Add 13 files

.gitattributes

@@ -33,3 +33,5 @@ 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
+training-metrics.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,99 @@
+---
+base_model: Qwen/Qwen3.5-0.8B
+library_name: peft
+license: other
+tags:
+  - lora
+  - peft
+  - fine-tuned
+  - adaption
+---
+
+# adaption_general_knowledge_qa
+
+## Model Training
+
+A LORA fine-tune of `Qwen/Qwen3.5-0.8B`. This model was trained with supervised fine-tuning (SFT) using [Adaption](https://adaptionlabs.ai)'s AutoScientist on the general_knowledge_qa dataset.
+
+
+![Training metrics](training-metrics.png)
+
+### AutoScientist Config
+
+```json
+{
+  "finetune_job_id": "69d2d2ca-5984-45d7-8e07-f24a59d39424",
+  "training_experiment_id": "b3805568-3565-4d1c-ad72-4e8173aee82f",
+  "original_model_name": "Qwen/Qwen3.5-0.8B",
+  "trained_model_name": "adaption_general_knowledge_qa",
+  "training_method": "sft",
+  "training_type": "lora",
+  "data_format": "chat",
+  "hyperparams": {
+    "lora": "true",
+    "lora_r": 16,
+    "n_evals": 5,
+    "n_epochs": 1,
+    "batch_size": "max",
+    "lora_alpha": 32,
+    "lora_dropout": 0,
+    "min_lr_ratio": 0.1,
+    "warmup_ratio": 0.03,
+    "weight_decay": 0,
+    "learning_rate": 0.00001,
+    "max_grad_norm": 2,
+    "base_model_size": "0.8B",
+    "train_on_inputs": "false",
+    "training_method": "sft",
+    "lr_scheduler_type": "cosine",
+    "scheduler_num_cycles": 0.5,
+    "lora_trainable_modules": "q_proj,k_proj,v_proj,o_proj"
+  }
+}
+```
+
+## Training Data
+
+The model was fine-tuned on 3,588 rows of adapted data with the following domain distribution: history (11%), sports (10%), science (9%), geography (7%), entertainment (6%), music (6%), animal-nature (5%), cooking (5%), culture (4%), travel (3%), transportation (3%), technology (2%), corporate-business (2%), governance (2%), medical (2%), games (2%), writing-editing-communication (2%), fitness-sports (2%), academic-education (1%), math (1%), code (1%), language (1%), agriculture (1%), how-to (1%), personal-finance (1%), art (1%), career-workplace (1%), religion (1%), product-advice (1%), parenting-family (1%), personal-growth (1%), fashion-beauty (1%), marketing (0%), architecture-design (0%), data-analysis-visualization (0%), other (0%), legal (0%), dating (0%), market-analysis (0%), news (0%), hr (0%), social (0%), roleplay (0%), literature (0%).
+
+## Model Evaluation
+
+The model was evaluated on an in-distribution held-out test set as well as a broader domain-specific test set to measure generalization.
+
+
+![Win rates](win-rates.png)
+
+
+## How to use
+
+```bash
+pip install torch transformers peft
+```
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+BASE = "Qwen/Qwen3.5-0.8B"
+ADAPTER = "<this-repo-id>"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.float32 if device == "cpu" else torch.bfloat16
+
+base = AutoModelForCausalLM.from_pretrained(BASE, dtype=dtype).to(device)
+model = PeftModel.from_pretrained(base, ADAPTER)
+# Optional: merge the LoRA weights into the base for faster inference
+model = model.merge_and_unload()
+model.eval()
+
+tokenizer = AutoTokenizer.from_pretrained(BASE)
+messages = [{"role": "user", "content": "Hello!"}]
+text = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(device)
+
+with torch.inference_mode():
+    out = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```

adapter_config.json

@@ -0,0 +1,168 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": [
+    "model.visual.blocks.8.mlp.linear_fc1",
+    "model.visual.blocks.4.attn.proj",
+    "model.visual.blocks.6.norm2",
+    "model.visual.blocks.9.norm1",
+    "model.visual.blocks.2.mlp.act_fn",
+    "model.visual.blocks.7.mlp.act_fn",
+    "model.visual.blocks.6.mlp",
+    "model.visual.blocks.6.attn.qkv",
+    "model.visual.blocks.4.attn.qkv",
+    "model.visual.blocks.8.attn.proj",
+    "model.visual.blocks.11.attn.proj",
+    "model.visual.blocks.1.attn",
+    "model.visual.pos_embed",
+    "model.visual.blocks.5.norm1",
+    "model.visual.blocks.10.mlp",
+    "model.visual.blocks.10.norm2",
+    "model.visual.patch_embed",
+    "model.visual.blocks.8.mlp",
+    "model.visual.blocks.10.attn",
+    "model.visual.blocks.3.norm2",
+    "model.visual.blocks.0",
+    "model.visual.blocks.5.attn",
+    "model.visual.blocks.2.attn.proj",
+    "model.visual.blocks.3.attn.proj",
+    "model.visual.blocks.2.norm2",
+    "model.visual.blocks.6.norm1",
+    "model.visual.blocks.10.mlp.linear_fc2",
+    "model.visual.blocks.9.attn.qkv",
+    "model.visual.blocks.9.mlp.linear_fc2",
+    "model.visual.blocks.0.attn",
+    "model.visual.blocks.5.mlp.act_fn",
+    "model.visual.blocks.9.attn.proj",
+    "model.visual.blocks.8",
+    "model.visual.blocks.1.norm1",
+    "model.visual.blocks.1.attn.qkv",
+    "model.visual.blocks.2.mlp",
+    "model.visual.blocks.7.norm2",
+    "model.visual.blocks.7",
+    "model.visual.rotary_pos_emb",
+    "model.visual.blocks.7.mlp",
+    "model.visual.blocks.8.norm2",
+    "model.visual.blocks.11.attn",
+    "model.visual.blocks.1",
+    "model.visual.blocks.7.mlp.linear_fc1",
+    "model.visual.blocks.10",
+    "model.visual.blocks.5.attn.proj",
+    "model.visual.blocks.4.mlp.linear_fc2",
+    "model.visual.blocks.2.norm1",
+    "model.visual.blocks.0.mlp.linear_fc1",
+    "model.visual.blocks.1.mlp",
+    "model.visual.blocks.9.mlp.linear_fc1",
+    "model.visual.blocks.3.norm1",
+    "model.visual.merger",
+    "model.visual.blocks.2.mlp.linear_fc1",
+    "model.visual.blocks.4.mlp",
+    "model.visual.blocks.3.attn.qkv",
+    "model.visual.blocks.5.norm2",
+    "model.visual.blocks.1.norm2",
+    "model.visual.blocks.8.mlp.linear_fc2",
+    "model.visual.blocks.0.norm1",
+    "model.visual.blocks.9.mlp.act_fn",
+    "model.visual.blocks.2",
+    "model.visual.blocks.0.mlp.act_fn",
+    "model.visual.blocks.3.mlp.act_fn",
+    "model.visual.blocks.1.mlp.linear_fc1",
+    "model.visual.blocks.10.norm1",
+    "model.visual.blocks.11.mlp.act_fn",
+    "model.visual.blocks.7.norm1",
+    "model.visual.blocks.4.norm1",
+    "model.visual.blocks.6.attn.proj",
+    "model.visual.blocks.9.mlp",
+    "model.visual.blocks.10.attn.proj",
+    "model.visual.merger.norm",
+    "model.visual.blocks.6.mlp.linear_fc2",
+    "model.visual.blocks.0.mlp",
+    "model.visual.blocks.3.mlp.linear_fc2",
+    "model.visual.blocks.6.attn",
+    "model.visual.blocks.5",
+    "model.visual.blocks.9.norm2",
+    "model.visual.blocks.3.attn",
+    "model.visual.blocks.7.attn.qkv",
+    "model.visual.blocks.3",
+    "model.visual.blocks.8.norm1",
+    "model.visual",
+    "model.visual.blocks.11.norm2",
+    "model.visual.blocks.5.mlp.linear_fc1",
+    "model.visual.blocks.4.norm2",
+    "model.visual.blocks.3.mlp",
+    "model.visual.blocks.6.mlp.act_fn",
+    "model.visual.blocks.7.mlp.linear_fc2",
+    "model.visual.blocks.2.attn",
+    "model.visual.blocks.5.attn.qkv",
+    "model.visual.blocks.6.mlp.linear_fc1",
+    "model.visual.merger.linear_fc1",
+    "model.visual.blocks.11.attn.qkv",
+    "model.visual.blocks.4.mlp.act_fn",
+    "model.visual.blocks.11.mlp",
+    "model.visual.blocks.0.mlp.linear_fc2",
+    "model.visual.blocks.4.mlp.linear_fc1",
+    "model.visual.blocks.6",
+    "model.visual.blocks.9.attn",
+    "model.visual.blocks.8.attn.qkv",
+    "model.visual.blocks.11.norm1",
+    "model.visual.blocks.0.norm2",
+    "model.visual.blocks.8.mlp.act_fn",
+    "model.visual.merger.act_fn",
+    "model.visual.blocks.11.mlp.linear_fc1",
+    "model.visual.blocks.7.attn.proj",
+    "model.visual.blocks.5.mlp.linear_fc2",
+    "model.visual.blocks.1.mlp.act_fn",
+    "model.visual.blocks.10.attn.qkv",
+    "model.visual.blocks.10.mlp.act_fn",
+    "model.visual.blocks",
+    "model.visual.blocks.8.attn",
+    "model.visual.blocks.10.mlp.linear_fc1",
+    "model.visual.blocks.9",
+    "model.visual.blocks.7.attn",
+    "model.visual.blocks.5.mlp",
+    "model.visual.blocks.0.attn.qkv",
+    "model.visual.blocks.11.mlp.linear_fc2",
+    "model.visual.blocks.0.attn.proj",
+    "model.visual.merger.linear_fc2",
+    "model.visual.patch_embed.proj",
+    "model.visual.blocks.11",
+    "model.visual.blocks.2.attn.qkv",
+    "model.visual.blocks.2.mlp.linear_fc2",
+    "model.visual.blocks.3.mlp.linear_fc1",
+    "model.visual.blocks.1.mlp.linear_fc2",
+    "model.visual.blocks.4",
+    "model.visual.blocks.4.attn",
+    "model.visual.blocks.1.attn.proj"
+  ],
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d809b424f54051a039d64f58505ef5be4f3aa15d3eaa51097e08639f8fb21b
+size 4332464

chat_template.jinja

@@ -0,0 +1,151 @@
+{%- 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 %}
+{%- 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 %}

config.json

@@ -0,0 +1,105 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 3584,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 16,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 8,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": false,
+    "vocab_size": 248320,
+    "torch_dtype": "bfloat16"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.1",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 12,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 12,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 1024,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "torch_dtype": "bfloat16"
+}

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "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_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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "eos_token": "<|im_end|>",
+  "image_token": "<|image_pad|>",
+  "pad_token": "<|endoftext|>",
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "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": false,
+  "local_files_only": 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|>",
+  "padding_side": "right",
+  "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": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 4,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 1.869510531425476,
+      "learning_rate": 0.0,
+      "loss": 1.6582717895507812,
+      "step": 1
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 1.4465402364730835,
+      "learning_rate": 1e-05,
+      "loss": 1.39208984375,
+      "step": 2
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 2.276446580886841,
+      "learning_rate": 9.94459753267812e-06,
+      "loss": 1.953125,
+      "step": 3
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 2.215484380722046,
+      "learning_rate": 9.779754323328192e-06,
+      "loss": 1.899658203125,
+      "step": 4
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 1.9182502031326294,
+      "learning_rate": 9.509529358847655e-06,
+      "loss": 1.667724609375,
+      "step": 5
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "eval_loss": 2.453125,
+      "eval_runtime": 10.6216,
+      "eval_samples_per_second": 0.094,
+      "eval_steps_per_second": 0.094,
+      "step": 5
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 2.0919392108917236,
+      "learning_rate": 9.140576474687263e-06,
+      "loss": 1.90869140625,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.093019962310791,
+      "learning_rate": 8.681980515339464e-06,
+      "loss": 1.7752685546875,
+      "step": 7
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.9170184135437012,
+      "learning_rate": 8.14503363531613e-06,
+      "loss": 1.70947265625,
+      "step": 8
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 1.925852656364441,
+      "learning_rate": 7.5429572488279615e-06,
+      "loss": 1.809814453125,
+      "step": 9
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "eval_loss": 2.390625,
+      "eval_runtime": 0.829,
+      "eval_samples_per_second": 1.206,
+      "eval_steps_per_second": 1.206,
+      "step": 9
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.0689780712127686,
+      "learning_rate": 6.890576474687264e-06,
+      "loss": 1.87548828125,
+      "step": 10
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 2.0856761932373047,
+      "learning_rate": 6.20395509268104e-06,
+      "loss": 1.931640625,
+      "step": 11
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.7902768850326538,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 1.6474609375,
+      "step": 12
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 1.6947816610336304,
+      "learning_rate": 4.796044907318961e-06,
+      "loss": 1.75390625,
+      "step": 13
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "eval_loss": 2.328125,
+      "eval_runtime": 0.8257,
+      "eval_samples_per_second": 1.211,
+      "eval_steps_per_second": 1.211,
+      "step": 13
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.8652945756912231,
+      "learning_rate": 4.109423525312738e-06,
+      "loss": 1.800048828125,
+      "step": 14
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.87651526927948,
+      "learning_rate": 3.45704275117204e-06,
+      "loss": 1.70166015625,
+      "step": 15
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.8096357583999634,
+      "learning_rate": 2.854966364683872e-06,
+      "loss": 1.751953125,
+      "step": 16
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 1.9394772052764893,
+      "learning_rate": 2.3180194846605367e-06,
+      "loss": 1.868896484375,
+      "step": 17
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "eval_loss": 2.296875,
+      "eval_runtime": 0.8266,
+      "eval_samples_per_second": 1.21,
+      "eval_steps_per_second": 1.21,
+      "step": 17
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.7789219617843628,
+      "learning_rate": 1.8594235253127373e-06,
+      "loss": 1.80322265625,
+      "step": 18
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 1.8745474815368652,
+      "learning_rate": 1.490470641152345e-06,
+      "loss": 1.703369140625,
+      "step": 19
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.7236051559448242,
+      "learning_rate": 1.2202456766718092e-06,
+      "loss": 1.692138671875,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.77152681350708,
+      "learning_rate": 1.0554024673218808e-06,
+      "loss": 1.63671875,
+      "step": 21
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.28125,
+      "eval_runtime": 0.8292,
+      "eval_samples_per_second": 1.206,
+      "eval_steps_per_second": 1.206,
+      "step": 21
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 21,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7489904145596416.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}