Upload folder using huggingface_hub

.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
+llm.mnn filter=lfs diff=lfs merge=lfs -text
+llm.mnn.weight filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,66 @@
+# TokForge Acceleration Pack — Draft Model
+
+**Qwen3-0.6B (MNN)** draft model for speculative decoding in [TokForge](https://tokforge.ai).
+
+## What is this?
+
+This is a curated, ready-to-use 0.6B parameter draft model packaged for TokForge's speculative decoding pipeline. Speculative decoding uses a small, fast "draft" model to propose candidate tokens, which are then verified in parallel by the larger "target" model. This amortizes the cost of target model inference and delivers significant speed improvements.
+
+## Performance
+
+Tested on Snapdragon 8 Elite 2 (SM8850 / Adreno 840):
+
+| Target Model | Baseline (tok/s) | With Spec-Decode (tok/s) | Improvement |
+|---|---|---|---|
+| Qwen3-8B (OpenCL) | 11.41 | 19.60 | **+72%** |
+| Qwen3.5-9B (CPU) | 9.55 | 16.67 | **+75%** |
+
+Improvements vary by device and target model. Typical range: **+18-75%** decode speed on flagship SoCs (SM8850, SM8650).
+
+## Compatible Target Models
+
+- Qwen3-4B (MNN, OpenCL or CPU)
+- Qwen3-8B (MNN, OpenCL)
+- Qwen3-14B (MNN, OpenCL, 24GB+ RAM devices)
+- Qwen3.5-9B (MNN, CPU)
+
+## Installation
+
+### Automatic (Recommended)
+
+In TokForge: **Settings > Advanced > Speculative Decoding > Download Acceleration Pack**
+
+The app will download and configure the draft model automatically.
+
+### Manual
+
+1. Download all files from this repository
+2. Copy them to: `<device>/Android/data/dev.tokforge/files/models/spec-decode-draft/`
+3. Enable speculative decoding in TokForge Settings > Advanced
+
+## Files
+
+| File | Size | Description |
+|---|---|---|
+| `llm.mnn` | ~450 KB | MNN model graph |
+| `llm.mnn.weight` | ~430 MB | Model weights |
+| `tokenizer.txt` | ~3 MB | Tokenizer vocabulary |
+| `config.json` | <1 KB | Model configuration |
+| `llm_config.json` | ~5 KB | LLM inference configuration |
+| `config_cpu.json` | <1 KB | CPU backend configuration for draft inference |
+| `draft_config_cpu.json` | <1 KB | Draft-specific CPU configuration |
+
+## Technical Details
+
+- **Architecture**: Qwen3-0.6B (28 transformer layers, 1024 hidden dim)
+- **Format**: MNN (Mobile Neural Network by Alibaba)
+- **Backend**: CPU with single-thread, low-precision inference for minimal draft overhead (~21ms/token)
+- **Optimal draft length**: d=2 for 8B targets, d=3 for 9B targets
+
+## Source
+
+Based on [taobao-mnn/Qwen3-0.6B-MNN](https://huggingface.co/taobao-mnn/Qwen3-0.6B-MNN), repackaged with TokForge-specific draft configurations.
+
+## License
+
+This model inherits the license from [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B). See the original model card for license terms.

config.json

@@ -0,0 +1,21 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
+    "backend_type": "cpu",
+    "thread_num": 4,
+    "precision": "low",
+    "memory": "low",
+    "sampler_type": "mixed",
+    "mixed_samplers": [
+        "penalty",
+        "topK",
+        "topP",
+        "min_p",
+        "temperature"
+    ],
+    "penalty": 1.1,
+    "temperature": 0.6,
+    "topP": 0.95,
+    "topK": 20,
+    "min_p": 0
+}

config_cpu.json

@@ -0,0 +1,9 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
+    "backend_type": "cpu",
+    "thread_num": 1,
+    "precision": "low",
+    "power": "high",
+    "sampler_type": "greedy"
+}

draft_config_cpu.json

@@ -0,0 +1,9 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
+    "backend_type": "cpu",
+    "thread_num": 1,
+    "precision": "low",
+    "power": "high",
+    "sampler_type": "greedy"
+}

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d426c65a5159c938ccc237cdfbd982137f276804f27b414ca0ecf3fc0a660f8c
+size 461520

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953afb7e0165818add34a7a6caf0af5d0ed9428da102eb22c9b98ee9da292e9f
+size 450810338

llm_config.json

@@ -0,0 +1,28 @@
+{
+    "hidden_size": 1024,
+    "layer_nums": 28,
+    "attention_mask": "float",
+    "key_value_shape": [
+        2,
+        1,
+        0,
+        8,
+        128
+    ],
+    "bos": "",
+    "system_prompt_template": "<|im_start|>system\n%s<|im_end|>\n",
+    "user_prompt_template": "<|im_start|>user\n%s<|im_end|>\n",
+    "assistant_prompt_template": "<|im_start|>assistant\n%s<|im_end|>\n",
+    "is_visual": false,
+    "jinja": {
+        "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+        "eos": "<|im_end|>"
+    },
+    "tie_embeddings": [
+        275780066,
+        431362530,
+        19447808,
+        8,
+        64
+    ]
+}