Upload 11 files

.gitattributes

@@ -34,3 +34,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.axmodel filter=lfs diff=lfs merge=lfs -text
+main_axcl_aarch64 filter=lfs diff=lfs merge=lfs -text
+main_axcl_x86 filter=lfs diff=lfs merge=lfs -text
+main_prefill filter=lfs diff=lfs merge=lfs -text

main_axcl_aarch64

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb111fc00c54abb6142a8f44df087bf104c8150a1cefa6be55c6b174b932c4ec
+size 999008

main_axcl_x86

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cba0be8df523e351789fcfa745772423096f52a3b0a760f8d8c9f5b8bb2ec82
+size 1022384

main_prefill

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90026f1e071aef781ccc9bc313db3805749b3e234bf03d578c9f97ae2e60abd2
+size 953544

post_config.json

@@ -0,0 +1,14 @@
+{
+    "enable_temperature" : true,
+    "temperature" : 0.9,
+    
+    "enable_repetition_penalty" : false,
+    "repetition_penalty" : 1.2,
+    "penalty_window" : 20,
+
+    "enable_top_p_sampling" : false,
+    "top_p" : 0.8,
+
+    "enable_top_k_sampling" : true,
+    "top_k" : 10
+}

qwen2.5_tokenizer.py

@@ -0,0 +1,133 @@
+from transformers import AutoTokenizer, PreTrainedTokenizerFast
+from http.server import HTTPServer, BaseHTTPRequestHandler
+import json
+import argparse
+
+
+class Tokenizer_Http():
+
+    def __init__(self):
+        model_id = "qwen2.5_tokenizer"
+        self.tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+    def encode(self, prompt):
+        messages = [
+            {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+            {"role": "user", "content": prompt}
+        ]
+        text = self.tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True
+        )
+        print(text)
+        token_ids = self.tokenizer.encode(text)
+        return token_ids
+
+    def decode(self, token_ids):
+        return self.tokenizer.decode(token_ids)
+
+    @property
+    def bos_id(self):
+        return self.tokenizer.bos_token_id
+
+    @property
+    def eos_id(self):
+        return self.tokenizer.eos_token_id
+    
+    @property
+    def bos_token(self):
+        return self.tokenizer.bos_token
+
+    @property
+    def eos_token(self):
+        return self.tokenizer.eos_token
+
+
+tokenizer = Tokenizer_Http()
+
+print(tokenizer.bos_id, tokenizer.bos_token, tokenizer.eos_id, tokenizer.eos_token)
+print(tokenizer.encode("hello world"))
+
+
+class Request(BaseHTTPRequestHandler):
+    #通过类继承，新定义类
+    timeout = 5
+    server_version = 'Apache'
+
+    def do_GET(self):
+        print(self.path)
+        #在新类中定义get的内容（当客户端向该服务端使用get请求时，本服务端将如下运行）
+        self.send_response(200)
+        self.send_header("type", "get")  #设置响应头，可省略或设置多个
+        self.end_headers()
+
+        if self.path == '/bos_id':
+            bos_id = tokenizer.bos_id
+            # print(bos_id)
+            # to json
+            if bos_id is None:
+                msg = json.dumps({'bos_id': -1})
+            else:
+                msg = json.dumps({'bos_id': bos_id})
+        elif self.path == '/eos_id':
+            eos_id = tokenizer.eos_id
+            if eos_id is None:
+                msg = json.dumps({'eos_id': -1})
+            else:
+                msg = json.dumps({'eos_id': eos_id})
+        else:
+            msg = 'error'
+
+        print(msg)
+        msg = str(msg).encode()  #转为str再转为byte格式
+
+        self.wfile.write(msg)  #将byte格式的信息返回给客户端
+
+    def do_POST(self):
+        #在新类中定义post的内容（当客户端向该服务端使用post请求时，本服务端将如下运行）
+        data = self.rfile.read(int(
+            self.headers['content-length']))  #获取从客户端传入的参数（byte格式）
+        data = data.decode()  #将byte格式转为str格式
+
+        self.send_response(200)
+        self.send_header("type", "post")  #设置响应头，可省略或设置多个
+        self.end_headers()
+
+        if self.path == '/encode':
+            req = json.loads(data)
+            prompt = req['text']
+
+            token_ids = tokenizer.encode(prompt)
+            if token_ids is None:
+                msg = json.dumps({'token_ids': -1})
+            else:
+                msg = json.dumps({'token_ids': token_ids})
+
+        elif self.path == '/decode':
+            req = json.loads(data)
+            token_ids = req['token_ids']
+            text = tokenizer.decode(token_ids)
+            if text is None:
+                msg = json.dumps({'text': ""})
+            else:
+                msg = json.dumps({'text': text})
+        else:
+            msg = 'error'
+        print(msg)
+        msg = str(msg).encode()  #转为str再转为byte格式
+
+        self.wfile.write(msg)  #将byte格式的信息返回给客户端
+
+
+if __name__ == "__main__":
+
+    args = argparse.ArgumentParser()
+    args.add_argument('--host', type=str, default='localhost')
+    args.add_argument('--port', type=int, default=8080)
+    args = args.parse_args()
+
+    host = (args.host, args.port)  #设定地址与端口号，'localhost'等价于'127.0.0.1'
+    print('http://%s:%s' % host)
+    server = HTTPServer(host, Request)  #根据地址端口号和新定义的类，创建服务器实例
+    server.serve_forever()  #开启服务

qwen2.5_tokenizer/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

run_qwen2.5_7b_gptq_int4_ax650.sh

@@ -0,0 +1,14 @@
+./main_prefill \
+--template_filename_axmodel "qwen2.5-7b-gptq-int4-ax650/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 28 \
+--tokenizer_type 2 \
+--filename_tokenizer_model "http://127.0.0.1:12345" \
+--bos 0 --eos 0 \
+--filename_post_axmodel "qwen2.5-7b-gptq-int4-ax650/qwen2_post.axmodel" \
+--filename_tokens_embed "qwen2.5-7b-gptq-int4-ax650/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 152064 \
+--tokens_embed_size 3584 \
+--use_mmap_load_embed 1 \
+--live_print 1 \
+--continue 1 \
+--prompt "$1"

run_qwen2.5_7b_gptq_int4_axcl_aarch64.sh

@@ -0,0 +1,14 @@
+./main_axcl_aarch64 \
+--template_filename_axmodel "qwen2.5-7b-gptq-int4-ax650/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 28 \
+--tokenizer_type 2 \
+--filename_tokenizer_model "http://127.0.0.1:12345" \
+--bos 0 --eos 0 \
+--filename_post_axmodel "qwen2.5-7b-gptq-int4-ax650/qwen2_post.axmodel" \
+--filename_tokens_embed "qwen2.5-7b-gptq-int4-ax650/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 152064 \
+--tokens_embed_size 3584 \
+--use_mmap_load_embed 0 \
+--live_print 1 \
+--continue 1 \
+--prompt "$1"

run_qwen2.5_7b_gptq_int4_axcl_x86.sh

@@ -0,0 +1,14 @@
+./main_axcl_x86 \
+--template_filename_axmodel "qwen2.5-7b-gptq-int4-ax650/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 28 \
+--tokenizer_type 2 \
+--filename_tokenizer_model "http://127.0.0.1:12345" \
+--bos 0 --eos 0 \
+--filename_post_axmodel "qwen2.5-7b-gptq-int4-ax650/qwen2_post.axmodel" \
+--filename_tokens_embed "qwen2.5-7b-gptq-int4-ax650/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 152064 \
+--tokens_embed_size 3584 \
+--use_mmap_load_embed 0 \
+--live_print 1 \
+--continue 1 \
+--prompt "$1"