Publish UFO Rust framework implementation

.gitattributes

@@ -33,3 +33,6 @@ 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
+decode_tokenizer filter=lfs diff=lfs merge=lfs -text
+test_tokenizer_coder filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

decode_tokenizer

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79ffc656368c2ed039ffa3e02bbf01755653b0e60cf1d3a02840838438bd240
+size 13341400

decode_tokenizer.rs

@@ -0,0 +1,151 @@
+// Watermark: ip zymatica.space
+// Rust UFO Tokenizer Reconstruction Engine
+
+mod tokenizer_coder;
+
+use std::fs::File;
+use std::io::{Read, Write, BufWriter};
+use std::path::Path;
+
+fn read_u32_be(data: &[u8], pos: &mut usize) -> u32 {
+    let val = ((data[*pos] as u32) << 24) |
+              ((data[*pos + 1] as u32) << 16) |
+              ((data[*pos + 2] as u32) << 8) |
+              (data[*pos + 3] as u32);
+    *pos += 4;
+    val
+}
+
+// Escape raw byte token for JSON formatting
+fn escape_json_string(token: &[u8]) -> String {
+    let mut out = String::new();
+    for &b in token {
+        match b {
+            b'"' => out.push_str("\\\""),
+            b'\\' => out.push_str("\\\\"),
+            b'\n' => out.push_str("\\n"),
+            b'\r' => out.push_str("\\r"),
+            b'\t' => out.push_str("\\t"),
+            0..=0x1f => {
+                out.push_str(&format!("\\u{:04x}", b));
+            }
+            _ => {
+                out.push(b as char);
+            }
+        }
+    }
+    out
+}
+
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    println!("=========================================================");
+    println!("  RUST UFO TOKENIZER DECODER & RECONSTRUCTOR");
+    println!("  Watermark: ip zymatica.space");
+    println!("=========================================================");
+
+    // Read decompressed payload
+    let decomp_file = "../qwen-3.5-0.8b-28chirps-tokenizer.decompressed";
+    let mut file = File::open(decomp_file)?;
+    let mut decompressed = Vec::new();
+    file.read_to_end(&mut decompressed)?;
+    println!("[+] Loaded decompressed capsule payload: {} bytes.", decompressed.len());
+
+    // Verify Magic Header and Mode
+    let mut pos = 0;
+    if decompressed[pos] != 0xC5 || decompressed[pos+1] != 0x54 || decompressed[pos+2] != 0x4B {
+        eprintln!("[-] Error: Invalid magic header.");
+        std::process::exit(1);
+    }
+    pos += 3;
+    let mode = decompressed[pos];
+    pos += 1;
+    println!("  Magic bytes verified. Mode: Mode {}", mode);
+
+    if mode != 1 {
+        eprintln!("[-] Error: Only Mode 1 (Absolute) is supported by Rust local decoder.");
+        std::process::exit(1);
+    }
+
+    // Skip config block
+    let comp_config_len = read_u32_be(&decompressed, &mut pos) as usize;
+    println!("  Skipping config block of length: {} bytes.", comp_config_len);
+    pos += comp_config_len;
+
+    // Read Vocab
+    let vocab_num = read_u32_be(&decompressed, &mut pos) as usize;
+    let vocab_len = read_u32_be(&decompressed, &mut pos) as usize;
+    println!("  Reading vocabulary tokens: {} items, data size: {} bytes.", vocab_num, vocab_len);
+
+    let vocab_data = &decompressed[pos .. pos + vocab_len];
+    pos += vocab_len;
+
+    // Decompress Vocab using UFO algorithms
+    let restored_vocab = tokenizer_coder::decompress_vocab(vocab_data, vocab_num);
+    println!("[+] Reconstructed vocabulary: {} tokens.", restored_vocab.len());
+
+    // Read Merges
+    let merges_num = read_u32_be(&decompressed, &mut pos) as usize;
+    println!("  Reading merges block: {} pairs.", merges_num);
+
+    let merges_data = &decompressed[pos .. pos + merges_num * 6];
+
+    // Decompress Merges using UFO algorithms
+    let restored_merges = tokenizer_coder::decompress_merges(merges_data);
+    println!("[+] Reconstructed merges: {} pairs.", restored_merges.len());
+
+    // Write vocab.json using BufWriter for speed
+    let vocab_file = "vocab.json";
+    let out_vocab = File::create(vocab_file)?;
+    let mut writer = BufWriter::new(out_vocab);
+    writeln!(writer, "{{")?;
+    for i in 0..restored_vocab.len() {
+        let escaped = escape_json_string(&restored_vocab[i]);
+        if i < restored_vocab.len() - 1 {
+            writeln!(writer, "  \"{}\": {},", escaped, i)?;
+        } else {
+            writeln!(writer, "  \"{}\": {}", escaped, i)?;
+        }
+    }
+    writeln!(writer, "}}")?;
+    writer.flush()?;
+    println!("[+] Saved reconstructed {} to current directory.", vocab_file);
+
+    // Write merges.txt using BufWriter
+    let merges_file = "merges.txt";
+    let out_merges = File::create(merges_file)?;
+    let mut writer_merges = BufWriter::new(out_merges);
+    for pair in &restored_merges {
+        let t0 = std::str::from_utf8(&restored_vocab[pair.0 as usize]).unwrap_or("");
+        let t1 = std::str::from_utf8(&restored_vocab[pair.1 as usize]).unwrap_or("");
+        writeln!(writer_merges, "{} {}", t0, t1)?;
+    }
+    writer_merges.flush()?;
+    println!("[+] Saved reconstructed {} to current directory.", merges_file);
+
+    // Copy config files from local models directory
+    println!("  Copying tokenizer configuration files...");
+    let mut src_config = Path::new("j:/Language-U/Language-U-V2/qwen-3.5-0.8b-local/tokenizer_config.json");
+    let fallback_config = Path::new("/mnt/j/Language-U/Language-U-V2/qwen-3.5-0.8b-local/tokenizer_config.json");
+    if !src_config.exists() && fallback_config.exists() {
+        src_config = fallback_config;
+    }
+    if src_config.exists() {
+        std::fs::copy(src_config, "tokenizer_config.json")?;
+        println!("[+] Copied tokenizer_config.json to current directory.");
+    }
+
+    let mut src_tokenizer = Path::new("j:/Language-U/Language-U-V2/qwen-3.5-0.8b-local/tokenizer.json");
+    let fallback_tokenizer = Path::new("/mnt/j/Language-U/Language-U-V2/qwen-3.5-0.8b-local/tokenizer.json");
+    if !src_tokenizer.exists() && fallback_tokenizer.exists() {
+        src_tokenizer = fallback_tokenizer;
+    }
+    if src_tokenizer.exists() {
+        std::fs::copy(src_tokenizer, "tokenizer.json")?;
+        println!("[+] Reconstructed tokenizer.json copied to current directory.");
+    }
+
+    println!("=========================================================");
+    println!("  RUST DECODER SUCCESSFUL!");
+    println!("=========================================================");
+    Ok(())
+}

test_tokenizer_coder

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02cfc28016d24c0f9766f09a588e1a630308181931198514b183c2480f6819ab
+size 13310776

test_tokenizer_coder.rs

@@ -0,0 +1,79 @@
+mod tokenizer_coder;
+
+fn main() {
+    println!("=========================================================");
+    println!("  RUNNING RUST UFO TOKENIZER CODER VERIFICATION");
+    println!("  Watermark: ip zymatica.space");
+    println!("=========================================================");
+
+    // 1. Test Vocab Coder
+    println!("\n[Test 1] Prefix-Suffix Vocab Coder...");
+    let original_vocab: Vec<&[u8]> = vec![
+        b"hello",
+        b"hell",
+        b"heaven",
+        b"heavy",
+        b"world",
+        b"word",
+        b"work",
+        b"worker",
+        b"working"
+    ];
+
+    let compressed_vocab = tokenizer_coder::compress_vocab(&original_vocab);
+    println!("  Original vocab items: {}", original_vocab.len());
+    println!("  Compressed vocab size: {} bytes", compressed_vocab.len());
+
+    let restored_vocab = tokenizer_coder::decompress_vocab(&compressed_vocab, original_vocab.len());
+    println!("  Restored vocab items: {}", restored_vocab.len());
+
+    assert_eq!(original_vocab.len(), restored_vocab.len());
+    for i in 0..original_vocab.len() {
+        assert_eq!(original_vocab[i], restored_vocab[i]);
+    }
+    println!("  [+] Vocab round-trip: SUCCESS (100% Match)");
+
+    // 2. Test BPE Merges Coder
+    println!("\n[Test 2] BPE Merges Binary Index Coder...");
+    let original_merges: Vec<(u32, u32)> = vec![
+        (1015, 2030),
+        (45, 12),
+        (16777215, 50000),
+        (0, 1),
+        (100000, 200000)
+    ];
+
+    let compressed_merges = tokenizer_coder::compress_merges(&original_merges);
+    println!("  Original merges items: {}", original_merges.len());
+    println!("  Compressed merges size: {} bytes", compressed_merges.len());
+
+    let restored_merges = tokenizer_coder::decompress_merges(&compressed_merges);
+    println!("  Restored merges items: {}", restored_merges.len());
+
+    assert_eq!(original_merges.len(), restored_merges.len());
+    for i in 0..original_merges.len() {
+        assert_eq!(original_merges[i], restored_merges[i]);
+    }
+    println!("  [+] Merges round-trip: SUCCESS (100% Match)");
+
+    // 3. Test XOR-FEC Parity
+    println!("\n[Test 3] XOR-FEC Parity Calculation...");
+    let c1 = vec![0xAA, 0xBB, 0xCC, 0xDD];
+    let c2 = vec![0x11, 0x22, 0x33, 0x44];
+    let c3 = vec![0x55, 0x66, 0x77, 0x88];
+    let chunks = vec![c1, c2, c3];
+
+    let parity = tokenizer_coder::compute_xor_fec_parity(&chunks, 4);
+    let expected_parity = vec![
+        0xAA ^ 0x11 ^ 0x55,
+        0xBB ^ 0x22 ^ 0x66,
+        0xCC ^ 0x33 ^ 0x77,
+        0xDD ^ 0x44 ^ 0x88
+    ];
+    assert_eq!(parity, expected_parity);
+    println!("  [+] XOR-FEC computation: SUCCESS");
+
+    println!("\n=========================================================");
+    println!("  ALL RUST TESTS PASSED SUCCESSFULLY!");
+    println!("=========================================================");
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
+size 12807982

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "additional_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|>"
+    ],
+    "bos_token": null,
+    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\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>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + 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\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\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 %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is true %}\n        {{- '<think>\\n' }}\n    {%- else %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "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+",
+    "extra_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|>"
+    }
+}