8d7de79711afdc19dcd210ccfe1279470d567
+size 1990284304

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571bb477b6c949ea017352f85dcd559d868066adfb6e7829e1bea10da5b8bfc8
+size 876652928

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}