Upload 36 files

.gitattributes

@@ -34,3 +34,4 @@ 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_ax650 filter=lfs diff=lfs merge=lfs -text

main_ax650

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870254b83b53d8f1909a03d2e73b0049fd5541e848579fc530888d07c28a48a2
+size 989368

post_config.json

@@ -0,0 +1,14 @@
+{
+    "enable_temperature" : false,
+    "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" : 1
+}

qwen2.5-0.5b-gptq-int8-ctx-ax630c/model.embed_tokens.weight.bfloat16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e96b0df6d274768cbb7e72404011853d23349999b658dc2f4dfb3c431ea223f
+size 272269312

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l0_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c377bebed44a395db6b0d506d8b31f3a5360c32b969707a38eb67d8657459d
+size 20304815

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l10_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f229d326d98a67fcd0e06fd626eee6982fac4c11fe497f78358ed8bb9f54f20b
+size 20303607

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l11_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:358a9714218158916f6c75888d50ec00a1ba79123711ae02b742825b08ca48f8
+size 20303935

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l12_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b7bc199cabfb2220b41ab029b04afc45fe648d9bcda705f8d1c7824437ec4b
+size 20304519

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l13_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2acb800c135a73da4839033b144d5f2d1390735db7239619c9b50ade97720a6
+size 20304231

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l14_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53308333e9d7da489babe6a477609f2d5c3266bc61c3eeea0ff7833502435288
+size 20303279

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l15_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04ba2aede7386c1416fe2048d86d37178b8c055677ec2e4ae268b52f3fda1ca
+size 20303407

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l16_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:babf6eb5a6d0d00bf45ef2568907894ef29a83951b5879db25e63e272c02afaf
+size 20304919

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l17_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae2ec8552c79007ddf594ecbae6b0c467a2761c1d3a7e1d1ed24dc41863b66a
+size 20304103

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l18_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c6250eecda26c7939e53f0859dc8102606e7d59199d8932d093d09d2773553
+size 20304727

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l19_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd087701ddd7ec1295b8de44b7b4b5cff175d097ef333000e66c32605e7b735
+size 20303319

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l1_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:184ed6a04383d297f67181e487933f3222f76485bd3841f8bcc6f790bca73f95
+size 20303695

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l20_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79acbb118c82c021650dbd8f355ddded2a6d96b9e245ac8d1c24607aacca69c4
+size 20304223

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l21_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7793790895e3bd068a2281b0ccb20d3259ba146e29d5a237abead475082f93
+size 20302911

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l22_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1916fbdce339603cec36742c3e3aa0b62dd77a5b2433774d1cb86ad2900fe1f
+size 20304399

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l23_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff2ea8ebc3f1d0b07d0ec514d80d1a4ea5138e5b0da6109700c437c13647b08
+size 20304479

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l2_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8792126c260b11fb09a283044b9482dfa2e47df7a8ef9e2648698443eeb503
+size 20304087

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l3_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bef007cf245fe101dcef2d84c83aa224fe4f325a7264799f10f2386f91c997
+size 20304023

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l4_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f089c322eed7bd1d2943f615359d9757eb3a9abe7e89509787e076c70ae4d0e
+size 20304071

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l5_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c70abb7daba97dab883b2e26cfe6f89cea50b004cae0ea6e4087295eb0a1ba0
+size 20304191

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l6_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85e521e0d03909fa88971cfca3a92de47a8d8d4c6398958e9c53e38ef864b34
+size 20304367

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l7_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c89120b2d1935e47643bbe832869ec58059be83316436e7004b42ea475c9f3
+size 20304543

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l8_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9bc3cb0ef4dfbd376750451107022119aa91c56070b78157e0b7ed40fa1aed
+size 20304303

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l9_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c40f94bbbbd59e87cfa7220df1067d2d641fe6491489b45fd2562e79082cba
+size 20303583

qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_post.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5265a2d1f3feed0ad4530a050c48ebad76711d1f1f6752e32d9d171b401c933
+size 139940316

qwen2.5_tokenizer/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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,
+  "add_bos_token": false
+}

qwen2.5_tokenizer_uid.py

@@ -0,0 +1,199 @@
+from transformers import AutoTokenizer, PreTrainedTokenizerFast
+from http.server import HTTPServer, BaseHTTPRequestHandler
+import json
+import argparse
+import uuid
+
+# 全局字典：存储 uid 到 Tokenizer_Http 实例的映射
+tokenizers = {}
+
+class Tokenizer_Http():
+    def __init__(self):
+        model_id = "qwen2.5_tokenizer"
+        self.tokenizer = AutoTokenizer.from_pretrained(model_id)
+        self.messages = [
+            {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+        ]
+        self.token_ids = []
+        
+        self.token_ids_cache = []
+
+    def encode(self, prompt, last_reply=None):
+        if last_reply is not None:
+            self.messages.append({"role": "assistant", "content": last_reply})
+            text = self.tokenizer.apply_chat_template(
+                self.messages,
+                tokenize=False,
+                add_generation_prompt=True
+            )
+            # print("生成的文本:\n============\n", text, "============\n")
+            self.token_ids = self.tokenizer.encode(text)[:-3]
+        self.messages.append({"role": "user", "content": prompt})
+        
+        text = self.tokenizer.apply_chat_template(
+            self.messages,
+            tokenize=False,
+            add_generation_prompt=True
+        )
+        print("生成的文本:\n============\n", text, "============\n")
+        token_ids = self.tokenizer.encode(text)
+        # 找出新增部分
+        diff = token_ids[len(self.token_ids):]
+        self.token_ids = token_ids
+        print(self.decode(diff))
+        return token_ids, diff
+
+    def decode(self, token_ids):
+        self.token_ids_cache += token_ids
+        text = self.tokenizer.decode(self.token_ids_cache)
+        if "\ufffd" in text:
+            print("text 中包含非法字符")
+            return ""
+        else:
+            self.token_ids_cache.clear()
+            return text
+        
+
+    @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
+    
+    def reset(self, system_prompt="You are Qwen, created by Alibaba Cloud. You are a helpful assistant."):
+        self.messages = [
+            {"role": "system", "content": system_prompt},
+        ]
+        text = self.tokenizer.apply_chat_template(
+            self.messages,
+            tokenize=False,
+            add_generation_prompt=True
+        )
+        token_ids = self.tokenizer.encode(text)[:-3]
+        self.token_ids = token_ids
+        print(self.decode(token_ids))
+        return token_ids
+        
+
+class Request(BaseHTTPRequestHandler):
+    timeout = 5
+    server_version = 'Apache'
+
+    def do_GET(self):
+        print("GET 请求路径:", self.path)
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.end_headers()
+
+        # 新增接口：获取 uid
+        if '/get_uid' in self.path:
+            new_uid = str(uuid.uuid4())
+            print("新 uid:", new_uid)
+            # 为该 uid 创建一个新的 Tokenizer_Http 实例
+            tokenizers[new_uid] = Tokenizer_Http()
+            msg = json.dumps({'uid': new_uid})
+        elif '/bos_id' in self.path:
+            # 获取 uid 参数（例如 ?uid=xxx）
+            uid = self.get_query_param("uid")
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                bos_id = instance.bos_id
+                msg = json.dumps({'bos_id': bos_id if bos_id is not None else -1})
+        elif '/eos_id' in self.path:
+            uid = self.get_query_param("uid")
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                eos_id = instance.eos_id
+                msg = json.dumps({'eos_id': eos_id if eos_id is not None else -1})
+        else:
+            msg = json.dumps({'error': 'Invalid GET endpoint'})
+
+        print("响应消息:", msg)
+        self.wfile.write(msg.encode())
+
+    def do_POST(self):
+        content_length = int(self.headers.get('content-length', 0))
+        data = self.rfile.read(content_length).decode()
+        print("POST 请求路径:", self.path)
+        print("接收到的数据:", data)
+        req = json.loads(data)
+
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.end_headers()
+
+        if '/encode' in self.path:
+            # 请求数据中必须包含 uid, text, 和可选的 last_reply
+            uid = req.get('uid')
+            prompt = req.get('text')
+            last_reply = req.get('last_reply')
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                token_ids, diff = instance.encode(prompt, last_reply)
+                msg = json.dumps({'token_ids': token_ids, 'diff': diff})
+        elif '/decode' in self.path:
+            uid = req.get('uid')
+            token_ids = req.get('token_ids')
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                text = instance.decode(token_ids)
+                msg = json.dumps({'text': text})
+        elif '/reset' in self.path:
+            uid = req.get("uid")
+            system_prompt = req.get("system_prompt")
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                if system_prompt is not None:
+                    print("system_prompt:", system_prompt)
+                    token_ids = instance.reset(system_prompt)
+                    msg = json.dumps({'token_ids': token_ids})
+                else:
+                    token_ids = instance.reset()
+                    msg = json.dumps({'token_ids': token_ids})
+        else:
+            msg = json.dumps({'error': 'Invalid POST endpoint'})
+
+        print("响应消息:", msg)
+        self.wfile.write(msg.encode())
+
+    def get_query_param(self, key):
+        """
+        辅助函数：从 GET 请求的 URL 中获取查询参数的值
+        例如：/bos_id?uid=xxx
+        """
+        from urllib.parse import urlparse, parse_qs
+        query = urlparse(self.path).query
+        params = parse_qs(query)
+        values = params.get(key)
+        return values[0] if values else None
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--host', type=str, default='0.0.0.0')
+    parser.add_argument('--port', type=int, default=12345)
+    args = parser.parse_args()
+
+    host = (args.host, args.port)
+    print('Server running at http://%s:%s' % host)
+    server = HTTPServer(host, Request)
+    server.serve_forever()

run_qwen2.5_0.5b_gptq_int8_ctx_ax630c.sh

@@ -0,0 +1,14 @@
+./main_ax650 \
+--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
+--template_filename_axmodel "qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 24 \
+--tokenizer_type 2 \
+--url_tokenizer_model "http://127.0.0.1:12345" \
+--filename_post_axmodel "qwen2.5-0.5b-gptq-int8-ctx-ax630c/qwen2_post.axmodel" \
+--filename_tokens_embed "qwen2.5-0.5b-gptq-int8-ctx-ax630c/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 151936 \
+--tokens_embed_size 896 \
+--use_mmap_load_embed 0 \
+--live_print 1
+
+# --kvcache_path /home/axera/ax-llm/build/kvcache_yuanqi \

run_qwen2.5_0.5b_gptq_int8_ctx_ax650.sh

@@ -0,0 +1,14 @@
+./main_ax650 \
+--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
+--template_filename_axmodel "qwen2.5-0.5b-gptq-int8-ctx-ax650/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 24 \
+--tokenizer_type 2 \
+--url_tokenizer_model "http://127.0.0.1:12345" \
+--filename_post_axmodel "qwen2.5-0.5b-gptq-int8-ctx-ax650/qwen2_post.axmodel" \
+--filename_tokens_embed "qwen2.5-0.5b-gptq-int8-ctx-ax650/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 151936 \
+--tokens_embed_size 896 \
+--use_mmap_load_embed 0 \
+--live_print 1
+
+# --kvcache_path /home/axera/ax-llm/build/kvcache_yuanqi \