Upload 47 files

.gitattributes

@@ -34,3 +34,7 @@ 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_api_ax650 filter=lfs diff=lfs merge=lfs -text
+main_api_axcl_x86 filter=lfs diff=lfs merge=lfs -text
+main_ax650 filter=lfs diff=lfs merge=lfs -text
+main_axcl_x86 filter=lfs diff=lfs merge=lfs -text

gradio_demo.py

@@ -0,0 +1,127 @@
+import mimetypes
+import os
+import gradio as gr
+import requests
+import json, time
+
+base_url = "http://127.0.0.1:8000"
+
+def upload_image(file_path):
+    if file_path is None:
+        return None
+    # Gradio File component returns a tempfile-like object
+    # file_path = image.name
+    filename = os.path.basename(file_path)
+    # Guess MIME type
+    mime_type, _ = mimetypes.guess_type(filename)
+    mime_type = mime_type or 'application/octet-stream'
+    # Open file in binary mode for upload
+    with open(file_path, 'rb') as f:
+        file_bytes = f.read()
+    # Prepare multipart form data
+    files = {
+        'image': (filename, file_bytes, mime_type)
+    }
+    # Send to upload endpoint
+    resp = requests.post(
+        f'{base_url}/api/upload',
+        files=files
+    )
+    resp.raise_for_status()
+    data = resp.json()
+    return data.get('file_path')
+
+def stop_generation():
+    try:
+        requests.get(f'{base_url}/api/stop')
+    except:
+        pass
+
+def respond(prompt, image:gr.Image, temp, rep_penalty, tp, tk, history=None):
+    if history is None:
+        history = []
+    if not prompt.strip():
+        return history
+    # append empty response to history
+    if  image is None:
+        file_path = None
+    else:
+        file_path = upload_image(image)
+        history.append((f'![]({file_path})', None))
+        relative_path = os.path.relpath(file_path)
+        # html = f"<img src='{relative_path}' style='max-width:300px;'/>"
+        # history.append((html, None))
+        # print(relative_path)
+        
+    
+    history.append((prompt, ""))
+    yield history
+    # stream updates
+    
+    
+    payload = {
+        "prompt": prompt,
+        "temperature": temp,
+        "repetition_penalty": rep_penalty,
+        "top-p": tp,
+        "top-k": tk
+    }
+    if file_path:
+        payload["file_path"] = file_path
+
+    response = requests.post(
+        f'{base_url}/api/generate',
+        json=payload
+    )
+    response.raise_for_status()
+    
+
+    while True:
+        time.sleep(0.01)
+        response = requests.get(
+                f'{base_url}/api/generate_provider'
+            )
+        data = response.json()
+        chunk:str = data.get("response", "") 
+        done = data.get("done", False)
+        if done:
+            break
+        if chunk.strip() == "":
+            continue
+        history[-1] = (prompt, history[-1][1] + chunk)
+        yield history
+       
+    print("end")
+    
+     
+
+
+def chat_interface():
+    with gr.Blocks(theme=gr.themes.Soft(font="Consolas"), fill_width=True) as demo:
+        gr.Markdown("## Chat with LLM\nUpload an image and chat with the model!")
+        with gr.Row():
+            image = gr.Image(label="Upload Image", type="filepath")
+            with gr.Column(scale=3):
+                chatbot = gr.Chatbot(height=600)
+                prompt = gr.Textbox(placeholder="Type your message...", label="Prompt", value="描述一下这张图片")
+                with gr.Row():
+                    btn_chat = gr.Button("Chat", variant="primary")
+                    btn_stop = gr.Button("Stop", variant="stop")
+
+            with gr.Column(scale=1):
+                temperature = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=0.7, label="Temperature")
+                repetition_penalty = gr.Slider(minimum=1.0, maximum=2.0, step=0.01, value=1.0, label="Repetition Penalty")
+                top_p = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=0.9, label="Top-p Sampling")
+                top_k = gr.Slider(minimum=0, maximum=100, step=1, value=40, label="Top-k Sampling")
+
+            btn_stop.click(fn=stop_generation, inputs=None, outputs=None)
+            btn_chat.click(
+                fn=respond,
+                inputs=[prompt, image, temperature, repetition_penalty, top_p, top_k, chatbot],
+                outputs=chatbot
+            )
+
+        demo.launch(server_name="0.0.0.0", server_port=7860)
+
+if __name__ == "__main__":
+    chat_interface()

internvl3_1b_ax650/internvl3_1b_vit.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0603400f56632d7580312bbc6dee7f25c61f43f57bc1e19a63fff20241ca99c6
+size 368057444

internvl3_1b_ax650/model.embed_tokens.weight.bfloat16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cecf2aa3a9d0762e525990561e75f08ab5df970d918f53e1b72dd73c81a6d34
+size 271799808

internvl3_1b_ax650/qwen2_p128_l0_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eead6ae0b49ad5a4c554fb85c345f18bed3104289ea4f612aaeea581aa708576
+size 20071994

internvl3_1b_ax650/qwen2_p128_l10_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9926dd7996dbe34e4fb117aa130d0ba2dd1d63d9b338e02e2d62dd4b62fbba80
+size 20071994

internvl3_1b_ax650/qwen2_p128_l11_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c9f09f97c5cd35fafc260e4e2fb29849fb1006b61b7a5158cdcadbc1688be33
+size 20071994

internvl3_1b_ax650/qwen2_p128_l12_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca530f6bc2c4a9d9656d5368fd547e2e75c76126e8980e6057520be384554aa
+size 20071994

internvl3_1b_ax650/qwen2_p128_l13_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a420ab0e159a13b349338faed80a33c63103dc489da58d3756a743943cfd8bb
+size 20071994

internvl3_1b_ax650/qwen2_p128_l14_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1a05a44e10c3f163cb1b53d955195efe10eea4a034d264391991ebd9b165ae
+size 20071994

internvl3_1b_ax650/qwen2_p128_l15_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa98c1c6645edde2f3917a006915d14fccea19ab89dd4d921cb724fbf421e9c
+size 20071994

internvl3_1b_ax650/qwen2_p128_l16_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7af902e12c1c4164f9f1d176d211568a86c3f218f0ff3acf7f4e46e070fe64b
+size 20071994

internvl3_1b_ax650/qwen2_p128_l17_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b979a366484f19c6cfa19e4fcf67f117612412e356e45533a2488d3634bd4c5d
+size 20071994

internvl3_1b_ax650/qwen2_p128_l18_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6d979c9dc5ee4fde522fcf2eb5b425c31a8f119281f40e424b424e41fb7782
+size 20071994

internvl3_1b_ax650/qwen2_p128_l19_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d8b0463bae2e9c38eaf94c12f3c693df79a2154e36ac156768ed4d6ca7a4cf
+size 20071994

internvl3_1b_ax650/qwen2_p128_l1_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6555c32c31e2ba89cbf4906517d4fee636cfa29145707f7a502af3b5a19933e5
+size 20071994

internvl3_1b_ax650/qwen2_p128_l20_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531c9e292abcd467f6d99fbacfaa7cee1b93450b0da974ca67ff8c47dec3c79a
+size 20071994

internvl3_1b_ax650/qwen2_p128_l21_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4d8b1aba7f6a57d755be7b2340881dd525aeab804ad26e2db7843764e20456
+size 20071994

internvl3_1b_ax650/qwen2_p128_l22_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624fc3ca9319c83252c830a5c97f68e90b4550363c9ff3f6c55f827ea42bca29
+size 20071994

internvl3_1b_ax650/qwen2_p128_l23_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72e3922f62e6b33721aa9b2fef57b720a206265ca2b90d5f886132c62b76b546
+size 20071994

internvl3_1b_ax650/qwen2_p128_l2_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d5e98ed1110457594d77ef379786eb0838b6d9f63b21e18ec67965ec218fd6
+size 20071994

internvl3_1b_ax650/qwen2_p128_l3_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abf7d7beeb56ef269abc2c1c6804e7f740d1a16432a86e8cecca926e29a027a
+size 20071994

internvl3_1b_ax650/qwen2_p128_l4_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2bb08583ab396116d38a39f1b66da3b6b75a72ea87f98e4b326f34c832ec6f3
+size 20071994

internvl3_1b_ax650/qwen2_p128_l5_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664596f8641b49121957e1d740ac668b6245831a39e35327e8f7ee460d906840
+size 20071994

internvl3_1b_ax650/qwen2_p128_l6_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8764ce12a92255d85c0a4cd86d9aaadb3ef14964e2108921d898b757402970b
+size 20071994

internvl3_1b_ax650/qwen2_p128_l7_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c705aed26bc995e361147a0d79fa9cfb7bb735f5903ba551726b38066fef5b2e
+size 20071994

internvl3_1b_ax650/qwen2_p128_l8_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd57814326331fd677adfdd903e585b078bf4a1b13169474029ebed1ea12aeb
+size 20071994

internvl3_1b_ax650/qwen2_p128_l9_together.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11eab50591e174e21d6c45dacc6fc0eb5a8eb543497d2d71f99c2f0a6ffbc133
+size 20071994

internvl3_1b_ax650/qwen2_post.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889f1bee82603ad07d5239fbcfccbea71dda8f5a3188b3ad1799f2f7608fcaff
+size 147705143

internvl3_tokenizer.py

@@ -0,0 +1,186 @@
+from transformers import AutoTokenizer
+from http.server import HTTPServer, BaseHTTPRequestHandler
+import json
+import argparse
+
+
+class Tokenizer_Http():
+
+    def __init__(self):
+
+        path = 'internvl3_tokenizer'
+        self.tokenizer = AutoTokenizer.from_pretrained(path,
+                                                       trust_remote_code=True,
+                                                       use_fast=False)
+
+    def encode(self, content):
+        prompt = f"<|im_start|>system\n你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。<|im_end|><|im_start|>user\n{content}<|im_end|><|im_start|>assistant\n"
+        input_ids = self.tokenizer.encode(prompt)
+        return input_ids
+
+    def encode_with_image(self, question, num_of_images, imgsz) -> list:
+        prompt = "<|im_start|>system\n你是书生·万象, 英文名是InternVL, 是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型.<|im_end|>\n"
+     
+        prompt += "<|im_start|>user\n" + question
+
+        context_len = 64
+        if imgsz == 448:
+            context_len = 256
+        elif imgsz == 224:
+            context_len = 64
+        else:
+            print(f"imgsz is {imgsz}")
+            return
+        print("context_len is ", context_len)
+        
+        if num_of_images > 0:
+            for idx in range(num_of_images):
+                prompt += "\n<img>" + "<IMG_CONTEXT>" * context_len + "</img>\n"
+        
+        prompt += "<|im_end|>\n<|im_start|>assistant"
+        print(f"prompt is {prompt}")
+        token_ids = self.tokenizer.encode(prompt)
+        return token_ids
+    
+    
+    def decode(self, token_ids):
+        return self.tokenizer.decode(token_ids,
+                                     clean_up_tokenization_spaces=False, skip_special_tokens=True)
+
+    @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
+
+    @property
+    def img_start_token(self):
+        return self.tokenizer.encode("<img>")[0]
+
+    @property
+    def img_context_token(self):
+        return self.tokenizer.encode("<IMG_CONTEXT>")[0]
+
+tokenizer = Tokenizer_Http()
+
+print(tokenizer.bos_id, tokenizer.bos_token, tokenizer.eos_id,
+      tokenizer.eos_token, tokenizer.img_start_token, tokenizer.img_context_token)
+token_ids = tokenizer.encode_with_image("你好", 1, 448)
+print(token_ids)
+print(len(token_ids))
+token_ids = tokenizer.encode("hello world")
+print(token_ids)
+print(len(token_ids))
+
+
+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})
+        elif self.path == '/img_start_token':
+            img_start_token = tokenizer.img_start_token
+            if img_start_token is None:
+                msg = json.dumps({'img_start_token': -1})
+            else:
+                msg = json.dumps({'img_start_token': img_start_token})
+        elif self.path == '/img_context_token':
+            img_context_token = tokenizer.img_context_token
+            if img_context_token is None:
+                msg = json.dumps({'img_context_token': -1})
+            else:
+                msg = json.dumps({'img_context_token': img_context_token})
+        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��略或设置多个
+        self.end_headers()
+
+        if self.path == '/encode':
+            req = json.loads(data)
+            print(req)
+            prompt = req['text']
+            b_img_prompt = False
+            if 'img_prompt' in req:
+                b_img_prompt = req['img_prompt']
+            if b_img_prompt:
+                num_img = req['num_img']
+                imgsz = req['imgsz']
+                token_ids = tokenizer.encode_with_image(prompt, num_img, imgsz)
+            else:
+                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='0.0.0.0')
+    args.add_argument('--port', type=int, default=12345)
+    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

internvl3_tokenizer/added_tokens.json

@@ -0,0 +1,33 @@
+{
+  "</box>": 151673,
+  "</img>": 151666,
+  "</quad>": 151669,
+  "</ref>": 151671,
+  "</tool_call>": 151658,
+  "<IMG_CONTEXT>": 151667,
+  "<box>": 151672,
+  "<img>": 151665,
+  "<quad>": 151668,
+  "<ref>": 151670,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

internvl3_tokenizer/config.json

@@ -0,0 +1,224 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "/mnt/petrelfs/wangweiyun/workspace_wwy/open_source/InternVL/internvl_chat/work_dirs/internvl_chat_v3_0/InternVL3_0-1B-MPO-try0-2",
+  "architectures": [
+    "InternVLChatModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
+    "AutoModel": "modeling_internvl_chat.InternVLChatModel",
+    "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
+  },
+  "downsample_ratio": 0.5,
+  "dynamic_image_size": true,
+  "force_image_size": 448,
+  "hidden_size": 896,
+  "image_fold": null,
+  "llm_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
+    "add_cross_attention": false,
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 151643,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 896,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4864,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "moe_config": null,
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 14,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "factor": 2.0,
+      "rope_type": "dynamic",
+      "type": "dynamic"
+    },
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.48.3",
+    "typical_p": 1.0,
+    "use_bfloat16": true,
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151674
+  },
+  "max_dynamic_patch": 12,
+  "min_dynamic_patch": 1,
+  "model_type": "internvl_chat",
+  "pad2square": false,
+  "ps_version": "v2",
+  "select_layer": -1,
+  "system_message": null,
+  "template": "internvl2_5",
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_backbone_lora": 0,
+  "use_llm_lora": 0,
+  "use_thumbnail": true,
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
+    "add_cross_attention": false,
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+      "AutoConfig": "configuration_intern_vit.InternVisionConfig",
+      "AutoModel": "modeling_intern_vit.InternVisionModel"
+    },
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "capacity_factor": 1.2,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "eval_capacity_factor": 1.4,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 448,
+    "initializer_factor": 0.1,
+    "initializer_range": 1e-10,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "laux_allreduce": "all_nodes",
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "intern_vit_6b",
+    "moe_coeff_ratio": 0.5,
+    "moe_intermediate_size": 768,
+    "moe_output_scale": 4.0,
+    "no_repeat_ngram_size": 0,
+    "noisy_gate_policy": "RSample_before",
+    "norm_type": "layer_norm",
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_experts": 8,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "num_routed_experts": 4,
+    "num_shared_experts": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qk_normalization": false,
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "shared_expert_intermediate_size": 3072,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.48.3",
+    "typical_p": 1.0,
+    "use_bfloat16": true,
+    "use_flash_attn": true,
+    "use_moe": false,
+    "use_residual": true,
+    "use_rts": false,
+    "use_weighted_residual": false
+  }
+}

internvl3_tokenizer/generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.48.3"
+}

internvl3_tokenizer/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 448,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "size": 448
+}

internvl3_tokenizer/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

internvl3_tokenizer/tokenizer_config.json

@@ -0,0 +1,281 @@
+{
+  "add_bos_token": false,
+  "add_eos_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
+    },
+    "151665": {
+      "content": "<img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "</img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<IMG_CONTEXT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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",
+  "extra_special_tokens": {},
+  "model_max_length": 12288,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

main_api_ax650

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc74b9dcf37c2b75d1894fa0f0ecaffe741b11f13a58dda0d30ff1b4ca8d508
+size 6667616

main_api_axcl_x86

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849231c5e30faa54cf62a55022a45b42ed767a7feb52ea26483e5c70eb9073dd
+size 1927840

main_ax650

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0bc06d4c78f592ae546a9f91f260dd62da7bf6b41a8f8a24a7a648d58c7f72
+size 6568824

main_axcl_x86

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273bac369315774e6e6df5e725647c49e5356f22cc512f1daadfd58066a37ef0
+size 1840560

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
+}

run_internvl_3_1b_448_api_ax650.sh

@@ -0,0 +1,10 @@
+./main_api_ax650 \
+--template_filename_axmodel "./internvl3_1b_ax650/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 24 \
+--filename_image_encoder_axmodedl "./internvl3_1b_ax650/internvl3_1b_vit.axmodel" \
+--use_mmap_load_embed 1 \
+--filename_tokenizer_model "http://0.0.0.0:12345" \
+--filename_post_axmodel "./internvl3_1b_ax650/qwen2_post.axmodel" \
+--filename_tokens_embed "./internvl3_1b_ax650/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 151674 \
+--tokens_embed_size 896 \

run_internvl_3_1b_448_api_axcl_x86.sh

@@ -0,0 +1,11 @@
+./main_api_axcl_x86 \
+--template_filename_axmodel "./internvl3_1b_ax650/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 24 \
+--filename_image_encoder_axmodedl "./internvl3_1b_ax650/internvl3_1b_vit.axmodel" \
+--use_mmap_load_embed 1 \
+--filename_tokenizer_model "http://0.0.0.0:12345" \
+--filename_post_axmodel "./internvl3_1b_ax650/qwen2_post.axmodel" \
+--filename_tokens_embed "./internvl3_1b_ax650/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 151674 \
+--tokens_embed_size 896 \
+--devices 0,2,4 \

run_internvl_3_1b_448_ax650.sh

@@ -0,0 +1,11 @@
+./main_ax650 \
+--template_filename_axmodel "./internvl3_1b_ax650/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 24 \
+--filename_image_encoder_axmodedl "./internvl3_1b_ax650/internvl3_1b_vit.axmodel" \
+--use_mmap_load_embed 1 \
+--filename_tokenizer_model "http://0.0.0.0:12345" \
+--filename_post_axmodel "./internvl3_1b_ax650/qwen2_post.axmodel" \
+--filename_tokens_embed "./internvl3_1b_ax650/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 151674 \
+--tokens_embed_size 896 \
+--live_print 1

run_internvl_3_1b_448_axcl_x86.sh

@@ -0,0 +1,12 @@
+./main_axcl_x86 \
+--template_filename_axmodel "./internvl3_1b_ax650/qwen2_p128_l%d_together.axmodel" \
+--axmodel_num 24 \
+--filename_image_encoder_axmodedl "./internvl3_1b_ax650/internvl3_1b_vit.axmodel" \
+--use_mmap_load_embed 1 \
+--filename_tokenizer_model "http://0.0.0.0:12345" \
+--filename_post_axmodel "./internvl3_1b_ax650/qwen2_post.axmodel" \
+--filename_tokens_embed "./internvl3_1b_ax650/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 151674 \
+--tokens_embed_size 896 \
+--devices 0,2,4 \
+--live_print 1