Instructions to use pipenetwork/LongCat-2.0-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/LongCat-2.0-6bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("pipenetwork/LongCat-2.0-6bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use pipenetwork/LongCat-2.0-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/LongCat-2.0-6bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "pipenetwork/LongCat-2.0-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pipenetwork/LongCat-2.0-6bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/LongCat-2.0-6bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default pipenetwork/LongCat-2.0-6bit

Run Hermes

hermes

OpenClaw new

How to use pipenetwork/LongCat-2.0-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/LongCat-2.0-6bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "pipenetwork/LongCat-2.0-6bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use pipenetwork/LongCat-2.0-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pipenetwork/LongCat-2.0-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pipenetwork/LongCat-2.0-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pipenetwork/LongCat-2.0-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

pipenetwork commited on 10 days ago

Commit

deed08f

verified ·

1 Parent(s): 1d83ec5

Add files using upload-large-folder tool

Browse files

Files changed (50) hide show

README.md +9 -0
chat_template.jinja +190 -0
config.json +374 -0
generation_config.json +7 -0
model-00010-of-00261.safetensors +3 -0
model-00015-of-00261.safetensors +3 -0
model-00016-of-00261.safetensors +3 -0
model-00022-of-00261.safetensors +3 -0
model-00027-of-00261.safetensors +3 -0
model-00028-of-00261.safetensors +3 -0
model-00049-of-00261.safetensors +3 -0
model-00051-of-00261.safetensors +3 -0
model-00052-of-00261.safetensors +3 -0
model-00054-of-00261.safetensors +3 -0
model-00063-of-00261.safetensors +3 -0
model-00066-of-00261.safetensors +3 -0
model-00069-of-00261.safetensors +3 -0
model-00071-of-00261.safetensors +3 -0
model-00087-of-00261.safetensors +3 -0
model-00090-of-00261.safetensors +3 -0
model-00095-of-00261.safetensors +3 -0
model-00103-of-00261.safetensors +3 -0
model-00106-of-00261.safetensors +3 -0
model-00109-of-00261.safetensors +3 -0
model-00111-of-00261.safetensors +3 -0
model-00129-of-00261.safetensors +3 -0
model-00131-of-00261.safetensors +3 -0
model-00134-of-00261.safetensors +3 -0
model-00137-of-00261.safetensors +3 -0
model-00142-of-00261.safetensors +3 -0
model-00147-of-00261.safetensors +3 -0
model-00148-of-00261.safetensors +3 -0
model-00170-of-00261.safetensors +3 -0
model-00175-of-00261.safetensors +3 -0
model-00183-of-00261.safetensors +3 -0
model-00186-of-00261.safetensors +3 -0
model-00189-of-00261.safetensors +3 -0
model-00203-of-00261.safetensors +3 -0
model-00211-of-00261.safetensors +3 -0
model-00214-of-00261.safetensors +3 -0
model-00223-of-00261.safetensors +3 -0
model-00226-of-00261.safetensors +3 -0
model-00229-of-00261.safetensors +3 -0
model-00247-of-00261.safetensors +3 -0
model-00250-of-00261.safetensors +3 -0
model-00255-of-00261.safetensors +3 -0
model.safetensors.index.json +0 -0
special_tokens_map.json +30 -0
tokenization_llama.py +231 -0
tokenizer_config.json +1811 -0

README.md ADDED Viewed

	@@ -0,0 +1,9 @@

+---
+library_name: mlx
+pipeline_tag: text-generation
+tags: [mlx, longcat]
+license: mit
+base_model: meituan-longcat/LongCat-2.0-FP8
+---
+# pipenetwork/LongCat-2.0-6bit
+6-bit MLX quant of LongCat-2.0 (from FP8 source). Requires mlx-lm PR #1464: `pip install git+https://github.com/ml-explore/mlx-lm.git@refs/pull/1464/head`

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,190 @@

+{%- set tool_choice = tool_choice | default('auto') -%}
+{%- set enable_thinking = enable_thinking | default(true) -%}
+{%- set save_history_reasoning_content = save_history_reasoning_content | default(true) -%}
+{%- set ns = namespace(final_messages = [], tool_types = [], last_query_index = -1) -%}
+{%- for message in messages -%}
+    {%- set role = message.get('role') -%}
+    {%- set c = message.get('content') -%}
+    {%- if c is string -%}
+        {%- set ns.final_messages = ns.final_messages + [message] -%}
+    {%- elif c is iterable and c is not mapping -%}
+        {%- set parts = namespace(text=[], thinking=[], tool_calls=[], tool_results=[]) -%}
+        {%- for item in c -%}
+            {%- if item['type'] == 'text' -%}
+                {%- set parts.text = parts.text + [item['text']] -%}
+            {%- elif item['type'] == 'thinking' -%}
+                {%- if item['thinking'] -%}
+                    {%- set parts.thinking = parts.thinking + [item['thinking']] -%}
+                {%- endif -%}
+            {%- elif item['type'] == 'tool_use' -%}
+                {%- set parts.tool_calls = parts.tool_calls + [{
+                    'id': item['id'],
+                    'type': 'function',
+                    'function': {
+                        'name': item['name'],
+                        'arguments': item['input']
+                    }
+                }] -%}
+            {%- elif item['type'] == 'tool_result' -%}
+                {%- set parts.tool_results = parts.tool_results + [{
+                    'role': 'tool',
+                    'name': item.get('name', ''),
+                    'tool_call_id': item['tool_use_id'],
+                    'content': item['content']
+                }] -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- set ns.final_messages = ns.final_messages + parts.tool_results -%}
+        {%- if not (parts.tool_results | length > 0 and parts.text | length == 0 and role == 'user') -%}
+            {%- set ns.final_messages = ns.final_messages + [{
+                'role': role,
+                'content': parts.text | join(''),
+                'reasoning_content': parts.thinking | join(''),
+                'tool_calls': parts.tool_calls
+            }] -%}
+        {%- endif -%}
+    {%- else -%}
+        {%- set ns.final_messages = ns.final_messages + [message] -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- set messages = ns.final_messages -%}
+{%- for idx in range(messages|length) -%}
+    {%- set msg = messages[idx] -%}
+    {%- if msg.role == 'user' -%}
+        {%- set ns.last_query_index = idx -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- if tools and tool_choice != 'none' -%}
+    {{- "<longcat_tool_declare>\n" -}}
+    {{- "# Tools\n" -}}
+    {{- "You have access to the following tools:\n\n" -}}
+    {%- for tool in tools -%}
+        {%- if tool.type not in ns.tool_types -%}
+            {%- set ns.tool_types = ns.tool_types + [tool.type] -%}
+            {{- "## Tool namespace: " ~ tool.type ~ "\n\n" -}}
+        {%- endif -%}
+        {%- if tool.type == 'code_interpreter' -%}
+            {%- set tool = {"type":"code_interpreter","function":{"name":"code_interpreter_preview","description":"The code will be executed in a stateful Jupyter notebook sandbox environment, only supports local computation, data processing, and file operations.\nCode sandbox environment (network isolated) Any external network requests or online API calls are prohibited.\nIf online functionality is needed, please use other permitted tools.\nCode will respond with the output of the execution or time out after 60.0 seconds. ","parameters":{"type":"object","properties":{"language":{"type":"string","description":"The programming language of the code to be executed. Available values: python (Default), java, go, js, ts, c, c++."},"code":{"type":"string","description":"Python code to be executed must not include the following:\n- Importing network libraries such as requests, httplib, etc.\n- Any form of HTTP requests.\n- External API calls.\n- Network port operations. Example: ```python\nimport pandas as pd\npd.DataFrame({'A':[1,2]})\n```"},"timeout":{"type":"number","description":"The maximum execution time of the code, in seconds. Default is 60.0."}}},"required":["code"]}} -%}
+        {%- endif -%}
+        {{- "### Tool name: " + tool.function.name + "\n" -}}
+        {{- "Description: " + tool.function.description + "\n\n" -}}
+        {{- "InputSchema: " + tool.function.parameters | tojson(ensure_ascii=False) + "\n\n" -}}
+    {%- endfor -%}
+    {{- '**Note**: For each function call, output the function name and arguments within the following XML format:\n<longcat_tool_call>{function-name}\n<longcat_arg_key>{arg-key-1}</longcat_arg_key>\n<longcat_arg_value>{arg-value-1}</longcat_arg_value>\n<longcat_arg_key>{arg-key-2}</longcat_arg_key>\n<longcat_arg_value>{arg-value-2}</longcat_arg_value>\n...\n</longcat_tool_call>\n' -}}
+    {{- "</longcat_tool_declare>"-}}
+{%- endif -%}
+{%- for msg in messages -%}
+    {%- if msg.role == "system" -%}
+        {{- "<longcat_system>" + msg.content -}}
+    {%- elif msg.role == "user" -%}
+        {{- "<longcat_user>" -}}
+        {%- if msg["files"] -%}
+            {{- '<longcat_files>\n' ~ msg.files | tojson(indent=2) ~ '\n</longcat_files>' -}}
+        {%- endif -%}
+        {{- msg.content -}}
+        {%- if save_history_reasoning_content and enable_thinking is not none -%}
+            {%- if loop.last or messages[loop.index0 + 1].role != 'assistant' -%}
+                {# pass #}
+            {%- else -%}
+                {%- if enable_thinking == true -%}
+                    {{- " /think_on" -}}
+                    {%- if thinking_budget -%}
+                        {%- if thinking_budget < 1024 -%}
+                            {%- set thinking_budget = 1024 -%}
+                        {%- endif -%}
+                        {{- "\nthinking_budget: < " ~ thinking_budget ~ "." -}}
+                    {%- endif -%}
+                    {{- " " -}}
+                {%- elif enable_thinking == false -%}
+                    {{- " /think_off " -}}
+                {%- endif -%}
+            {%- endif -%}
+        {%- elif loop.index0 >= ns.last_query_index and enable_thinking is not none -%}
+            {%- if loop.last or messages[loop.index0 + 1].role != 'assistant' -%}
+                {# pass #}
+            {%- else -%}
+                {%- if enable_thinking == true -%}
+                    {{- " /think_on" -}}
+                    {%- if thinking_budget -%}
+                        {%- if thinking_budget < 1024 -%}
+                            {%- set thinking_budget = 1024 -%}
+                        {%- endif -%}
+                        {{- "\nthinking_budget: < " ~ thinking_budget ~ "." -}}
+                    {%- endif -%}
+                    {{- " " -}}
+                {%- elif enable_thinking == false -%}
+                    {{- " /think_off " -}}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif msg.role == "assistant" -%}
+        {{- "<longcat_assistant>" -}}
+        {%- if save_history_reasoning_content == true or loop.index0 > ns.last_query_index -%}
+            {%- if enable_thinking == true -%}
+                {%- if msg.reasoning_content -%}
+                    {%- set reasoning_content = msg.reasoning_content | trim -%}
+                    {{- "<longcat_think>\n" ~ reasoning_content ~ "\n</longcat_think>\n" -}}
+                {%- else -%}
+                    {{- "<longcat_think>\n\n</longcat_think>\n" -}}
+                {%- endif -%}
+            {%- elif enable_thinking == false -%}
+                {{- "<longcat_think>\n\n</longcat_think>\n" -}}
+            {%- endif -%}
+        {%- endif -%}
+        {%- if msg.content -%}
+            {{- msg.content -}}
+        {%- endif -%}
+        {%- if msg.tool_calls -%}
+            {%- for tool_call in msg.tool_calls -%}
+                {{- "<longcat_tool_call>" ~ tool_call.function.name ~ "\n" -}}
+                {%- set _args = tool_call.function.arguments -%}
+                {%- for k, v in _args.items() -%}
+                    {{- "<longcat_arg_key>" ~ k ~ "</longcat_arg_key>\n" -}}
+                    {{- "<longcat_arg_value>" ~ (v if v is string else v | tojson(ensure_ascii=False)) ~ "</longcat_arg_value>\n" -}}
+                {% endfor -%}
+                {{- "</longcat_tool_call>\n" -}}
+            {%- endfor -%}
+        {%- endif -%}
+        {{- "</longcat_s>" -}}
+    {%- elif msg.role == "tool" -%}
+        {%- if messages[loop.index0 - 1].role != "tool" -%}
+            {{- "<longcat_observation>" -}}
+        {%- endif -%}
+        {{- "<longcat_tool_response>" ~ msg.name ~ "\n" ~ msg.content ~ "</longcat_tool_response>" -}}
+        {%- if loop.index0 == messages|length - 1 -%}
+            {# pass #}
+        {%- elif (save_history_reasoning_content or loop.index0 > ns.last_query_index) and messages[loop.index0 + 1].role != "tool" -%}
+            {%- if enable_thinking == true -%}
+                {{- " /think_on" -}}
+                {%- if thinking_budget -%}
+                    {%- if thinking_budget < 1024 -%}
+                        {%- set thinking_budget = 1024 -%}
+                    {%- endif -%}
+                    {{- "\nthinking_budget: < " ~ thinking_budget ~ "." -}}
+                {%- endif -%}
+                {{- " " -}}
+            {%- elif enable_thinking == false -%}
+                {{- " /think_off " -}}
+            {%- endif -%}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if enable_thinking == true -%}
+        {{- " /think_on" -}}
+        {%- if thinking_budget -%}
+            {%- if thinking_budget < 1024 -%}
+                {%- set thinking_budget = 1024 -%}
+            {%- endif -%}
+            {{- "\nthinking_budget: < " ~ thinking_budget ~ "." -}}
+        {%- endif -%}
+        {{- " <longcat_assistant><longcat_think>" -}}
+    {%- elif enable_thinking == false -%}
+        {{- " /think_off <longcat_assistant><longcat_think>\n\n</longcat_think>\n" -}}
+    {%- else -%}
+        {{- " /think_off <longcat_assistant><longcat_think>\n\n</longcat_think>\n" -}}
+    {%- endif -%}
+{%- endif -%}

config.json ADDED Viewed

	@@ -0,0 +1,374 @@

+{
+    "architectures": [
+        "LongcatCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_method": "MLA",
+    "bos_token_id": 1,
+    "cli_factor": 2,
+    "disable_quant_module": [],
+    "dsa_mtp_cli": true,
+    "eos_token_id": 2,
+    "expert_ffn_hidden_size": 2048,
+    "ffn_hidden_size": 12288,
+    "hidden_size": 8192,
+    "index_head_dim": 128,
+    "index_init_tokens": 16,
+    "index_k_norm_type": "rms",
+    "index_local_tokens": 1024,
+    "index_n_heads": 32,
+    "index_topk": 2048,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 262144,
+    "mla_scale_kv_lora": true,
+    "mla_scale_q_lora": true,
+    "model_type": "longcat2",
+    "moe_impl": "mix",
+    "moe_switch_token_num": 1024,
+    "moe_topk": 12,
+    "mtp_disable_over_tokenizer": true,
+    "mtp_num_layers": 3,
+    "mtp_replicate_modules": true,
+    "n_routed_experts": 768,
+    "num_attention_heads": 64,
+    "num_layers": 38,
+    "oe_neighbor_num": 5,
+    "oe_split_num": 4,
+    "oe_vocab_size_ratio": 100.567,
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "quantization": {
+        "group_size": 64,
+        "bits": 6,
+        "mode": "affine",
+        "model.layers.0.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.32.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.33.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.34.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.35.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.36.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.37.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 6,
+        "mode": "affine",
+        "model.layers.0.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.32.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.33.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.34.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.35.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.36.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.37.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "beta_fast": 32,
+        "beta_slow": 1,
+        "factor": 120,
+        "mscale": 1,
+        "mscale_all_dim": 1,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "deepseek_yarn"
+    },
+    "rope_theta": 1000000.0,
+    "routed_scaling_factor": 9,
+    "use_cache": true,
+    "use_mla": 1,
+    "v_head_dim": 128,
+    "vocab_size": 163840,
+    "zero_expert_num": 128,
+    "zero_expert_type": "identity"
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.55.0"
+}

model-00010-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:369f376a607ac3e1b823e484d94ae59ef6a8e744a125c4299a5cabac7cc1bb57
+size 6327132057

model-00015-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:87bc892b610fdfd30c3e2a31e080d606dcbc0b5c21168b4bf5c4ea636f5385cd
+size 527261391

model-00016-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac08668632b2224543551831c4af0fd6a6ca5ad9aff1d459efb3098d8050dd8
+size 6327134361

model-00022-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5e95dd37de31e61bb17190ea09dd6116ae7e65dcd93207f164f73c7e4573b0
+size 6327136666

model-00027-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:545285afc092d206174a0abf3300fc347f0692275020287b4dcebc6369d5ea96
+size 527261777

model-00028-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bd59b70de3fb50ab224a45d01fdf3cdf07e834b0e280d0642499999d81f5da
+size 6327138970

model-00049-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a1bdbdba82c71f7e8455da856916904598871fff8bb74cf22dcfeb595bcc10
+size 805306649

model-00051-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ceb7c476a677db85ca69f7e2e0ecaa6296d5a0def4d4674ef90e518133b9c68
+size 1492046622

model-00052-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:af65e1eccedfa6c6370e8136b4def8c50dd764b8e6ac5e885605341551d942df
+size 9663676576

model-00054-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:60cce66e7fa14c0c5058fda06ea38d90b73d2fb02d8c3483692ad1670cd6f922
+size 9663676574

model-00063-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d723d35994695ecf6bb790d8774ae221710ee3dfaa53154f5b93a28c3ee3991
+size 1492046646

model-00066-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6183bfaf0bb231d25293b21f1d9972149c2b874391b2b0c71d5193ccef92d9f7
+size 9663676574

model-00069-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d22054db22deed03dc60ecdf514ec40d7bb2e1bbf593a8034aa706ff30b837d3
+size 1492046648

model-00071-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a640044fbebef514e3e2736e2dfcd0de4f650e3a206d953932f28d21319a70
+size 805306653

model-00087-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4e528fba84627635379870fe16505b0faa90e08bdedaf67839bb612f444a3952
+size 1492046644

model-00090-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:595021c951a12ab32b4635de35e9051b05ed033d4b018e0d71aea8ed3f908414
+size 9663676574

model-00095-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:52e7f74a14e936e80f692a93610ed1ce922ad2b9435b5fbe1bff17c7e9637452
+size 805306655

model-00103-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9f7a278bd4d016fb29d69c5310dc93c45065d5642536a578b2ed37f6bad02224
+size 805306651

model-00106-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e3abc6564b8e918aa8aa316b4340ce7521a8fb9824f64c81c9407b927e27f678
+size 9663676577

model-00109-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bca44cee47ca0c06ebe0ab3e8e74be6174ce240a615f244e57b9deaacb3c1dbf
+size 805306651

model-00111-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:46f8a420df462bcfdb4c36c449a41906bfff773c5bc128166b32454464f1e7e7
+size 1492046706

model-00129-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f32676ab9623c1bdb564f0536ea982cffbba053276cb098713c5ff5508e9e39
+size 1492046690

model-00131-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0589909821adb6822c9c041af702752e5c5306472eb9baf8697220684c20221b
+size 805306655

model-00134-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2337500fd3564019089370dfa0d1a7eed939ecd74dd5c390ed0101dafccdd40a
+size 9663676576

model-00137-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:95cb7938c79ed4d3fed89cc326b7e9ab2fc8fa25e5720b4c77910c81c5213219
+size 805306655

model-00142-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a3401b583c92d84e6d396eea4a713524cf65989b5ffb14ee5be5462e426d79
+size 9663676577

model-00147-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cffc7c0926001a3768cf402b57f295f6e8ff46d05e354be9b29068b41e9ec337
+size 1492046702

model-00148-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc42d98d82b699e1d07a3384e53df50456e24da3688b14a1b0fdc6a820737d3
+size 9663676577

model-00170-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7fccacebd72294062d732dc9cf20b21d6dcc47399ca2b766dda39e5c623a1787
+size 9663676576

model-00175-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0268856db99ea72f1a1699deb467f55966cbc2e75d11685dc2d8153b407906df
+size 805306651

model-00183-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8a60f57ffadfe408a62730fd3a3068d3ccf85ff8101508d5ee52b6e1c54e4412
+size 1492046736

model-00186-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9ad05fc2a6bf23da3a4b0521a9fbcbf355ef5610745124ea868058ff481340
+size 9663676575

model-00189-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:74eb0627a85fc53d6cddbe280dad0f73b63db809831cb77f32ce33f601dd98de
+size 1492046740

model-00203-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cab43738a7f6dc006ddf23d16d8980c39e0eac702898037c40d75eb6e0610343
+size 805306655

model-00211-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d2ed79d8be21ae63ecc5f48ea98ab6810772386a9be2beeae8064cc0f518da
+size 805306651

model-00214-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:88194f80b5312cefc50c356ba29b07101929458fbccfd5339e708068773b6bf1
+size 9663676577

model-00223-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:552d4578560aab8e1ebeb72a00ec1e14237cc92e044e66d50e5e01dcfc676df3
+size 805306651

model-00226-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2bda46aad68f4871b42c79229d2185abb7fa19b2fda71d091c7f1667ff658ade
+size 9663676577

model-00229-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d20cdfd5dfe5e475c0b543605a26e5262a06d6917a162aa7a2bef610f5115dcd
+size 805306651

model-00247-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7071dbd90618a32fb59f4fba7e50bf01031764f5fa1b21dc4bb7f3b3e36ca986
+size 805306651

model-00250-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f56323594862355b8edffa2ac40f1e8082d7b3c400a551eb1430d15d5f285c5f
+size 9663676577

model-00255-of-00261.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:18f04dd548c4aa596ff5052b0a66fcc6f5b031de3f53c90c5295970b7da5882b
+size 1492046714

model.safetensors.index.json ADDED Viewed

The diff for this file is too large to render. See raw diff

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "bos_token": {
+    "content": "<longcat_s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</longcat_s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<longcat_pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<longcat_unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenization_llama.py ADDED Viewed

	@@ -0,0 +1,231 @@

+# coding=utf-8
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Tokenization classes for LLaMA."""
+import os
+from shutil import copyfile
+from typing import Any, Dict, List, Optional, Tuple
+import sentencepiece as spm
+from transformers.tokenization_utils import PreTrainedTokenizer
+from transformers.utils import logging
+logger = logging.get_logger(__name__)
+VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
+PRETRAINED_VOCAB_FILES_MAP = {}
+class LlamaTokenizer(PreTrainedTokenizer):
+    """
+    Construct a Llama tokenizer. Based on byte-level Byte-Pair-Encoding.
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+    """
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    model_input_names = ["input_ids", "attention_mask"]
+    def __init__(
+        self,
+        vocab_file,
+        unk_token="<unk>",
+        bos_token="<s>",
+        eos_token="</s>",
+        sp_model_kwargs: Optional[Dict[str, Any]] = None,
+        add_bos_token=True,
+        add_eos_token=False,
+        decode_with_prefix_space=False,
+        **kwargs,
+    ):
+        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
+        super().__init__(bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, **kwargs)
+        self.vocab_file = vocab_file
+        self.add_bos_token = add_bos_token
+        self.add_eos_token = add_eos_token
+        self.decode_with_prefix_space = decode_with_prefix_space
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(vocab_file)
+        self._no_prefix_space_tokens = None
+        """ Initialisation"""
+    @property
+    def no_prefix_space_tokens(self):
+        if self._no_prefix_space_tokens is None:
+            vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
+            self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
+        return self._no_prefix_space_tokens
+    @property
+    def vocab_size(self):
+        """Returns vocab size"""
+        return self.sp_model.get_piece_size()
+    @property
+    def bos_token_id(self) -> Optional[int]:
+        return self.sp_model.bos_id()
+    @property
+    def eos_token_id(self) -> Optional[int]:
+        return self.sp_model.eos_id()
+    def get_vocab(self):
+        """Returns vocab as a dict"""
+        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+    def _tokenize(self, text):
+        """Returns a tokenized string."""
+        return self.sp_model.encode(text, out_type=str)
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        return self.sp_model.piece_to_id(token)
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        token = self.sp_model.IdToPiece(index)
+        return token
+    def _maybe_add_prefix_space(self, tokens, decoded):
+        if tokens and tokens[0] not in self.no_prefix_space_tokens:
+            return " " + decoded
+        else:
+            return decoded
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (string) in a single string."""
+        current_sub_tokens = []
+        out_string = ""
+        prev_is_special = False
+        for token in tokens:
+            # make sure that special tokens are not decoded using sentencepiece model
+            if token in self.all_special_tokens:
+                if not prev_is_special:
+                    out_string += " "
+                out_string += self.sp_model.decode(current_sub_tokens) + token
+                prev_is_special = True
+                current_sub_tokens = []
+            else:
+                current_sub_tokens.append(token)
+                prev_is_special = False
+        out_string += self.sp_model.decode(current_sub_tokens)
+        out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
+        return out_string
+    def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        """
+        Save the vocabulary and special tokens file to a directory.
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+        elif not os.path.isfile(self.vocab_file):
+            with open(out_vocab_file, "wb") as fi:
+                content_spiece_model = self.sp_model.serialized_model_proto()
+                fi.write(content_spiece_model)
+        return (out_vocab_file,)
+    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
+        if self.add_bos_token:
+            bos_token_ids = [self.bos_token_id]
+        else:
+            bos_token_ids = []
+        output = bos_token_ids + token_ids_0
+        if token_ids_1 is not None:
+            output = output + token_ids_1
+        if self.add_eos_token:
+            output = output + [self.eos_token_id]
+        return output
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+        if token_ids_1 is None:
+            return [1] + ([0] * len(token_ids_0)) + [1]
+        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
+        use of token type ids, therefore a list of zeros is returned.
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            `List[int]`: List of zeros.
+        """
+        eos = [self.eos_token_id]
+        if token_ids_1 is None:
+            return len(token_ids_0 + eos) * [0]
+        return len(token_ids_0 + eos + token_ids_1 + eos) * [0]

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,1811 @@

+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<longcat_unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<longcat_s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</longcat_s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<longcat_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<shift_unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<shift_s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</shift_s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<shift_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<mask_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<program_lang>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<|image_placeholder|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<|url_placeholder|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<|hyperlink_placeholder|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<|table_placeholder|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<|equation_placeholder|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<|code_placeholder|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<|reference_placeholder|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<longcat_think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "</longcat_think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<longcat_answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "</longcat_answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<longcat_files>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "</longcat_files>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<longcat_tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "</longcat_tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<longcat_tool_declare>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "</longcat_tool_declare>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "<longcat_system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "47": {
+      "content": "<longcat_user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "48": {
+      "content": "<longcat_assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49": {
+      "content": "<longcat_tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "</longcat_tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<longcat_arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "</longcat_arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<longcat_arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "</longcat_arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<longcat_observation>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "56": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<mask_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "<mask_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "<mask_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "<mask_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "<mask_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69": {
+      "content": "<mask_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "<mask_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "content": "<mask_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "72": {
+      "content": "<mask_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73": {
+      "content": "<mask_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "content": "<mask_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75": {
+      "content": "<mask_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "76": {
+      "content": "<mask_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "77": {
+      "content": "<mask_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "78": {
+      "content": "<mask_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<mask_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "81": {
+      "content": "<mask_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "82": {
+      "content": "<mask_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "83": {
+      "content": "<mask_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "84": {
+      "content": "<mask_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "85": {
+      "content": "<mask_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "86": {
+      "content": "<mask_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "87": {
+      "content": "<mask_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "88": {
+      "content": "<mask_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "89": {
+      "content": "<mask_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "90": {
+      "content": "<mask_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "91": {
+      "content": "<mask_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92": {
+      "content": "<mask_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "93": {
+      "content": "<mask_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "94": {
+      "content": "<mask_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95": {
+      "content": "<mask_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96": {
+      "content": "<mask_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "97": {
+      "content": "<mask_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "98": {
+      "content": "<mask_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "99": {
+      "content": "<mask_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "<mask_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "<mask_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "<mask_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "<mask_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "<mask_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "<mask_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<mask_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<mask_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "<mask_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "109": {
+      "content": "<mask_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110": {
+      "content": "<mask_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "111": {
+      "content": "<mask_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "112": {
+      "content": "<mask_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "113": {
+      "content": "<mask_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "114": {
+      "content": "<mask_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "115": {
+      "content": "<mask_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "116": {
+      "content": "<mask_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "117": {
+      "content": "<mask_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "118": {
+      "content": "<mask_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "119": {
+      "content": "<mask_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "120": {
+      "content": "<mask_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "121": {
+      "content": "<mask_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "122": {
+      "content": "<mask_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "123": {
+      "content": "<mask_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "124": {
+      "content": "<mask_100>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "125": {
+      "content": "<mask_101>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "126": {
+      "content": "<mask_102>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "127": {
+      "content": "<mask_103>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128": {
+      "content": "<mask_104>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "129": {
+      "content": "<mask_105>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "130": {
+      "content": "<mask_106>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "131": {
+      "content": "<mask_107>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "132": {
+      "content": "<mask_108>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "133": {
+      "content": "<mask_109>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "134": {
+      "content": "<mask_110>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "135": {
+      "content": "<mask_111>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "136": {
+      "content": "<mask_112>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "137": {
+      "content": "<mask_113>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "138": {
+      "content": "<mask_114>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "139": {
+      "content": "<mask_115>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "140": {
+      "content": "<mask_116>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "141": {
+      "content": "<mask_117>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "142": {
+      "content": "<mask_118>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "143": {
+      "content": "<mask_119>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "144": {
+      "content": "<mask_120>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145": {
+      "content": "<mask_121>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "146": {
+      "content": "<mask_122>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147": {
+      "content": "<mask_123>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "148": {
+      "content": "<mask_124>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "149": {
+      "content": "<mask_125>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "150": {
+      "content": "<mask_126>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151": {
+      "content": "<mask_127>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "152": {
+      "content": "<mask_128>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "153": {
+      "content": "<mask_129>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "154": {
+      "content": "<mask_130>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "155": {
+      "content": "<mask_131>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "156": {
+      "content": "<mask_132>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "157": {
+      "content": "<mask_133>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "158": {
+      "content": "<mask_134>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "159": {
+      "content": "<mask_135>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "160": {
+      "content": "<mask_136>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "161": {
+      "content": "<mask_137>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "162": {
+      "content": "<mask_138>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163": {
+      "content": "<mask_139>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "164": {
+      "content": "<mask_140>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "165": {
+      "content": "<mask_141>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166": {
+      "content": "<mask_142>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "167": {
+      "content": "<mask_143>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "168": {
+      "content": "<mask_144>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "169": {
+      "content": "<mask_145>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "170": {
+      "content": "<mask_146>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "171": {
+      "content": "<mask_147>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "172": {
+      "content": "<mask_148>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "173": {
+      "content": "<mask_149>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "174": {
+      "content": "<mask_150>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "175": {
+      "content": "<mask_151>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "176": {
+      "content": "<mask_152>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "177": {
+      "content": "<mask_153>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "178": {
+      "content": "<mask_154>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "179": {
+      "content": "<mask_155>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "180": {
+      "content": "<mask_156>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "181": {
+      "content": "<mask_157>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "182": {
+      "content": "<mask_158>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "183": {
+      "content": "<mask_159>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "184": {
+      "content": "<mask_160>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "185": {
+      "content": "<mask_161>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "186": {
+      "content": "<mask_162>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "187": {
+      "content": "<mask_163>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "188": {
+      "content": "<mask_164>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "189": {
+      "content": "<mask_165>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "190": {
+      "content": "<mask_166>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "191": {
+      "content": "<mask_167>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "192": {
+      "content": "<mask_168>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "193": {
+      "content": "<mask_169>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "194": {
+      "content": "<mask_170>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "195": {
+      "content": "<mask_171>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "196": {
+      "content": "<mask_172>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "197": {
+      "content": "<mask_173>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "198": {
+      "content": "<mask_174>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199": {
+      "content": "<mask_175>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200": {
+      "content": "<mask_176>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "201": {
+      "content": "<mask_177>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "202": {
+      "content": "<mask_178>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "203": {
+      "content": "<mask_179>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "204": {
+      "content": "<mask_180>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "205": {
+      "content": "<mask_181>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "206": {
+      "content": "<mask_182>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "207": {
+      "content": "<mask_183>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "208": {
+      "content": "<mask_184>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "209": {
+      "content": "<mask_185>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "210": {
+      "content": "<mask_186>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "211": {
+      "content": "<mask_187>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "212": {
+      "content": "<mask_188>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "213": {
+      "content": "<mask_189>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "214": {
+      "content": "<mask_190>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "215": {
+      "content": "<mask_191>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "216": {
+      "content": "<mask_192>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "217": {
+      "content": "<mask_193>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "218": {
+      "content": "<mask_194>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219": {
+      "content": "<mask_195>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "220": {
+      "content": "<mask_196>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "221": {
+      "content": "<mask_197>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "222": {
+      "content": "<mask_198>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "223": {
+      "content": "<mask_199>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<longcat_s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</longcat_s>",
+  "extra_special_tokens": {},
+  "merges_file": null,
+  "model_max_length": 131072,
+  "pad_token": "<longcat_pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BloomTokenizer",
+  "tool_parser_type": "longcat",
+  "unk_token": "<longcat_unk>",
+  "vocab_file": null
+}