Upload smoke LoRA adapter

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

README.md

@@ -0,0 +1,89 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen3.5-0.8B
+tags:
+- peft
+- lora
+- multimodal
+- embedding
+- qwen3_5
+- nexus
+---
+
+# Nexus Qwen3.5-0.8B Smoke LoRA Adapter
+
+This repository contains a small LoRA adapter produced from a real smoke finetune run of the Nexus multimodal embedding stack.
+
+It is intended for pipeline validation rather than benchmark claims or production deployment.
+
+## What This Repo Contains
+
+This is an adapter-only release. It does not include the full base model weights.
+
+Main files:
+
+- `adapter_model.safetensors`
+- `adapter_config.json`
+- `processor_config.json`
+- `tokenizer.json`
+- `tokenizer_config.json`
+- `chat_template.jinja`
+- `nexus_configs/`
+
+Expected base model:
+
+- `Qwen/Qwen3.5-0.8B`
+
+## Training Summary
+
+- Base model: `Qwen/Qwen3.5-0.8B`
+- Training stack: Nexus multimodal retrieval embedder
+- Finetune type: LoRA
+- Training goal: smoke validation for training, save, reload, and inference paths
+- Data: a small HatefulMemes smoke subset
+- Steps: `10`
+- Precision: `bf16`
+- Per-device batch size: `8`
+- Gradient checkpointing: enabled
+
+The exact Nexus config files used in this run are included under `nexus_configs/`.
+
+## Recommended Usage
+
+### Load directly with Nexus
+
+Inside the Nexus codebase, the simplest path is to point both model and processor to this adapter directory:
+
+```python
+from Nexus import MultimodalEmbedder
+
+model = MultimodalEmbedder(
+    model_name_or_path="path/to/this/adapter/repo",
+    processor_name_or_path="path/to/this/adapter/repo",
+    model_type="qwen3_5",
+    trust_remote_code=True,
+    normalize_embeddings=True,
+    pooling_method="last_token",
+)
+```
+
+Nexus will detect `adapter_config.json`, load the base model, and then attach the LoRA adapter.
+
+### Merge before publishing a full model
+
+If you want a standalone full-weight repository, merge this adapter into the base model and publish the merged checkpoint as a separate repo.
+
+For Stage 1 delivery, the adapter-only release is the primary artifact.
+
+## Limitations
+
+- This is a smoke finetune artifact, not a fully trained multimodal embedding model.
+- The training data scale is intentionally tiny.
+- Use this checkpoint to validate code and release flow, not to claim final model quality.
+
+## Notes
+
+- The original training run used a machine-local base model path.
+- For Hugging Face publication, `adapter_config.json` in this release directory has been normalized to `Qwen/Qwen3.5-0.8B`.
+- If you need an offline local test on the original training machine, keep a second local-only adapter copy that still points to the local base model directory.

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5Model",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
+  },
+  "base_model_name_or_path": "Qwen/Qwen3.5-0.8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8157029affe529d6bc94a2152c9f503f4d90a81f6935b7af6e9a66aa1e5ee26
+size 102263200

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

nexus_configs/data_config.json

@@ -0,0 +1,16 @@
+{
+  "train_data": [
+    "/home/szn/zhangx/explore/related_data/nexus_teacher_delivery_used_assets/data/train_1000/HatefulMemes.jsonl"
+  ],
+  "cache_path": "/tmp/nexus_qwen35_0p8b_smoke_cache",
+  "media_root": null,
+  "train_group_size": 4,
+  "query_max_len": 512,
+  "passage_max_len": 1024,
+  "query_instruction_for_retrieval": "Represent this multimodal query for retrieving matching targets: ",
+  "query_instruction_format": "{}{}",
+  "passage_instruction_for_retrieval": null,
+  "passage_instruction_format": "{}{}",
+  "knowledge_distillation": false,
+  "shuffle_ratio": 0.0
+}

nexus_configs/model_config.json

@@ -0,0 +1,18 @@
+{
+  "model_name_or_path": "/home/szn/zhangx/model_weights/qwen3_5_0_8b_local",
+  "processor_name_or_path": "/home/szn/zhangx/model_weights/qwen3_5_0_8b_local",
+  "model_type": "qwen3_5",
+  "backbone_load_strategy": "prefer_base_model",
+  "cache_dir": null,
+  "trust_remote_code": true,
+  "torch_dtype": "bfloat16",
+  "attn_implementation": null,
+  "use_chat_template": true,
+  "processor_kwargs": null,
+  "processor_call_kwargs": null,
+  "use_lora": true,
+  "lora_r": 64,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "lora_target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj"
+}

nexus_configs/training_config.json

@@ -0,0 +1,23 @@
+{
+  "output_dir": "/tmp/nexus_qwen35_0p8b_smoke_adapter",
+  "overwrite_output_dir": true,
+  "do_train": true,
+  "max_steps": 10,
+  "per_device_train_batch_size": 8,
+  "gradient_accumulation_steps": 1,
+  "learning_rate": 2e-5,
+  "warmup_ratio": 0.0,
+  "logging_steps": 1,
+  "save_strategy": "no",
+  "bf16": true,
+  "gradient_checkpointing": true,
+  "remove_unused_columns": false,
+  "dataloader_drop_last": true,
+  "negatives_cross_device": false,
+  "temperature": 0.02,
+  "sentence_pooling_method": "last_token",
+  "normalize_embeddings": true,
+  "sub_batch_size": null,
+  "kd_loss_type": "kl_div",
+  "report_to": "none"
+}

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16e2120f0438146e52f34462e44362da7b6fc2498152887fa72eb52389aa197
+size 19989442

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}