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

README.md

@@ -0,0 +1,71 @@
+---
+license: mit
+base_model:
+- Qwen/Qwen3.8-2.4T-A95B
+library_name: transformers
+---
+
+# Qwen3.8-1.0B-A0.6B
+
+This is a tiny version of [Qwen/Qwen3.8-2.4T-A95B](https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B) created for testing and development.
+
+## Model Details
+
+- **Base Model**: Qwen/Qwen3.8-2.4T-A95B
+- **Architecture**: qwen3_5_moe_text (Qwen3_5MoeForCausalLM)
+- **Total Parameters**: 0.97B
+- **Activated Parameters**: ~0.6B
+
+## Configuration Changes
+
+The following parameters were reduced from the original model:
+
+| Parameter | Original | Tiny |
+|---|---|---|
+| num_hidden_layers | 92 | 8 |
+| hidden_size | 8192 | 1024 |
+| num_attention_heads | 64 | 8 |
+| num_key_value_heads | 4 | 2 |
+| head_dim | 256 | 128 |
+| num_experts | 512 | 16 |
+| num_experts_per_tok | 10 | 2 |
+| moe_intermediate_size | 2048 | 1024 |
+| shared_expert_intermediate_size | 2048 | 1024 |
+| linear_key_head_dim | 128 | 64 |
+| linear_num_key_heads | 16 | 4 |
+| linear_num_value_heads | 128 | 16 |
+| linear_value_head_dim | 128 | 64 |
+| mtp_num_hidden_layers | 1 | 0 |
+
+## Checkpoint Structure
+
+Single safetensors file with packed expert format (`experts.gate_up_proj`, `experts.down_proj`) matching the original checkpoint structure. Layer types follow the [linear, linear, linear, full] x 2 pattern from the original.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("Qwen3.8-1.0B-A0.6B", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("Qwen3.8-1.0B-A0.6B")
+
+input_ids = tokenizer("According to all known laws", return_tensors="pt").input_ids.to(model.device)
+output = model.generate(input_ids, max_new_tokens=20)
+print(tokenizer.decode(output[0]))
+```
+
+## Creation Process
+
+This model was created using the llm-compressor `create-tiny-model` claude skill.
+
+1. Inspected the original 2.4T parameter MoE model configuration
+2. Reduced all dimensions to create a ~1B parameter model while preserving the hybrid linear/full attention architecture
+3. Fine-tuned on a toy dataset to achieve perplexity ~1.0
+4. Converted checkpoint format to match the original (packed experts, correct tensor naming)
+5. Validated model loading and generation
+
+## Notes
+
+- The model preserves the hybrid attention pattern: 6 linear attention layers and 2 full attention layers in a [linear, linear, linear, full] x 2 pattern
+- MTP (multi-token prediction) layers are removed (mtp_num_hidden_layers=0) as they are not needed for the tiny model
+- Expert weights use the packed format (gate_up_proj fused, stacked across experts) matching the original checkpoint

chat_template.jinja

@@ -0,0 +1,142 @@
+{%- macro render_content(content) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if '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 enable_thinking is defined and enable_thinking is false %}
+    {{- raise_exception('Disabling thinking is not supported.') }}
+{%- endif %}
+{%- set reasoning_instructions = '' %}
+{%- 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 %}
+{%- 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)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content)|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)|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)|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<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen3_5MoeForCausalLM"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "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": 64,
+  "linear_num_key_heads": 4,
+  "linear_num_value_heads": 16,
+  "linear_value_head_dim": 64,
+  "mamba_ssm_dtype": "float32",
+  "max_position_embeddings": 262144,
+  "model_type": "qwen3_5_moe_text",
+  "moe_intermediate_size": 1024,
+  "mtp_num_hidden_layers": 0,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 8,
+  "num_experts": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "output_gate_type": "swish",
+  "output_router_logits": false,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 1024,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false,
+  "vocab_size": 248320
+}

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": "5.16.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5773d6e41575364b17ec9f6a5fe14130d7550caf011bcbcbafa2e81c6177e63f
+size 1932276024

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b95cc075eb3b4ad8454383694d3e4189ebca27abc944d0a51dfa4e1d57024d
+size 19989603

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,
+  "local_files_only": false,
+  "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+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3c28452853be57cc7a98256773bea178871fd831abc6b79a5df0cf957888b5
+size 5201