Upload folder using huggingface_hub

.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

.meta.json

@@ -0,0 +1,15 @@
+{
+  "Pillow": "12.2.0",
+  "accelerate": "1.15.0",
+  "av": "19.0.2",
+  "flashinfer-python": "0.7.2",
+  "huggingface_hub": "1.33.0",
+  "kernels": "0.17.0",
+  "numpy": "2.3.5",
+  "safetensors": "0.8.0",
+  "sglang": "0.5.23.dev384+g9ab74b851",
+  "tiny-random": "0.2.0",
+  "torch": "2.14.1",
+  "torchcodec": "0.17.0",
+  "transformers": "5.19.0"
+}

README.md

@@ -0,0 +1,152 @@
+---
+library_name: transformers
+base_model:
+- Qwen/Qwen3.8-27B
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B).
+
+Structural comparison with `Qwen/Qwen3.8-27B`:
+
+| Feature | Source | Tiny |
+|---|---|---|
+| Input modalities | Text, image, video | Same |
+| Vocabulary | 248,320 | Same; special-token IDs preserved |
+| Backbone layers | 64 | 8 |
+| Hidden size | 5,120 | 128 |
+| Attention Q/KV heads; head dim | 24/4; 256 | 12/2; 128 |
+| Attention cycle | 3 linear + 1 full | Same; two complete cycles |
+| Linear-attention key/value heads | 16/48 | 2/6 |
+| Linear-attention key/value head dim | 128/128 | Same |
+| MLP intermediate size | 17,408 | 512 |
+| MTP | 1 full-attention layer; shared embeddings | Same |
+| Vision layers / hidden size | 27 / 1,152 | 2 / 64 |
+| Vision patch / temporal patch / merge | 16 / 2 / 2 | Same |
+| Vision output size | 5,120 | 128 |
+| Checkpoint format | BF16 | Same |
+
+| File path | Size |
+|------|------|
+| model.safetensors | 139.9MB |
+
+
+### Example usage:
+
+- SGLang
+
+  - Runs with TP=2, the embedded NEXTN/MTP layer, and CUDA Graph.
+  - Verified for text, image-plus-text and video-plus-text on two NVIDIA H20 GPUs;
+    see Test environment for dependency versions.
+
+```bash
+model_id=tiny-random/qwen3.8
+SGLANG_JIT_DEEPGEMM_FAST_WARMUP=1 sglang serve \
+  --model-path $model_id \
+  --tp-size 2 \
+  --speculative-algorithm NEXTN \
+  --speculative-num-steps 3 \
+  --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 4 \
+  --context-length 4096 \
+  --max-total-tokens 4096 \
+  --chunked-prefill-size 512 \
+  --mem-fraction-static 0.4 \
+  --cuda-graph-config '{"decode": {"bs": [1, 2, 4, 8]}}' \
+  --disable-custom-all-reduce
+```
+
+- Transformers
+
+```python
+import torch
+from PIL import Image
+from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
+
+model_id = "tiny-random/qwen3.8"
+model = Qwen3_5ForConditionalGeneration.from_pretrained(
+    model_id, dtype=torch.bfloat16, device_map="cuda", attn_implementation="sdpa",
+)
+processor = AutoProcessor.from_pretrained(model_id)
+messages = [{"role": "user", "content": [
+    {"type": "image", "image": Image.new("RGB", (64, 64), (220, 30, 30))},
+    {"type": "text", "text": "Describe this image."},
+]}]
+inputs = processor.apply_chat_template(
+    messages, tokenize=True, add_generation_prompt=True,
+    return_dict=True, return_tensors="pt",
+).to(model.device)
+output = model.generate(**inputs, do_sample=False, max_new_tokens=10)
+print(processor.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```
+
+### Codes to create this repo:
+
+<details><summary>Click to expand</summary>
+
+```python
+import json
+from pathlib import Path
+
+import torch
+from huggingface_hub import hf_hub_download
+from transformers import AutoConfig, AutoModelForImageTextToText, AutoProcessor, GenerationConfig, set_seed
+# Creation helpers: pip install git+https://github.com/yujiepan/tiny-random.git
+from tiny_random.qwen_utils import add_qwen_mtp, save_random_qwen_checkpoint
+
+source_model_id = "Qwen/Qwen3.8-27B"
+save_folder = "/tmp/tiny-random/qwen38"
+source_revision = '1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0'
+set_seed(42)
+folder = Path(save_folder)
+folder.mkdir(parents=True, exist_ok=True)
+raw = json.loads(Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text())
+raw["text_config"].update(
+    hidden_size=128, head_dim=128, num_hidden_layers=8,
+    layer_types=(["linear_attention"] * 3 + ["full_attention"]) * 2,
+    num_attention_heads=12, num_key_value_heads=2,
+    linear_num_key_heads=2, linear_num_value_heads=6,
+    linear_key_head_dim=128, linear_value_head_dim=128,
+    intermediate_size=512,
+)
+raw["text_config"]["rope_parameters"]["mrope_section"] = [6, 5, 5]
+raw["vision_config"].update(depth=2, hidden_size=64, intermediate_size=128, num_heads=2, out_hidden_size=128)
+(folder / "config.json").write_text(json.dumps(raw, indent=2))
+config = AutoConfig.from_pretrained(folder)
+model = AutoModelForImageTextToText.from_config(config, dtype=torch.bfloat16)
+add_qwen_mtp(model, model.model.language_model)
+save_random_qwen_checkpoint(model, folder)
+AutoProcessor.from_pretrained(source_model_id, revision=source_revision).save_pretrained(folder)
+GenerationConfig.from_pretrained(source_model_id, revision=source_revision).save_pretrained(folder)
+```
+
+</details>
+
+### Printing the model:
+
+<details><summary>Click to expand</summary>
+
+```text
+Qwen3.8 VL: 8 backbone layers + 1 MTP layer; hidden_size=128
+```
+
+</details>
+
+### Test environment:
+
+- Pillow: 12.2.0
+- accelerate: 1.15.0
+- av: 19.0.2
+- flashinfer-python: 0.7.2
+- huggingface_hub: 1.33.0
+- kernels: 0.17.0
+- numpy: 2.3.5
+- safetensors: 0.8.0
+- sglang: 0.5.23.dev384+g9ab74b851
+- tiny-random: 0.2.0
+- torch: 2.14.1
+- torchcodec: 0.17.0
+- transformers: 5.19.0
+
+### Change log:
+
+- 2026-10-23: Initial version.

chat_template.jinja

@@ -0,0 +1,170 @@
+{%- 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 %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# 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 %}
+        {%- if content %}
+            {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + content + '<|im_end|>\n' }}
+        {%- elif reasoning_instructions %}
+            {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+        {%- endif %}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|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 %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or preserve_thinking is true or 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 and tool_call.arguments != '' %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- 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 false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,84 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen3_5",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 128,
+    "initializer_range": 0.02,
+    "intermediate_size": 512,
+    "layer_types": [
+      "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": 2,
+    "linear_num_value_heads": 6,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 2,
+    "output_gate_type": "swish",
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        6,
+        5,
+        5
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0.dev0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 2,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 64,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 128,
+    "model_type": "qwen3_5",
+    "num_heads": 2,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 128,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 248044,
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.19.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad7d04172397ad42753662b4786257103b27440fd2bb64c07663c37da9e5135
+size 139932696

processor_config.json

@@ -0,0 +1,61 @@
+{
+  "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,
+    "max_video_tokens": 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:a5cd9732badce41de57e6efce8302930ded1c1188c5f81feb2bd6c24c4a1941f
+size 19989339

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "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",
+  "extra_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|>"
+  ],
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "merges_file": null,
+  "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": "Qwen3_5Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}