" * IMG_CONTEXT_REPEAT + ""
+ prompt += "<|im_end|>\n<|im_start|>assistant\n"
+ return prompt
+
+ def _insert_vision_features(self, token_ids: List[int], prefill_data: np.ndarray, vit_features: List[np.ndarray]):
+ image_start_indices = np.where(np.array(token_ids) == IMG_PLACEHOLDER_TOKEN_ID)[0].tolist()
+ if len(image_start_indices) != len(vit_features):
+ raise ValueError("图片数量与占位符数量不一致, 请检查输入和模板生成逻辑")
+ for idx, image_start_index in enumerate(image_start_indices):
+ insert_pos = image_start_index + 1
+ prefill_data[insert_pos: insert_pos + IMG_CONTEXT_REPEAT] = vit_features[idx][0, :, :]
+ return prefill_data
+
+ def _run_model(self, prompt: str, vit_features: List[np.ndarray]):
+ """Non-streaming推理，保留以防需要一次性结果。"""
+ for k_cache in self.infer_manager.k_caches:
+ k_cache.fill(0)
+ for v_cache in self.infer_manager.v_caches:
+ v_cache.fill(0)
+
+ token_ids = self.tokenizer.encode(prompt)
+ prefill_data = np.take(self.embeds, token_ids, axis=0).astype(bfloat16)
+ if vit_features:
+ prefill_data = self._insert_vision_features(token_ids, prefill_data, vit_features)
+
+ eos_token_id = None
+ if isinstance(self.cfg.eos_token_id, list) and len(self.cfg.eos_token_id) > 1:
+ eos_token_id = self.cfg.eos_token_id
+
+ slice_len = 128
+ token_ids = self.infer_manager.prefill(self.tokenizer, token_ids, prefill_data, slice_len=slice_len)
+ return self.infer_manager.decode(
+ self.tokenizer,
+ token_ids,
+ self.embeds,
+ slice_len=slice_len,
+ eos_token_id=eos_token_id,
+ stream=False,
+ )
+
+ def _stream_generate(self, prompt: str, vit_features: List[np.ndarray]):
+ """流式生成，逐 token 产出累积文本与计时信息 (TTFT 与平均 decode ms/token)。"""
+ # reset kv cache per request
+ for k_cache in self.infer_manager.k_caches:
+ k_cache.fill(0)
+ for v_cache in self.infer_manager.v_caches:
+ v_cache.fill(0)
+
+ token_ids = self.tokenizer.encode(prompt)
+ prefill_data = np.take(self.embeds, token_ids, axis=0).astype(bfloat16)
+ if vit_features:
+ prefill_data = self._insert_vision_features(token_ids, prefill_data, vit_features)
+
+ eos_token_id = None
+ if isinstance(self.cfg.eos_token_id, list) and len(self.cfg.eos_token_id) > 1:
+ eos_token_id = self.cfg.eos_token_id
+
+ slice_len = 128
+ t_start = time.time()
+ token_ids = self.infer_manager.prefill(self.tokenizer, token_ids, prefill_data, slice_len=slice_len)
+
+ # copy decode逻辑，实现手动流式输出
+ mask = np.zeros((1, 1, self.infer_manager.max_seq_len + 1), dtype=np.float32).astype(bfloat16)
+ mask[:, :, :self.infer_manager.max_seq_len] -= 65536
+ seq_len = len(token_ids) - 1
+ if slice_len > 0:
+ mask[:, :, :seq_len] = 0
+
+ ttft_ms: Optional[float] = None
+ decode_tokens = 0
+ decode_elapsed_ms: float = 0.0
+ generated_text = ""
+ yield generated_text, ttft_ms, None, None, False
+
+ for step_idx in range(self.infer_manager.max_seq_len):
+ if slice_len > 0 and step_idx < seq_len:
+ continue
+ cur_token = token_ids[step_idx]
+ indices = np.array([step_idx], np.uint32).reshape((1, 1))
+ data = self.embeds[cur_token, :].reshape((1, 1, self.cfg.hidden_size)).astype(bfloat16)
+ for layer_idx in range(self.cfg.num_hidden_layers):
+ input_feed = {
+ "K_cache": self.infer_manager.k_caches[layer_idx],
+ "V_cache": self.infer_manager.v_caches[layer_idx],
+ "indices": indices,
+ "input": data,
+ "mask": mask,
+ }
+ outputs = self.infer_manager.decoder_sessions[layer_idx].run(None, input_feed, shape_group=0)
+ self.infer_manager.k_caches[layer_idx][:, step_idx, :] = outputs[0][:, :, :]
+ self.infer_manager.v_caches[layer_idx][:, step_idx, :] = outputs[1][:, :, :]
+ data = outputs[2]
+ mask[..., step_idx] = 0
+ if step_idx < seq_len - 1:
+ continue
+ post_out = self.infer_manager.post_process_session.run(None, {"input": data})[0]
+ next_token, possible_tokens, possible_probs = self.infer_manager.post_process(post_out, temperature=0.7)
+ if eos_token_id is not None and next_token in eos_token_id:
+ ttft_ms = ttft_ms or (time.time() - t_start) * 1000
+ break
+ if next_token == self.tokenizer.eos_token_id:
+ ttft_ms = ttft_ms or (time.time() - t_start) * 1000
+ break
+
+ token_ids.append(next_token)
+ # 使用完整 token 列表解码，避免多字节 UTF-8 字符被截断显示为乱码
+ # 只解码新生成的 tokens（从 seq_len 开始）
+ generated_text = self.tokenizer.decode(token_ids[seq_len:], skip_special_tokens=True)
+
+ if ttft_ms is None:
+ ttft_ms = (time.time() - t_start) * 1000
+ else:
+ decode_tokens += 1
+ decode_elapsed_ms = (time.time() - t_start) * 1000 - ttft_ms
+
+ avg_decode = (decode_elapsed_ms / decode_tokens) if decode_tokens > 0 else None
+ yield generated_text, ttft_ms, avg_decode, decode_tokens, False
+
+ total_ms = (time.time() - t_start) * 1000
+ avg_decode = (decode_elapsed_ms / decode_tokens) if decode_tokens > 0 else None
+ yield generated_text, ttft_ms, avg_decode, decode_tokens, True
+
+ def chat(self, user_input: str, image: Optional[Image.Image]) -> Generator:
+ user_text = (user_input or "").strip()
+ if not user_text and image is None:
+ yield [], gr.update(), gr.update(), gr.update(), gr.update()
+ return
+
+ # 先展示占位，保持图片不清空；同时占位速度信息
+ yield [(user_text, "处理中…")], gr.update(value=""), gr.update(), gr.update(value="TTFT -- ms | Decode -- ms/token | Tokens --
"), gr.update(interactive=False)
+
+ vit_outputs = []
+ if image is not None:
+ pixel_values = load_image(image, input_size=448, max_num=1)
+ vit_output = self.vit_session.run(None, {"image": pixel_values.numpy()})[0]
+ vit_outputs.append(vit_output.copy())
+
+ prompt = self._build_single_turn_prompt(user_text, vit_outputs)
+
+ chatbot_history = [(user_text, "")] # 将在流式过程中填充
+ for partial, ttft_ms, avg_decode_ms, decode_tokens, finished in self._stream_generate(prompt, vit_outputs):
+ chatbot_history[-1] = (user_text, partial)
+ ttft_disp = f"{ttft_ms:.0f}" if ttft_ms is not None else "--"
+ decode_disp = f"{avg_decode_ms:.1f}" if avg_decode_ms is not None else "--"
+ tok_disp = f"{decode_tokens}" if decode_tokens is not None else "--"
+ metrics_text = f"TTFT {ttft_disp} ms | Decode {decode_disp} ms/token | Tokens {tok_disp}
"
+ if finished:
+ yield chatbot_history, gr.update(value=""), gr.update(), gr.update(value=metrics_text), gr.update(interactive=True)
+ else:
+ yield chatbot_history, gr.update(value=""), gr.update(), gr.update(value=metrics_text), gr.update(interactive=False)
+
+ @staticmethod
+ def build_ui(demo: "InternVLGradioDemo", server_name: str = "0.0.0.0", server_port: int = 7860, share: bool = False):
+ # 自定义 JavaScript: Enter 发送, Shift+Enter 换行
+ custom_js = """
+ function() {
+ // 等待 DOM 加载完成后绑定事件
+ setTimeout(() => {
+ const textareas = document.querySelectorAll('#user-input textarea');
+ textareas.forEach(textarea => {
+ // 移除可能存在的旧监听器
+ textarea.removeEventListener('keydown', textarea._customKeyHandler);
+
+ textarea._customKeyHandler = function(e) {
+ if (e.key === 'Enter') {
+ if (e.shiftKey) {
+ // Shift+Enter: 插入换行符
+ e.preventDefault();
+ const start = this.selectionStart;
+ const end = this.selectionEnd;
+ const value = this.value;
+ this.value = value.substring(0, start) + '\\n' + value.substring(end);
+ this.selectionStart = this.selectionEnd = start + 1;
+ // 触发 input 事件让 Gradio 感知变化
+ this.dispatchEvent(new Event('input', { bubbles: true }));
+ } else {
+ // Enter: 发送消息
+ e.preventDefault();
+ const sendBtn = document.querySelector('#send-btn');
+ if (sendBtn) {
+ sendBtn.click();
+ }
+ }
+ }
+ };
+ textarea.addEventListener('keydown', textarea._customKeyHandler);
+ });
+ }, 500);
+ }
+ """
+
+ with gr.Blocks(title="InternVL3-5-1B AX Gradio Demo", theme=gr.themes.Soft(), js=custom_js) as iface:
+ gr.HTML("""""")
+ gr.Markdown("""### InternVL3-5-1B 图文对话演示\n上传一张图片 (可选)，输入问题，获取中文回答。""")
+
+ with gr.Row():
+ # 左侧：对话框和输入区域
+ with gr.Column(scale=5):
+ with gr.Group(elem_id="chat-wrap"):
+ chatbot = gr.Chatbot(height=500, label="对话")
+ metrics_md = gr.Markdown("TTFT -- ms | Decode -- ms/token | Tokens --
", elem_id="metrics-display")
+
+ with gr.Row():
+ user_input = gr.Textbox(
+ placeholder="按 Enter 发送，Shift+Enter 换行",
+ lines=2,
+ scale=7,
+ max_lines=5,
+ show_label=False,
+ elem_id="user-input",
+ )
+ with gr.Column(scale=1, min_width=100):
+ send_btn = gr.Button("发送", variant="primary", size="sm", elem_id="send-btn")
+ clear_btn = gr.Button("清空对话", variant="secondary", size="sm")
+
+ # 右侧：图像上传和信息提示
+ with gr.Column(scale=3):
+ image_input = gr.Image(
+ type="pil",
+ label="上传图片 (可选)",
+ height=380,
+ image_mode="RGB",
+ show_download_button=False,
+ elem_id="image-pane",
+ )
+ gr.Markdown("""- 支持单张图像理解\n- 仅当前问题与回答，不保留历史\n- 处理时间取决于硬件，请耐心等待""")
+
+ def _clear():
+ return [], gr.update(value=""), gr.update(), gr.update(value="TTFT -- ms | Decode -- ms/token | Tokens --
"), gr.update(interactive=True)
+
+ send_btn.click(
+ fn=demo.chat,
+ inputs=[user_input, image_input],
+ outputs=[chatbot, user_input, image_input, metrics_md, send_btn],
+ show_progress=False,
+ queue=True,
+ )
+ # 移除 user_input.submit，由自定义 JS 处理 Enter 发送，Shift+Enter 换行
+ clear_btn.click(fn=_clear, inputs=None, outputs=[chatbot, user_input, image_input, metrics_md, send_btn])
+
+ iface.queue().launch(server_name=server_name, server_port=server_port, share=share)
+
+
+def parse_args():
+ parser = argparse.ArgumentParser(description="InternVL3-5-1B AX gradio demo")
+ parser.add_argument("--hf_model", type=str, default="./InternVL3_5-1B",
+ help="HuggingFace 模型路径")
+ parser.add_argument("--axmodel_path", type=str, default="./InternVL3_5-1B_axmodel",
+ help="LLM axmodel 目录")
+ parser.add_argument("--vit_model", type=str, default="./vit-models/internvl_vit_model_1x3x448x448.axmodel",
+ help="ViT axmodel 路径")
+ parser.add_argument("--port", type=int, default=7860, help="Gradio 端口")
+ parser.add_argument("--host", type=str, default="0.0.0.0", help="Gradio 监听地址")
+ parser.add_argument("--share", action="store_true", help="启用 gradio share")
+ return parser.parse_args()
+
+
+def main():
+ args = parse_args()
+ demo = InternVLGradioDemo(args.hf_model, args.axmodel_path, args.vit_model)
+ InternVLGradioDemo.build_ui(demo, server_name=args.host, server_port=args.port, share=args.share)
+
+
+if __name__ == "__main__":
+ main()
diff --git a/infer_axmodel.py b/infer_axmodel.py
new file mode 100644
index 0000000000000000000000000000000000000000..75233a68441456b9bd7de2b5a6e7399d412f9724
--- /dev/null
+++ b/infer_axmodel.py
@@ -0,0 +1,183 @@
+from transformers import AutoProcessor, AutoModelForImageTextToText
+import torch
+import onnx
+import onnxruntime as ort
+import numpy as np
+import os
+from tqdm import tqdm
+from transformers import AutoConfig, AutoTokenizer
+from typing import List, Tuple
+from axengine import InferenceSession
+from ml_dtypes import bfloat16
+from utils.infer_func import InferManager
+import argparse
+from PIL import Image
+import torchvision.transforms as T
+from torchvision.transforms.functional import InterpolationMode
+
+
+IMAGENET_MEAN = (0.485, 0.456, 0.406)
+IMAGENET_STD = (0.229, 0.224, 0.225)
+
+def build_transform(input_size):
+ MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
+ transform = T.Compose([
+ T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
+ T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
+ T.ToTensor(),
+ T.Normalize(mean=MEAN, std=STD)
+ ])
+ return transform
+
+def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
+ best_ratio_diff = float('inf')
+ best_ratio = (1, 1)
+ area = width * height
+ for ratio in target_ratios:
+ target_aspect_ratio = ratio[0] / ratio[1]
+ ratio_diff = abs(aspect_ratio - target_aspect_ratio)
+ if ratio_diff < best_ratio_diff:
+ best_ratio_diff = ratio_diff
+ best_ratio = ratio
+ elif ratio_diff == best_ratio_diff:
+ if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
+ best_ratio = ratio
+ return best_ratio
+
+def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
+ orig_width, orig_height = image.size
+ aspect_ratio = orig_width / orig_height
+
+ # calculate the existing image aspect ratio
+ target_ratios = set(
+ (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
+ i * j <= max_num and i * j >= min_num)
+ target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
+
+ # find the closest aspect ratio to the target
+ target_aspect_ratio = find_closest_aspect_ratio(
+ aspect_ratio, target_ratios, orig_width, orig_height, image_size)
+
+ # calculate the target width and height
+ target_width = image_size * target_aspect_ratio[0]
+ target_height = image_size * target_aspect_ratio[1]
+ blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
+
+ # resize the image
+ resized_img = image.resize((target_width, target_height))
+ processed_images = []
+ for i in range(blocks):
+ box = (
+ (i % (target_width // image_size)) * image_size,
+ (i // (target_width // image_size)) * image_size,
+ ((i % (target_width // image_size)) + 1) * image_size,
+ ((i // (target_width // image_size)) + 1) * image_size
+ )
+ # split the image
+ split_img = resized_img.crop(box)
+ processed_images.append(split_img)
+ assert len(processed_images) == blocks
+ if use_thumbnail and len(processed_images) != 1:
+ thumbnail_img = image.resize((image_size, image_size))
+ processed_images.append(thumbnail_img)
+ return processed_images
+
+def load_image(image_file, input_size=448, max_num=12):
+ image = Image.open(image_file).convert('RGB')
+ transform = build_transform(input_size=input_size)
+ images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
+ pixel_values = [transform(image) for image in images]
+ pixel_values = torch.stack(pixel_values)
+ return pixel_values
+
+if __name__ == "__main__":
+
+ """
+ python3 infer_axmodel.py --vit_model vit-models/internvl_vit_model_1x3x448x448.axmodel --images examples/image_0.jpg
+ """
+ prompt = None
+ parser = argparse.ArgumentParser(description="Model configuration parameters")
+ parser.add_argument("--hf_model", type=str, default="./InternVL3_5-1B",
+ help="Path to HuggingFace model")
+ parser.add_argument("--axmodel_path", type=str, default="./InternVL3_5-1B_axmodel",
+ help="Path to save compiled axmodel of llama model")
+ parser.add_argument("--vit_model", type=str, default=None, help="Path to save compiled axmodel of llama model")
+ parser.add_argument("-i", "--images", nargs='+', type=str, default=None,
+ help="Path to the test image.")
+ parser.add_argument("-q", "--question", type=str, default="请你描述这幅图的内容.",
+ help="Your question that you want to ask the model.")
+ args = parser.parse_args()
+
+ hf_model_path = args.hf_model
+ axmodel_path = args.axmodel_path
+ images = args.images
+ prompt = args.question
+
+ device = "cuda" if torch.cuda.is_available() else "cpu"
+ embeds = np.load(os.path.join(axmodel_path, "model.embed_tokens.weight.npy"))
+
+ # load the tokenizer and the model
+ tokenizer = AutoTokenizer.from_pretrained(hf_model_path)
+ config = AutoConfig.from_pretrained(hf_model_path, trust_remote_code=True)
+
+ # model = AutoModelForCausalLM.from_pretrained(
+ # hf_model_path,
+ # ).to(device)
+
+ test_imgs_path = args.images
+ vit_axmodel_path = args.vit_model
+
+ # set the max number of tiles in `max_num`
+ pixel_values_list = []
+ if test_imgs_path is not None:
+ for img_path in test_imgs_path:
+ pixel_values = load_image(img_path, input_size=448, max_num=1)
+ pixel_values_list.append(pixel_values)
+ print(f"输入图像数: {len(pixel_values_list)}")
+ print("preprocess image done!")
+
+ # extract img feature by vit
+ vit_session = InferenceSession(vit_axmodel_path)
+ vit_output_list = []
+ for idx, pixel_values in enumerate(pixel_values_list):
+ vit_output = vit_session.run(None, {"image": pixel_values.numpy()})[0]
+ vit_output_list.append(vit_output.copy()) # 避免 vit 输出结果使用同一块内存
+
+ print(f"vit_output.shape is {vit_output_list[0].shape}, vit feature extract done!")
+
+ prompt = "<|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 InternVL3, 是一个有用无害的人工智能助手, 擅长思考和回答用户的问题. 请你在回答问题时使用简体中文.<|im_end|>\n"
+ question = args.question
+ prompt += "<|im_start|>user\n" + question
+
+ if len(pixel_values_list) > 0:
+ for idx in range(len(pixel_values_list)):
+ prompt += "\n![]()
" + "" * 256 + "\n"
+ prompt += "<|im_end|>\n<|im_start|>assistant\n"
+ print(f"prompt is {prompt}")
+ token_ids = tokenizer.encode(prompt)
+ # 图像理解
+ image_start_indices = np.where(np.array(token_ids) == 151669)[0].tolist() # ![]()
tag 151669, 151665
+ prefill_data = np.take(embeds, token_ids, axis=0)
+ prefill_data = prefill_data.astype(bfloat16)
+ token_len = len(token_ids)
+
+ for idx, image_start_index in enumerate(image_start_indices):
+ image_insert_index = image_start_index + 1
+ prefill_data[image_insert_index : image_insert_index + 256] = vit_output_list[idx][0, :, :]
+ ##################################
+
+ cfg = config.llm_config
+
+ eos_token_id = None
+ if isinstance(cfg.eos_token_id, list) and len(cfg.eos_token_id) > 1:
+ eos_token_id = cfg.eos_token_id
+
+ slice_len = 128
+ prefill_max_len = 1024 - 1
+ max_seq_len = 2048 - 1 # prefill + decode max length
+
+ imer = InferManager(cfg, axmodel_path, max_seq_len=max_seq_len) # prefill + decode max length
+ # import pdb; pdb.set_trace()
+ token_ids = imer.prefill(tokenizer, token_ids, prefill_data, slice_len=slice_len)
+ imer.decode(tokenizer, token_ids, embeds, slice_len=slice_len, eos_token_id=eos_token_id)
+ print("\n")
\ No newline at end of file
diff --git a/infer_torch.py b/infer_torch.py
new file mode 100644
index 0000000000000000000000000000000000000000..1f718b6525fff55d7b40ddc968729e3e623742f6
--- /dev/null
+++ b/infer_torch.py
@@ -0,0 +1,212 @@
+import math
+import numpy as np
+import torch
+import torchvision.transforms as T
+from decord import VideoReader, cpu
+from PIL import Image
+from torchvision.transforms.functional import InterpolationMode
+from transformers import AutoModel, AutoTokenizer
+
+IMAGENET_MEAN = (0.485, 0.456, 0.406)
+IMAGENET_STD = (0.229, 0.224, 0.225)
+
+def build_transform(input_size):
+ MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
+ transform = T.Compose([
+ T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
+ T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
+ T.ToTensor(),
+ T.Normalize(mean=MEAN, std=STD)
+ ])
+ return transform
+
+def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
+ best_ratio_diff = float('inf')
+ best_ratio = (1, 1)
+ area = width * height
+ for ratio in target_ratios:
+ target_aspect_ratio = ratio[0] / ratio[1]
+ ratio_diff = abs(aspect_ratio - target_aspect_ratio)
+ if ratio_diff < best_ratio_diff:
+ best_ratio_diff = ratio_diff
+ best_ratio = ratio
+ elif ratio_diff == best_ratio_diff:
+ if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
+ best_ratio = ratio
+ return best_ratio
+
+def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
+ orig_width, orig_height = image.size
+ aspect_ratio = orig_width / orig_height
+
+ # calculate the existing image aspect ratio
+ target_ratios = set(
+ (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
+ i * j <= max_num and i * j >= min_num)
+ target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
+
+ # find the closest aspect ratio to the target
+ target_aspect_ratio = find_closest_aspect_ratio(
+ aspect_ratio, target_ratios, orig_width, orig_height, image_size)
+
+ # calculate the target width and height
+ target_width = image_size * target_aspect_ratio[0]
+ target_height = image_size * target_aspect_ratio[1]
+ blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
+
+ # resize the image
+ resized_img = image.resize((target_width, target_height))
+ processed_images = []
+ for i in range(blocks):
+ box = (
+ (i % (target_width // image_size)) * image_size,
+ (i // (target_width // image_size)) * image_size,
+ ((i % (target_width // image_size)) + 1) * image_size,
+ ((i // (target_width // image_size)) + 1) * image_size
+ )
+ # split the image
+ split_img = resized_img.crop(box)
+ processed_images.append(split_img)
+ assert len(processed_images) == blocks
+ if use_thumbnail and len(processed_images) != 1:
+ thumbnail_img = image.resize((image_size, image_size))
+ processed_images.append(thumbnail_img)
+ return processed_images
+
+def load_image(image_file, input_size=448, max_num=12):
+ image = Image.open(image_file).convert('RGB')
+ transform = build_transform(input_size=input_size)
+ images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
+ pixel_values = [transform(image) for image in images]
+ pixel_values = torch.stack(pixel_values)
+ return pixel_values
+
+path = './InternVL3_5-1B'
+model = AutoModel.from_pretrained(
+ path,
+ torch_dtype=torch.bfloat16,
+ load_in_8bit=False,
+ low_cpu_mem_usage=True,
+ use_flash_attn=True,
+ trust_remote_code=True,
+ device_map="auto").eval()
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
+# set the max number of tiles in `max_num`
+pixel_values = load_image('./examples/image_1.jpg', input_size=448, max_num=1).to(torch.bfloat16).cuda()
+generation_config = dict(max_new_tokens=1024, do_sample=True)
+
+# pure-text conversation (纯文本对话)
+question = '中国的首都'
+response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
+print(f'User: {question}\nAssistant: {response}')
+
+
+# single-image single-round conversation (单图单轮对话)
+question = '\n请你描述这幅图的内容.'
+response = model.chat(tokenizer, pixel_values, question, generation_config)
+print(f'User: {question}\nAssistant: {response}')
+
+# # single-image multi-round conversation (单图多轮对话)
+# question = '\nPlease describe the image in detail.'
+# response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
+# print(f'User: {question}\nAssistant: {response}')
+
+# question = 'Please write a poem according to the image.'
+# response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
+# print(f'User: {question}\nAssistant: {response}')
+
+# # multi-image multi-round conversation, combined images (多图多轮对话，拼接图像)
+# pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
+# pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
+# pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
+
+# question = '\nDescribe the two images in detail.'
+# response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+# history=None, return_history=True)
+# print(f'User: {question}\nAssistant: {response}')
+
+# question = 'What are the similarities and differences between these two images.'
+# response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+# history=history, return_history=True)
+# print(f'User: {question}\nAssistant: {response}')
+
+# # multi-image multi-round conversation, separate images (多图多轮对话，独立图像)
+# pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
+# pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
+# pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
+# num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
+
+# question = 'Image-1: \nImage-2: \nDescribe the two images in detail.'
+# response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+# num_patches_list=num_patches_list,
+# history=None, return_history=True)
+# print(f'User: {question}\nAssistant: {response}')
+
+# question = 'What are the similarities and differences between these two images.'
+# response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+# num_patches_list=num_patches_list,
+# history=history, return_history=True)
+# print(f'User: {question}\nAssistant: {response}')
+
+# # batch inference, single image per sample (单图批处理)
+# pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
+# pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
+# num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
+# pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
+
+# questions = ['\nDescribe the image in detail.'] * len(num_patches_list)
+# responses = model.batch_chat(tokenizer, pixel_values,
+# num_patches_list=num_patches_list,
+# questions=questions,
+# generation_config=generation_config)
+# for question, response in zip(questions, responses):
+# print(f'User: {question}\nAssistant: {response}')
+
+# # video multi-round conversation (视频多轮对话)
+# def get_index(bound, fps, max_frame, first_idx=0, num_segments=32):
+# if bound:
+# start, end = bound[0], bound[1]
+# else:
+# start, end = -100000, 100000
+# start_idx = max(first_idx, round(start * fps))
+# end_idx = min(round(end * fps), max_frame)
+# seg_size = float(end_idx - start_idx) / num_segments
+# frame_indices = np.array([
+# int(start_idx + (seg_size / 2) + np.round(seg_size * idx))
+# for idx in range(num_segments)
+# ])
+# return frame_indices
+
+# def load_video(video_path, bound=None, input_size=448, max_num=1, num_segments=32):
+# vr = VideoReader(video_path, ctx=cpu(0), num_threads=1)
+# max_frame = len(vr) - 1
+# fps = float(vr.get_avg_fps())
+
+# pixel_values_list, num_patches_list = [], []
+# transform = build_transform(input_size=input_size)
+# frame_indices = get_index(bound, fps, max_frame, first_idx=0, num_segments=num_segments)
+# for frame_index in frame_indices:
+# img = Image.fromarray(vr[frame_index].asnumpy()).convert('RGB')
+# img = dynamic_preprocess(img, image_size=input_size, use_thumbnail=True, max_num=max_num)
+# pixel_values = [transform(tile) for tile in img]
+# pixel_values = torch.stack(pixel_values)
+# num_patches_list.append(pixel_values.shape[0])
+# pixel_values_list.append(pixel_values)
+# pixel_values = torch.cat(pixel_values_list)
+# return pixel_values, num_patches_list
+
+# video_path = './examples/red-panda.mp4'
+# pixel_values, num_patches_list = load_video(video_path, num_segments=8, max_num=1)
+# pixel_values = pixel_values.to(torch.bfloat16).cuda()
+# video_prefix = ''.join([f'Frame{i+1}: \n' for i in range(len(num_patches_list))])
+# question = video_prefix + 'What is the red panda doing?'
+# # Frame1: \nFrame2: \n...\nFrame8: \n{question}
+# response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+# num_patches_list=num_patches_list, history=None, return_history=True)
+# print(f'User: {question}\nAssistant: {response}')
+
+# question = 'Describe this video in detail.'
+# response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+# num_patches_list=num_patches_list, history=history, return_history=True)
+# print(f'User: {question}\nAssistant: {response}')
diff --git a/internvl3-5_axmodel/model.embed_tokens.weight.bfloat16.bin b/internvl3-5_axmodel/model.embed_tokens.weight.bfloat16.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ff68cfc6e311f6bd2619d21687e7b6fa02ad395e
--- /dev/null
+++ b/internvl3-5_axmodel/model.embed_tokens.weight.bfloat16.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9458f8d6cac0fb032e0d9aa5e237148a2ee2e6f9c98ebf7584b065e174127009
+size 311164928
diff --git a/internvl3-5_axmodel/model.embed_tokens.weight.float32.bin b/internvl3-5_axmodel/model.embed_tokens.weight.float32.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ab6c9fc5137d6dd29ccf595ee6b996558c7f971b
--- /dev/null
+++ b/internvl3-5_axmodel/model.embed_tokens.weight.float32.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69f2b742ddc9d789d16f46073fbe8fdfce77222958071fabf4ff708af07bf23
+size 622329856
diff --git a/internvl3-5_axmodel/model.embed_tokens.weight.npy b/internvl3-5_axmodel/model.embed_tokens.weight.npy
new file mode 100644
index 0000000000000000000000000000000000000000..3660027a3d7e54534aeb0ba345c7dd7e4bc101bc
--- /dev/null
+++ b/internvl3-5_axmodel/model.embed_tokens.weight.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e826d74d8269b0085d3fdd397e7fa6303ec26719c76f4d5b1d029fab63fcf50
+size 622329984
diff --git a/internvl3-5_axmodel/qwen3_p128_l0_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l0_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..6d6aa294a270f1bc7e0719e49c484f6ef693b279
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l0_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12d7e947b42e933d6c3119e08d6be0ecb703df7746839cb91a0452d12c490f0
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l10_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l10_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..5424bb093388f186638611198417cea4e16ff9df
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l10_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452cc345d0b182b95f3e961ac9faa1767563f8324fc3d3ed3372f5b63851059b
+size 21569348
diff --git a/internvl3-5_axmodel/qwen3_p128_l11_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l11_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..8f21b83fe00ad4df51f7b72b69a6546db33ad01e
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l11_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f031d1f7e7713d4f0aee4a5fc1a3beffd4593eae922e81946537eca946b04f
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l12_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l12_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..b5a6c06093b253014757b1bc809c317da11201a5
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l12_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3295106128b7d41ae737274abc58a9b9e49fc1d56df904eb8b44d08b2a13462b
+size 21569220
diff --git a/internvl3-5_axmodel/qwen3_p128_l13_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l13_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..31792de8a5f0e8a55bbe6b08dc1b0323282fc2fe
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l13_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b192de65f95a19271ddcf91eca383c782ecd23fb6be2fdb47369ec76d480e21
+size 21569156
diff --git a/internvl3-5_axmodel/qwen3_p128_l14_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l14_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..7ceb74fb0599b277969e83063a843dd684c6612b
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l14_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd05f0f6d2b2f6b07c74cece9dfd09a86a5e2a0d1b941b6a01baf31a19edc53
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l15_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l15_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..431fff961b12daefd240485d1823d898d1b67cbd
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l15_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205d2b186e641bd8efb5cbcba1422d7f47384fc2e308ea791f79e0cffb002d48
+size 21568836
diff --git a/internvl3-5_axmodel/qwen3_p128_l16_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l16_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..d596e18d66b057223f8b1dc8148d61b40a35b21a
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l16_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab96615046ebf359d86fbab9c45af036fb79bcd8e4bbf2d9cab63fef8b0ef47
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l17_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l17_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..475bc78830b118137e1ed12ea62bdd65e6d26fc1
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l17_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b2569ba99a274fee59ef56ea4ba0e4109971d196240b254a68e4e0f0808ac2
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l18_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l18_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..f9d7b754cb807beda1a0bb478e6253403c9fbb7c
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l18_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb521e5c3e03f3b96b6370362234e741910cf82c038984081e9ab95a101c31d
+size 21568900
diff --git a/internvl3-5_axmodel/qwen3_p128_l19_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l19_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..611448d9a7c269b7c4dbe2db99467275dfecbda5
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l19_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821a3937c506eaa268440ee116961ef2ceb17b5362661d3c9f41997a7aacf54f
+size 21568740
diff --git a/internvl3-5_axmodel/qwen3_p128_l1_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l1_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..b940f17bb738064aceb93715915dd52700384aa7
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l1_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba82686a72bb26759fbf96c7544277d5547ec23634f4128579bd53464072432
+size 21568932
diff --git a/internvl3-5_axmodel/qwen3_p128_l20_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l20_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..f86a62b553e794939c6ee773bb91225f621ebd2a
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l20_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e70045401bd0c6748558ec0374d11cb381644109b687c0358fb8cec5e88de1c
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l21_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l21_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..40620dc27170585cdb90b4431ae956cce0eaf71c
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l21_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ecb18c9bd8d79fe019df779b5f7212f0af1b742adbd69b9968f9e93ec83a83
+size 21568772
diff --git a/internvl3-5_axmodel/qwen3_p128_l22_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l22_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..c5dbb908f190fedc8af11495a365f2a94ca7bb22
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l22_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5037445038d24a9a44c6defc22638f53ef9875ca62e9ea836077d1518c28d8d
+size 21568964
diff --git a/internvl3-5_axmodel/qwen3_p128_l23_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l23_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..b768b139c989d3ad41d6f0130babddf3e8c3edb8
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l23_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510b76060ef414a7100989e631d6d8336ebf5573467eceb9cf5ad0641df15119
+size 21568644
diff --git a/internvl3-5_axmodel/qwen3_p128_l24_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l24_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..250283a14d342b880361a3d1a8faab1e0c3d2fcb
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l24_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b6fed1cb82fee89097d326ddfd414e41f0d9bdc27087b630dc678235085a4c
+size 21569508
diff --git a/internvl3-5_axmodel/qwen3_p128_l25_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l25_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..f735fe2e80557363b30766ed2af0ed7c27127585
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l25_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f1c7b43867ca7c38b942d78b81eed377e61123c3ec1b954bc309c71793f4aa
+size 21568964
diff --git a/internvl3-5_axmodel/qwen3_p128_l26_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l26_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..3d167a06a7f86b9bad1b4a8e5240c31b8d2eba1e
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l26_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7726bb67ea16ba081e73b9982c464cbd7317de09b7c1e34c58072b7a55a1cb8
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l27_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l27_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..959ae24ba9ee24d699b5d31c638d2b222804e4c4
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l27_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0888376b5c59ee87687961078bce26e9dc016a8207838659dabbaa400ce4f3
+size 21570244
diff --git a/internvl3-5_axmodel/qwen3_p128_l2_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l2_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..0a66583f42e8a2ffec6c213a2ca64f10233e9dd6
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l2_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ed31ea8c87f7ea9d4e31b4911ad4be22d3b917b9ce4a8723ea11eaf53f2aca
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l3_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l3_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..a328de25529e6990a1c55d97b53eeb5bc99b80f5
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l3_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681988b5ae14445af3219f465b53dea50590bd755b91aeaee83646401b08d058
+size 21568708
diff --git a/internvl3-5_axmodel/qwen3_p128_l4_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l4_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..254a3f28b3161fd2be0f4fab149e2e16e99b7c48
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l4_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e4d21c3ee0a63b2e3d4728a784885611105c796bc400d0f4403cc68e5113df
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l5_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l5_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..a0b956266567cdc4af3553403b53fb50a20ffde0
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l5_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15c93c5e243ff7a55e96dc1dd38a47747164c1ef4ef7a9ba3acc6846fe93e3c
+size 21568996
diff --git a/internvl3-5_axmodel/qwen3_p128_l6_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l6_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..b55c69e10ac5f2a1989df91e22390b6fadeaaf06
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l6_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88dddad7925e2c455cb8ee7ed23de8743efd51378aa4a16fae11049649841981
+size 21568292
diff --git a/internvl3-5_axmodel/qwen3_p128_l7_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l7_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..39e94fb57cc67db7f54be795e126f196f3aea332
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l7_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fb8302f98ec47f75e0d0608af30df1bdaebdad870d3412ea4cdf4f9a9a0632
+size 21569988
diff --git a/internvl3-5_axmodel/qwen3_p128_l8_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l8_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..7abe3330cde632202033042bfee5107ad248a345
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l8_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff0ddf70c1cefe35bae6e06dbcda6e1714a3077255085db50a7184314baccdc
+size 21569060
diff --git a/internvl3-5_axmodel/qwen3_p128_l9_together.axmodel b/internvl3-5_axmodel/qwen3_p128_l9_together.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..3b304616803e938769af91f69207593ec0f9472b
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_p128_l9_together.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df43e2bf7490043031395eedfd7c099b420ed4bd752fe2d8ef7b3c60489f952
+size 21568612
diff --git a/internvl3-5_axmodel/qwen3_post.axmodel b/internvl3-5_axmodel/qwen3_post.axmodel
new file mode 100644
index 0000000000000000000000000000000000000000..8dbf45abbf608083e257876e68e1a081bdae6006
--- /dev/null
+++ b/internvl3-5_axmodel/qwen3_post.axmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0475e343fc60202f8ae651fd3a4ff574e31a61563bca4840aacd3f59539307e
+size 170001027
diff --git a/internvl3-5_tokenizer/.gitattributes b/internvl3-5_tokenizer/.gitattributes
new file mode 100644
index 0000000000000000000000000000000000000000..52373fe24473b1aa44333d318f578ae6bf04b49b
--- /dev/null
+++ b/internvl3-5_tokenizer/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/internvl3-5_tokenizer/README.md b/internvl3-5_tokenizer/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..0e04c4e23aa13d0297b5088c432d792757341f51
--- /dev/null
+++ b/internvl3-5_tokenizer/README.md
@@ -0,0 +1,830 @@
+---
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
+base_model:
+ - OpenGVLab/InternVL3_5-1B-MPO
+base_model_relation: finetune
+datasets:
+ - OpenGVLab/MMPR-v1.2
+language:
+ - multilingual
+tags:
+ - internvl
+ - custom_code
+---
+
+# InternVL3_5-1B
+
+[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821) [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271) [\[📜 InternVL2.5-MPO\]](https://huggingface.co/papers/2411.10442) [\[📜 InternVL3\]](https://huggingface.co/papers/2504.10479) [\[📜 InternVL3.5\]](https://huggingface.co/papers/2508.18265)
+
+[\[🆕 Blog\]](https://internvl.github.io/blog/) [\[🗨️ Chat Demo\]](https://chat.intern-ai.org.cn/) [\[🚀 Quick Start\]](#quick-start) [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/)
+
+
+
+