Initial upload for MiniMax-M2-THRIFT-55-v1 (sharded)

.gitattributes

@@ -0,0 +1,5 @@
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
+vocab.json filter=lfs diff=lfs merge=lfs -text
+merges.txt filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,56 @@
+{
+  "</minimax:tool_call>": 200053,
+  "</think>": 200051,
+  "<add_file>": 200036,
+  "<code_context>": 200043,
+  "<code_interpreter>": 200023,
+  "<commit_after>": 200018,
+  "<commit_before>": 200016,
+  "<commit_message>": 200040,
+  "<commit_msg>": 200017,
+  "<delete_file>": 200037,
+  "<edit_file>": 200039,
+  "<empty_output>": 200015,
+  "<empty_source_file>": 200041,
+  "<file_content>": 200044,
+  "<file_sep>": 200049,
+  "<filename>": 200006,
+  "<filepath>": 200048,
+  "<fim_middle>": 200002,
+  "<fim_pad>": 200004,
+  "<fim_prefix>": 200001,
+  "<fim_suffix>": 200003,
+  "<function_call>": 200022,
+  "<gh_stars>": 200007,
+  "<issue_closed>": 200010,
+  "<issue_comment>": 200009,
+  "<issue_start>": 200008,
+  "<jupyter_code>": 200013,
+  "<jupyter_error>": 200035,
+  "<jupyter_output>": 200014,
+  "<jupyter_start>": 200011,
+  "<jupyter_text>": 200012,
+  "<minimax:tool_call>": 200052,
+  "<pr_start>": 200046,
+  "<rename_file>": 200038,
+  "<repo_struct>": 200042,
+  "<reponame>": 200005,
+  "<review_comment>": 200047,
+  "<source_files>": 200045,
+  "<think>": 200050,
+  "[e~[": 200020,
+  "]!d~[": 200021,
+  "]!p~[": 200000,
+  "]<]end of image[>[": 200030,
+  "]<]end of speech[>[": 200028,
+  "]<]end of video[>[": 200032,
+  "]<]image[>[": 200025,
+  "]<]speech[>[": 200024,
+  "]<]start of image[>[": 200029,
+  "]<]start of speech[>[": 200027,
+  "]<]start of video[>[": 200031,
+  "]<]video[>[": 200026,
+  "]<]vision pad[>[": 200033,
+  "]~!b[": 200034,
+  "]~b]": 200019
+}

chat_template.jinja

@@ -0,0 +1,159 @@
+{# ----------‑‑‑ special token variables ‑‑‑---------- #}
+{%- set toolcall_begin_token   = '<minimax:tool_call>'         -%}
+{%- set toolcall_end_token     = '</minimax:tool_call>'        -%}
+{#- Tool Rendering Functions ============================================== -#}
+{%- macro render_tool_namespace(namespace_name, tool_list) -%}
+{%- for tool in tool_list -%}
+<tool>{{ tool.function | tojson(ensure_ascii=False) }}</tool>
+{% endfor -%}
+{%- endmacro -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{ content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{#- System Message Construction ============================================ -#}
+{%- macro build_system_message(system_message) -%}
+    {%- if system_message and system_message.content -%}
+        {{- visible_text(system_message.content) }}
+    {%- else -%}
+        {%- if model_identity is not defined -%}
+            {%- set model_identity = "You are a helpful assistant." -%}
+        {%- endif -%}
+        {{- model_identity }}
+    {%- endif -%}
+    
+    {#- Handle current_date -#}
+    {%- if system_message and system_message.current_date -%}
+        {{- '\n' ~ 'Current date: ' + system_message.current_date }}
+    {%- endif -%}
+    {#- Handle current_location -#}
+    {%- if system_message and system_message.current_location -%}
+        {{- '\n' ~ 'Current location: ' + system_message.current_location }}
+    {%- endif -%}
+{%- endmacro -%}
+{#- Main Template Logic ================================================= -#}
+{#- Extract system message (only first message if it's system) -#}
+{%- set system_message = none -%}
+{%- set conversation_messages = messages -%}
+{%- if messages and messages[0].role == "system" -%}
+    {%- set system_message = messages[0] -%}
+    {%- set conversation_messages = messages[1:] -%}
+{%- endif -%}
+{#- Get the last user message turn, for interleved thinking -#}
+{%- set ns = namespace(last_user_index=-1) %}
+{% for m in conversation_messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{#- Render system message -#}
+{{- ']~!b[' ~ ']~b]system' ~ '\n' }}
+{{- build_system_message(system_message) }}
+{#- Render tools if available -#}
+{%- if tools -%}
+    {{- '\n\n' ~ '# Tools' ~ '\n' ~ 'You may call one or more tools to assist with the user query.\nHere are the tools available in JSONSchema format:' ~ '\n' }}
+    {{- '\n' ~ '<tools>' ~ '\n' }}
+    {{- render_tool_namespace("functions", tools) }}
+    {{- '</tools>' ~ '\n\n' }}
+{{- 'When making tool calls, use XML format to invoke tools and pass parameters:' ~ '\n' }}
+{{- '\n' ~ toolcall_begin_token }}
+<invoke name="tool-name-1">
+<parameter name="param-key-1">param-value-1</parameter>
+<parameter name="param-key-2">param-value-2</parameter>
+...
+</invoke>
+{{- '\n' ~ toolcall_end_token }}
+{%- endif -%}
+{{- '[e~[\n' }}
+
+{#- Render messages -#}
+{%- set last_tool_call = namespace(name=none) -%}
+{%- for message in conversation_messages -%}
+    {%- if message.role == 'assistant' -%}
+        {#- Only render reasoning_content if no user message follows -#}
+        {{- ']~b]ai' ~ '\n' }}
+
+        {%- set reasoning_content = '' %}
+        {%- set content = visible_text(message.content) %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].strip('\n').split('<think>')[-1].strip('\n') %}
+                {%- set content = content.split('</think>')[-1].strip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if reasoning_content and loop.index0 > ns.last_user_index -%}
+            {{- '<think>' ~ '\n' ~ reasoning_content ~ '\n' ~ '</think>' ~ '\n\n' }}
+        {%- endif -%}
+        {%- if content -%}
+            {{- content }}
+        {%- endif -%}
+        {%- if message.tool_calls -%}
+            {{- '\n' ~ toolcall_begin_token ~ '\n' }}
+
+            {%- for tool_call in message.tool_calls -%}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<invoke name="' + tool_call.name + '">' }}
+                {% set _args = tool_call.arguments %}
+                {%- for k, v in _args.items() %}
+                {{- '<parameter name="' + k + '">' }}
+                {{- v | tojson(ensure_ascii=False) if v is not string else v }}
+                {{- '</parameter>' }}
+                {% endfor %}
+                {{- '</invoke>' ~ '\n' }}
+            {%- endfor -%}
+            
+            {{- toolcall_end_token}}
+            {%- set last_tool_call.name = message.tool_calls[-1].name -%}
+        {%- else -%}
+            {%- set last_tool_call.name = none -%}
+        {%- endif -%}
+        {{- '[e~[' ~ '\n' }}
+        
+    {%- elif message.role == 'tool' -%}
+    {%- if last_tool_call.name is none -%}
+        {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
+    {%- endif -%}
+    {%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}
+        {{- ']~b]tool' }}
+    {%- endif -%}
+    {%- if message.content is string -%}
+        {{- '\n<response>' }}
+        {{- message.content }}
+        {{- '</response>' }}
+    {%- else -%}
+        {%- for tr in message.content -%}
+            {{- '\n<response>' }}
+            {{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}
+            {{- '\n</response>' }}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}
+        {{- '[e~[\n' -}}
+    {%- endif -%}
+        
+    {%- elif message.role == 'user' -%}
+        {{- ']~b]user' ~ '\n' }}
+        {{- visible_text(message.content) }}
+        {{- '[e~[' ~ '\n' }}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Generation prompt -#}
+{%- if add_generation_prompt -%}
+{{- ']~b]ai' ~ '\n' ~ '<think>' ~ '\n' }}
+{%- endif -%}

config.json

@@ -0,0 +1,120 @@
+{
+  "architectures": [
+    "MiniMaxM2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_type_list": [
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1
+  ],
+  "attn_window_size": null,
+  "auto_map": {
+    "AutoConfig": "configuration_minimax_m2.MiniMaxM2Config",
+    "AutoModelForCausalLM": "modeling_minimax_m2.MiniMaxM2ForCausalLM"
+  },
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layernorm_full_attention_beta": 1.0,
+  "layernorm_linear_attention_beta": 1.0,
+  "layernorm_mlp_beta": 1.0,
+  "max_model_len": null,
+  "max_position_embeddings": 196608,
+  "mlp_intermediate_size": 8192,
+  "model_type": "minimax",
+  "mtp_transformer_layers": 1,
+  "num_attention_heads": 48,
+  "num_expert_group": null,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "num_local_experts": 116,
+  "num_mtp_modules": 3,
+  "output_router_logits": false,
+  "partial_rotary_factor": 0.5,
+  "qk_norm_type": "per_layer",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "rotary_dim": 64,
+  "routed_scaling_factor": 1.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "scoring_func": "sigmoid",
+  "shared_intermediate_size": 0,
+  "shared_moe_mode": "sigmoid",
+  "sliding_window": null,
+  "swa_rope_theta": -1.0,
+  "tie_word_embeddings": false,
+  "topk_group": null,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_grouped_topk": true,
+  "use_mtp": true,
+  "use_qk_norm": true,
+  "use_routing_bias": true,
+  "vocab_size": 200064
+}

configuration_minimax_m2.py

@@ -0,0 +1,131 @@
+# SPDX-FileCopyrightText: 2024-2025 ModelCloud.ai
+# SPDX-FileCopyrightText: 2024-2025 [email protected]
+# SPDX-License-Identifier: Apache-2.0
+# Contact: [email protected], x.com/qubitium
+
+"""Configuration for the MiniMax M2 architecture."""
+
+from __future__ import annotations
+
+from typing import List, Optional, Union
+
+from transformers.configuration_utils import PretrainedConfig
+
+
+class MiniMaxM2Config(PretrainedConfig):
+    model_type = "minimax"
+
+    def __init__(
+        self,
+        vocab_size: int = 200_064,
+        hidden_size: int = 3_072,
+        intermediate_size: int = 1_536,
+        mlp_intermediate_size: int = 8_192,
+        num_hidden_layers: int = 62,
+        num_attention_heads: int = 48,
+        num_key_value_heads: int = 8,
+        head_dim: Optional[int] = 128,
+        num_local_experts: int = 256,
+        num_experts_per_tok: int = 8,
+        attn_type_list: Optional[List[int]] = None,
+        attention_dropout: float = 0.0,
+        hidden_act: str = "silu",
+        rms_norm_eps: float = 1e-6,
+        max_position_embeddings: int = 196_608,
+        rope_theta: float = 5_000_000.0,
+        rotary_dim: int = 64,
+        rope_scaling: Optional[dict] = None,
+        use_qk_norm: bool = True,
+        qk_norm_type: str = "per_layer",
+        use_routing_bias: bool = True,
+        scoring_func: str = "sigmoid",
+        router_aux_loss_coef: float = 0.001,
+        router_jitter_noise: float = 0.0,
+        output_router_logits: bool = False,
+        use_grouped_topk: bool = True,
+        num_expert_group: Optional[int] = None,
+        topk_group: Optional[int] = None,
+        routed_scaling_factor: float = 1.0,
+        layernorm_full_attention_beta: float = 1.0,
+        layernorm_linear_attention_beta: float = 1.0,
+        layernorm_mlp_beta: float = 1.0,
+        shared_intermediate_size: int = 0,
+        shared_moe_mode: str = "sigmoid",
+        use_mtp: bool = True,
+        num_mtp_modules: int = 3,
+        mtp_transformer_layers: int = 1,
+        attn_window_size: Optional[Union[int, List[int]]] = None,
+        swa_rope_theta: float = -1.0,
+        sliding_window: Optional[int] = None,
+        initializer_range: float = 0.02,
+        tie_word_embeddings: bool = False,
+        max_model_len: Optional[int] = None,
+        bos_token_id: Optional[int] = None,
+        eos_token_id: Optional[int] = None,
+        pad_token_id: Optional[int] = None,
+        use_cache: bool = True,
+        **kwargs,
+    ) -> None:
+        quantization_config = kwargs.pop("quantization_config", None)
+        transformers_version = kwargs.pop("transformers_version", None)
+
+        super().__init__(
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            pad_token_id=pad_token_id,
+            **kwargs,
+        )
+
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.mlp_intermediate_size = mlp_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_key_value_heads = num_key_value_heads
+        self.head_dim = head_dim or hidden_size // num_attention_heads
+        self.num_local_experts = num_local_experts
+        self.num_experts_per_tok = num_experts_per_tok
+        self.attn_type_list = attn_type_list or [1] * num_hidden_layers
+        self.attention_dropout = attention_dropout
+        self.hidden_act = hidden_act
+        self.rms_norm_eps = rms_norm_eps
+        self.max_position_embeddings = max_position_embeddings
+        self.rope_theta = rope_theta
+        self.rotary_dim = rotary_dim
+        self.rope_scaling = rope_scaling
+        self.use_qk_norm = use_qk_norm
+        self.qk_norm_type = qk_norm_type
+        self.use_routing_bias = use_routing_bias
+        self.scoring_func = scoring_func
+        self.router_aux_loss_coef = router_aux_loss_coef
+        self.router_jitter_noise = router_jitter_noise
+        self.output_router_logits = output_router_logits
+        self.use_grouped_topk = use_grouped_topk
+        self.num_expert_group = num_expert_group
+        self.topk_group = topk_group
+        self.routed_scaling_factor = routed_scaling_factor
+        self.layernorm_full_attention_beta = layernorm_full_attention_beta
+        self.layernorm_linear_attention_beta = layernorm_linear_attention_beta
+        self.layernorm_mlp_beta = layernorm_mlp_beta
+        self.shared_intermediate_size = shared_intermediate_size
+        self.shared_moe_mode = shared_moe_mode
+        self.use_mtp = use_mtp
+        self.num_mtp_modules = num_mtp_modules
+        self.mtp_transformer_layers = mtp_transformer_layers
+        self.attn_window_size = attn_window_size
+        self.swa_rope_theta = swa_rope_theta
+        self.sliding_window = sliding_window
+        self.initializer_range = initializer_range
+        self.max_model_len = max_model_len
+        self.use_cache = use_cache
+
+        # Convenient accessor used by rotary embedding helper
+        self.partial_rotary_factor = float(self.rotary_dim) / float(self.head_dim)
+        if quantization_config is not None:
+            self.quantization_config = quantization_config
+        self.transformers_version = transformers_version
+
+
+__all__ = ["MiniMaxM2Config"]

merges.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c54e1d6eb451b1db3ab89669382c097e6533a47fe526e90dd70b35a0d28bc8
+size 2414078

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87441b8743917e14c7569367437b353d3f9ebdd2ee94fec529cf3d9c79a5d519
+size 10733280832

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b3808a2c99582351a846156b5c0df519a6ee631b049603a0505b591de8a222
+size 10732445712

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c9b358049a858390bbe22d85fbc7ca6b537297a954fec195e2c106f781415c
+size 10732445712

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87fbccf362f6c7a0c670943ba39f2507a23daa2b09768781bb9c93ed59e0763
+size 10736330640

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde7f15e53ec8e1dad1c61f3595b3c429dc6639e4344d7f94bc6c365360004bd
+size 10732445408

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9411de3c15f225dbef2aa729280e8f22b15939e90d774f6ea340b6af5f39e030
+size 10732445712

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ddff75d84d902dfa3e678f9779666beb0c77de8d408083d0e9c9ea5187f86b7
+size 10732445712

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bee5074e2106442039af56f5a37f0c0cfcded7216a0a386ab9d0cd95444c526
+size 10732445360

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b588cfab4237c9e80c62ab9f06bd296fb2a889426359449b60005e312d9fd60
+size 10732445712

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47892273d418f87e24ab2e19eb68ba85d9a84f3f71939895410b504b940e2a4
+size 10736330656

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474938c0f72c5eaf2209ff655e20020f1f7f27644b10c849f0dde83a0feb9c87
+size 10732445640

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced02c8ffd78c65934fa32f1424aaed183de7b6be53a31efa074747a8c0d1a00
+size 10732445456

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5574a46069528ba54172409b8538ed604b59f9481a558f710b7890d13d571f36
+size 10732445712

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea6d45792e7927b04086daf63da9c34347109d84c32642ae0f07251e02998ff
+size 10732445712

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dfaccd03265c4829aa17f78dd72246f3f3ec7013bb4a9da1a12965e4c62ee2
+size 10736330280

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bd7f3ebd0c8c8ba10f326d14751d1b5c720462fbaadc69135cfc4fd42415a3
+size 10732445760

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0265c857910062cd049797ad533f0c1fc520684f7ee2959001c787a78071dec2
+size 10732445712

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cdfcbfe5bbdff90f256e9e6076c0c213d1d953f91d165004f37ca335bfcff0
+size 10732445520

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d44a0507aa900c56ca68f29daaaab71c528b91520d7fd1882ab1d871cb7d52c
+size 10732445288

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1694a164946d9e16685a0a1bcaa81e207e679ed52f7cbbc24c98115a27e2b1
+size 7655885952

special_tokens_map.json

@@ -0,0 +1,75 @@
+{
+  "additional_special_tokens": [
+    "<code_interpreter>",
+    "<commit_after>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<empty_output>",
+    "<filename>",
+    "<fim_middle>",
+    "<fim_pad>",
+    "<fim_prefix>",
+    "<fim_suffix>",
+    "<function_call>",
+    "<gh_stars>",
+    "]<]speech[>[",
+    "]<]image[>[",
+    "]<]video[>[",
+    "]<]start of speech[>[",
+    "]<]end of speech[>[",
+    "]<]start of image[>[",
+    "]<]end of image[>[",
+    "]<]start of video[>[",
+    "]<]end of video[>[",
+    "]<]vision pad[>[",
+    "]~!b[",
+    "<issue_closed>",
+    "<issue_comment>",
+    "<issue_start>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<reponame>",
+    "[e~[",
+    "]!d~[",
+    "]!p~[",
+    "]~b]",
+    "<jupyter_error>",
+    "<add_file>",
+    "<delete_file>",
+    "<rename_file>",
+    "<edit_file>",
+    "<commit_message>",
+    "<empty_source_file>",
+    "<repo_struct>",
+    "<code_context>",
+    "<file_content>",
+    "<source_files>",
+    "<pr_start>",
+    "<review_comment>",
+    "<filepath>",
+    "<file_sep>"
+  ],
+  "bos_token": {
+    "content": "]~!b[",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[e~[",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "]!d~[",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b90ed7f55d905175bc26771d6d7d33b40b46742f073675bc816fedaf482ea1
+size 15522763

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb1c28a83798e52fb41550d95cc6e93eb9db16fdc608c73c56172a72bb73581
+size 11091

vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449838e19b2c13a375ee324056b4fe0f19128ea359283941d27c4e603292dab5
+size 3905412