GLM-5.3-Flash-NVFP4 (NVFP4 routed experts + dense MLP, FP8 KV cache)

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,257 @@
+[gMASK]<sop>
+{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}
+{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
+{%- set clear_thinking = clear_thinking if clear_thinking is defined else false -%}
+{%- if tools -%}
+{%- macro tool_to_json(tool) -%}
+    {%- set ns_tool = namespace(first=true) -%}
+    {{ '{' -}}
+    {%- for k, v in tool.items() -%}
+        {%- if k != 'defer_loading' and k != 'strict' -%}
+            {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
+            {%- set ns_tool.first = false -%}
+            "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- endmacro -%}
+{%- macro tool_references_to_response(refs) -%}
+    {{- '<tool_response><tools>\n' -}}
+    {%- for tr in refs -%}
+        {%- for tool in tools -%}
+            {%- if 'function' in tool -%}
+                {%- set tool = tool['function'] -%}
+            {%- endif -%}
+            {%- if tool.name == tr.name -%}
+                {{- tool_to_json(tool) + '\n' -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endfor -%}
+    {{- '</tools></tool_response>' -}}
+{%- endmacro -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{%- if 'function' in tool -%}
+    {%- set tool = tool['function'] -%}
+{%- endif -%}
+{% if tool.defer_loading is not defined or not tool.defer_loading %}
+{{ tool_to_json(tool) }}
+{% endif %}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
+{%- macro emit_image() -%}<|begin_of_image|><|image|><|end_of_image|>{%- endmacro -%}
+{%- macro emit_video() -%}<|begin_of_video|><|video|><|end_of_video|>{%- endmacro -%}
+{%- macro emit_audio() -%}<|begin_of_audio|><|end_of_audio|>{%- 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 -}}
+            {%- elif item is mapping and item.type in ['image', 'image_url'] -%}
+                {{- emit_image() -}}
+            {%- elif item is mapping and item.type in ['video', 'video_url'] -%}
+                {{- emit_video() -}}
+            {%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%}
+                {{- emit_audio() -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro tool_response(text) -%}
+{{- '<tool_response>' + text + '</tool_response>' -}}
+{%- endmacro -%}
+{%- macro render_tool_response(m) -%}
+{%- if m.content is string -%}
+    {{- tool_response(m.content) -}}
+{%- elif m.content and m.content is not mapping and m.content.0.type == "tool_reference" -%}
+    {{- tool_references_to_response(m.content) -}}
+{%- elif is_list_of_outputs(m) -%}
+    {%- for tr in m.content -%}
+        {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == "tool_reference" -%}
+            {{- tool_references_to_response(tr.output) -}}
+        {%- else -%}
+            {{- tool_response(visible_text(tr.output)) -}}
+        {%- endif -%}
+    {%- endfor -%}
+{%- else -%}
+    {{- tool_response(visible_text(m.content)) -}}
+{%- endif -%}
+{%- endmacro -%}
+{%- macro id_of(obj) -%}
+    {%- if obj.tool_call_id -%}
+        {{- obj.tool_call_id -}}
+    {%- elif obj.id -%}
+        {{- obj.id -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro is_list_of_outputs(m) -%}
+    {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}
+{%- endmacro -%}
+{%- macro has_dup_tool_result_id(lo, hi, target) -%}
+    {%- set ns_cnt = namespace(n=0) -%}
+    {%- for k in range(lo, hi + 1) -%}
+        {%- set m = messages[k] -%}
+        {%- if is_list_of_outputs(m) -%}
+            {%- for entry in m.content -%}
+                {%- if id_of(entry) == target -%}
+                    {%- set ns_cnt.n = ns_cnt.n + 1 -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- elif id_of(m) == target -%}
+            {%- set ns_cnt.n = ns_cnt.n + 1 -%}
+        {%- endif -%}
+        {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}
+    {%- endfor -%}
+    {%- if ns_cnt.n > 1 -%}1{%- endif -%}
+{%- endmacro -%}
+{%- macro tc_id_exists(tcs, target) -%}
+    {%- set ns_f = namespace(found=false) -%}
+    {%- for tc in tcs -%}
+        {%- if id_of(tc) == target -%}
+            {%- set ns_f.found = true -%}
+            {%- break -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- if ns_f.found -%}1{%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) -%}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{%- for m in messages -%}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- elif '</think>' in content %}
+    {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
+    {%- set content = content.split('</think>')[-1] %}
+{%- endif %}
+{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
+{{ '<think>' + reasoning_content +  '</think>'}}
+{%- else -%}
+{{ '<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' -}}
+    {%- set block_start = loop.index0 -%}
+    {%- set ns_blk = namespace(end=block_start) -%}
+    {%- for j in range(block_start, messages|length) -%}
+        {%- if messages[j].role == 'tool' -%}
+            {%- set ns_blk.end = j -%}
+        {%- else -%}
+            {%- break -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns_a = namespace(tool_calls=none) -%}
+    {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}
+        {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}
+    {%- endif -%}
+    {%- set ns_chk = namespace(can_sort=true) -%}
+    {%- if not ns_a.tool_calls -%}
+        {%- set ns_chk.can_sort = false -%}
+    {%- else -%}
+        {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {%- set m = messages[k] -%}
+            {%- if is_list_of_outputs(m) -%}
+                {%- for entry in m.content -%}
+                    {%- set eid = id_of(entry) -%}
+                    {%- if not eid -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {%- set tk_id = id_of(m) -%}
+                {%- if not tk_id -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- for i in range(ns_a.tool_calls | length) -%}
+            {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}
+            {%- if not tc_id -%}
+                {%- set ns_chk.can_sort = false -%}
+            {%- endif -%}
+            {%- for j in range(i + 1, ns_a.tool_calls | length) -%}
+                {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- endif -%}
+            {%- endfor -%}
+    {%- endfor -%}
+    {%- endif -%}
+    {%- if ns_chk.can_sort -%}
+        {%- for tc in ns_a.tool_calls -%}
+            {%- set tc_id = id_of(tc) -%}
+            {%- for k in range(block_start, ns_blk.end + 1) -%}
+                {%- set m = messages[k] -%}
+                {%- if is_list_of_outputs(m) -%}
+                    {%- for entry in m.content -%}
+                        {%- set eid = id_of(entry) -%}
+                        {%- if eid == tc_id -%}
+                            {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == "tool_reference" -%}
+                                {{- tool_references_to_response(entry.output) -}}
+                            {%- else -%}
+                                {{- tool_response(visible_text(entry.output)) -}}
+                            {%- endif -%}
+                        {%- endif -%}
+    {%- endfor -%}
+{%- else -%}
+                    {%- set tk_id = id_of(m) -%}
+                    {%- if tk_id == tc_id -%}
+                        {{- render_tool_response(m) -}}
+                    {%- endif -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endfor -%}
+    {%- else -%}
+        {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {{- render_tool_response(messages[k]) -}}
+        {%- endfor -%}
+    {%- endif -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,469 @@
+{
+    "architectures": [
+        "Glm5NextForConditionalGeneration"
+    ],
+    "dtype": "bfloat16",
+    "image_end_token_id": 154831,
+    "image_start_token_id": 154830,
+    "image_token_id": 154854,
+    "model_type": "glm5_next",
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "base_model_ep_plan": {
+            "layers.*.mlp.experts": "torch_a2a_experts",
+            "layers.*.mlp.experts.down_proj": "grouped_gemm",
+            "layers.*.mlp.experts.gate_up_proj": "grouped_gemm",
+            "layers.*.mlp.gate": "torch_a2a_router"
+        },
+        "bos_token_id": null,
+        "dtype": "bfloat16",
+        "eos_token_id": [
+            154820,
+            154827,
+            154829
+        ],
+        "first_k_dense_replace": 3,
+        "hc_eps": 1e-06,
+        "hc_mult": 4,
+        "hc_sinkhorn_iters": 20,
+        "head_dim": 0,
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "index_head_dim": 128,
+        "index_kpool": 4,
+        "index_kpool_always_select_tail": true,
+        "index_kpool_compress": true,
+        "index_n_heads": 32,
+        "index_share_for_mtp_iteration": true,
+        "index_topk": 2048,
+        "indexer_rope_interleave": true,
+        "indexer_types": [
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full",
+            "full"
+        ],
+        "initializer_range": 0.02,
+        "intermediate_size": 12288,
+        "kv_lora_rank": 512,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "deepseek_sparse_attention",
+            "linear_attention"
+        ],
+        "linear_attn_config": {
+            "full_attn_layers": [
+                3,
+                7,
+                11,
+                15,
+                19,
+                23,
+                27,
+                31,
+                35,
+                39,
+                43
+            ],
+            "gate_lower_bound": -5.0,
+            "head_dim": 128,
+            "kda_layers": [
+                0,
+                1,
+                2,
+                4,
+                5,
+                6,
+                8,
+                9,
+                10,
+                12,
+                13,
+                14,
+                16,
+                17,
+                18,
+                20,
+                21,
+                22,
+                24,
+                25,
+                26,
+                28,
+                29,
+                30,
+                32,
+                33,
+                34,
+                36,
+                37,
+                38,
+                40,
+                41,
+                42,
+                44
+            ],
+            "num_heads": 64,
+            "short_conv_kernel_size": 4
+        },
+        "linear_conv_kernel_dim": 4,
+        "linear_head_dim": 128,
+        "linear_lower_bound": -5.0,
+        "linear_num_heads": 64,
+        "max_position_embeddings": 1048576,
+        "mhc": true,
+        "mla_use_nope": true,
+        "mlp_layer_types": [
+            "dense",
+            "dense",
+            "dense",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse",
+            "sparse"
+        ],
+        "model_type": "glm5_next_text",
+        "moe_intermediate_size": 2048,
+        "moe_router_dtype": "float32",
+        "n_group": 1,
+        "n_routed_experts": 288,
+        "n_shared_experts": 1,
+        "norm_topk_prob": true,
+        "num_attention_heads": 64,
+        "num_experts_per_tok": 8,
+        "num_hidden_layers": 45,
+        "num_key_value_heads": 64,
+        "num_nextn_predict_layers": 1,
+        "output_router_logits": false,
+        "pad_token_id": 154820,
+        "q_lora_rank": 1536,
+        "qk_head_dim": 256,
+        "qk_nope_head_dim": 256,
+        "qk_rope_head_dim": 0,
+        "rms_norm_eps": 1e-05,
+        "routed_scaling_factor": 2.5,
+        "router_aux_loss_coef": 0.001,
+        "scoring_func": "sigmoid",
+        "swiglu_limit": 10.0,
+        "tie_word_embeddings": false,
+        "topk_group": 1,
+        "topk_method": "noaux_tc",
+        "use_cache": true,
+        "v_head_dim": 256,
+        "vocab_size": 154880
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "5.16.1",
+    "video_end_token_id": 154833,
+    "video_start_token_id": 154832,
+    "video_token_id": 154855,
+    "vision_config": {
+        "attention_bias": true,
+        "attention_dropout": 0.0,
+        "depth": 24,
+        "dtype": "bfloat16",
+        "hidden_act": "silu",
+        "hidden_size": 1024,
+        "image_size": 448,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4096,
+        "model_type": "glm5_next_vision",
+        "num_heads": 16,
+        "out_hidden_size": 4096,
+        "patch_size": 14,
+        "projection_intermediate_size": 10240,
+        "rms_norm_eps": 1e-05,
+        "spatial_merge_size": 2,
+        "swiglu_limit": 10.0,
+        "temporal_patch_size": 2
+    },
+    "quantization_config": {
+        "config_groups": {
+            "group_0": {
+                "input_activations": {
+                    "dynamic": false,
+                    "num_bits": 4,
+                    "type": "float",
+                    "group_size": 16
+                },
+                "weights": {
+                    "dynamic": false,
+                    "num_bits": 4,
+                    "type": "float",
+                    "group_size": 16
+                },
+                "targets": [
+                    "Linear"
+                ]
+            }
+        },
+        "ignore": [
+            "lm_head",
+            "model.language_model.embed_tokens",
+            "model.language_model.layers.0.self_attn*",
+            "model.language_model.layers.1.self_attn*",
+            "model.language_model.layers.10.mlp.gate",
+            "model.language_model.layers.10.mlp.shared_experts*",
+            "model.language_model.layers.10.self_attn*",
+            "model.language_model.layers.11.mlp.gate",
+            "model.language_model.layers.11.mlp.shared_experts*",
+            "model.language_model.layers.11.self_attn*",
+            "model.language_model.layers.12.mlp.gate",
+            "model.language_model.layers.12.mlp.shared_experts*",
+            "model.language_model.layers.12.self_attn*",
+            "model.language_model.layers.13.mlp.gate",
+            "model.language_model.layers.13.mlp.shared_experts*",
+            "model.language_model.layers.13.self_attn*",
+            "model.language_model.layers.14.mlp.gate",
+            "model.language_model.layers.14.mlp.shared_experts*",
+            "model.language_model.layers.14.self_attn*",
+            "model.language_model.layers.15.mlp.gate",
+            "model.language_model.layers.15.mlp.shared_experts*",
+            "model.language_model.layers.15.self_attn*",
+            "model.language_model.layers.16.mlp.gate",
+            "model.language_model.layers.16.mlp.shared_experts*",
+            "model.language_model.layers.16.self_attn*",
+            "model.language_model.layers.17.mlp.gate",
+            "model.language_model.layers.17.mlp.shared_experts*",
+            "model.language_model.layers.17.self_attn*",
+            "model.language_model.layers.18.mlp.gate",
+            "model.language_model.layers.18.mlp.shared_experts*",
+            "model.language_model.layers.18.self_attn*",
+            "model.language_model.layers.19.mlp.gate",
+            "model.language_model.layers.19.mlp.shared_experts*",
+            "model.language_model.layers.19.self_attn*",
+            "model.language_model.layers.2.self_attn*",
+            "model.language_model.layers.20.mlp.gate",
+            "model.language_model.layers.20.mlp.shared_experts*",
+            "model.language_model.layers.20.self_attn*",
+            "model.language_model.layers.21.mlp.gate",
+            "model.language_model.layers.21.mlp.shared_experts*",
+            "model.language_model.layers.21.self_attn*",
+            "model.language_model.layers.22.mlp.gate",
+            "model.language_model.layers.22.mlp.shared_experts*",
+            "model.language_model.layers.22.self_attn*",
+            "model.language_model.layers.23.mlp.gate",
+            "model.language_model.layers.23.mlp.shared_experts*",
+            "model.language_model.layers.23.self_attn*",
+            "model.language_model.layers.24.mlp.gate",
+            "model.language_model.layers.24.mlp.shared_experts*",
+            "model.language_model.layers.24.self_attn*",
+            "model.language_model.layers.25.mlp.gate",
+            "model.language_model.layers.25.mlp.shared_experts*",
+            "model.language_model.layers.25.self_attn*",
+            "model.language_model.layers.26.mlp.gate",
+            "model.language_model.layers.26.mlp.shared_experts*",
+            "model.language_model.layers.26.self_attn*",
+            "model.language_model.layers.27.mlp.gate",
+            "model.language_model.layers.27.mlp.shared_experts*",
+            "model.language_model.layers.27.self_attn*",
+            "model.language_model.layers.28.mlp.gate",
+            "model.language_model.layers.28.mlp.shared_experts*",
+            "model.language_model.layers.28.self_attn*",
+            "model.language_model.layers.29.mlp.gate",
+            "model.language_model.layers.29.mlp.shared_experts*",
+            "model.language_model.layers.29.self_attn*",
+            "model.language_model.layers.3.mlp.gate",
+            "model.language_model.layers.3.mlp.shared_experts*",
+            "model.language_model.layers.3.self_attn*",
+            "model.language_model.layers.30.mlp.gate",
+            "model.language_model.layers.30.mlp.shared_experts*",
+            "model.language_model.layers.30.self_attn*",
+            "model.language_model.layers.31.mlp.gate",
+            "model.language_model.layers.31.mlp.shared_experts*",
+            "model.language_model.layers.31.self_attn*",
+            "model.language_model.layers.32.mlp.gate",
+            "model.language_model.layers.32.mlp.shared_experts*",
+            "model.language_model.layers.32.self_attn*",
+            "model.language_model.layers.33.mlp.gate",
+            "model.language_model.layers.33.mlp.shared_experts*",
+            "model.language_model.layers.33.self_attn*",
+            "model.language_model.layers.34.mlp.gate",
+            "model.language_model.layers.34.mlp.shared_experts*",
+            "model.language_model.layers.34.self_attn*",
+            "model.language_model.layers.35.mlp.gate",
+            "model.language_model.layers.35.mlp.shared_experts*",
+            "model.language_model.layers.35.self_attn*",
+            "model.language_model.layers.36.mlp.gate",
+            "model.language_model.layers.36.mlp.shared_experts*",
+            "model.language_model.layers.36.self_attn*",
+            "model.language_model.layers.37.mlp.gate",
+            "model.language_model.layers.37.mlp.shared_experts*",
+            "model.language_model.layers.37.self_attn*",
+            "model.language_model.layers.38.mlp.gate",
+            "model.language_model.layers.38.mlp.shared_experts*",
+            "model.language_model.layers.38.self_attn*",
+            "model.language_model.layers.39.mlp.gate",
+            "model.language_model.layers.39.mlp.shared_experts*",
+            "model.language_model.layers.39.self_attn*",
+            "model.language_model.layers.4.mlp.gate",
+            "model.language_model.layers.4.mlp.shared_experts*",
+            "model.language_model.layers.4.self_attn*",
+            "model.language_model.layers.40.mlp.gate",
+            "model.language_model.layers.40.mlp.shared_experts*",
+            "model.language_model.layers.40.self_attn*",
+            "model.language_model.layers.41.mlp.gate",
+            "model.language_model.layers.41.mlp.shared_experts*",
+            "model.language_model.layers.41.self_attn*",
+            "model.language_model.layers.42.mlp.gate",
+            "model.language_model.layers.42.mlp.shared_experts*",
+            "model.language_model.layers.42.self_attn*",
+            "model.language_model.layers.43.mlp.gate",
+            "model.language_model.layers.43.mlp.shared_experts*",
+            "model.language_model.layers.43.self_attn*",
+            "model.language_model.layers.44.mlp.gate",
+            "model.language_model.layers.44.mlp.shared_experts*",
+            "model.language_model.layers.44.self_attn*",
+            "model.language_model.layers.5.mlp.gate",
+            "model.language_model.layers.5.mlp.shared_experts*",
+            "model.language_model.layers.5.self_attn*",
+            "model.language_model.layers.6.mlp.gate",
+            "model.language_model.layers.6.mlp.shared_experts*",
+            "model.language_model.layers.6.self_attn*",
+            "model.language_model.layers.7.mlp.gate",
+            "model.language_model.layers.7.mlp.shared_experts*",
+            "model.language_model.layers.7.self_attn*",
+            "model.language_model.layers.8.mlp.gate",
+            "model.language_model.layers.8.mlp.shared_experts*",
+            "model.language_model.layers.8.self_attn*",
+            "model.language_model.layers.9.mlp.gate",
+            "model.language_model.layers.9.mlp.shared_experts*",
+            "model.language_model.layers.9.self_attn*",
+            "model.visual*"
+        ],
+        "quant_algo": "NVFP4",
+        "kv_cache_scheme": {
+            "dynamic": false,
+            "num_bits": 8,
+            "type": "float"
+        },
+        "producer": {
+            "name": "modelopt",
+            "version": "0.47.0.dev393+ga4bc45b30.d20260828"
+        },
+        "quant_method": "modelopt"
+    }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.16.1"
+}

hf_quant_config.json

@@ -0,0 +1,145 @@
+{
+    "producer": {
+        "name": "modelopt",
+        "version": "0.47.0.dev393+ga4bc45b30.d20260828"
+    },
+    "quantization": {
+        "quant_algo": "NVFP4",
+        "kv_cache_quant_algo": "FP8",
+        "group_size": 16,
+        "exclude_modules": [
+            "lm_head",
+            "model.language_model.embed_tokens",
+            "model.language_model.layers.0.self_attn*",
+            "model.language_model.layers.1.self_attn*",
+            "model.language_model.layers.10.mlp.gate",
+            "model.language_model.layers.10.mlp.shared_experts*",
+            "model.language_model.layers.10.self_attn*",
+            "model.language_model.layers.11.mlp.gate",
+            "model.language_model.layers.11.mlp.shared_experts*",
+            "model.language_model.layers.11.self_attn*",
+            "model.language_model.layers.12.mlp.gate",
+            "model.language_model.layers.12.mlp.shared_experts*",
+            "model.language_model.layers.12.self_attn*",
+            "model.language_model.layers.13.mlp.gate",
+            "model.language_model.layers.13.mlp.shared_experts*",
+            "model.language_model.layers.13.self_attn*",
+            "model.language_model.layers.14.mlp.gate",
+            "model.language_model.layers.14.mlp.shared_experts*",
+            "model.language_model.layers.14.self_attn*",
+            "model.language_model.layers.15.mlp.gate",
+            "model.language_model.layers.15.mlp.shared_experts*",
+            "model.language_model.layers.15.self_attn*",
+            "model.language_model.layers.16.mlp.gate",
+            "model.language_model.layers.16.mlp.shared_experts*",
+            "model.language_model.layers.16.self_attn*",
+            "model.language_model.layers.17.mlp.gate",
+            "model.language_model.layers.17.mlp.shared_experts*",
+            "model.language_model.layers.17.self_attn*",
+            "model.language_model.layers.18.mlp.gate",
+            "model.language_model.layers.18.mlp.shared_experts*",
+            "model.language_model.layers.18.self_attn*",
+            "model.language_model.layers.19.mlp.gate",
+            "model.language_model.layers.19.mlp.shared_experts*",
+            "model.language_model.layers.19.self_attn*",
+            "model.language_model.layers.2.self_attn*",
+            "model.language_model.layers.20.mlp.gate",
+            "model.language_model.layers.20.mlp.shared_experts*",
+            "model.language_model.layers.20.self_attn*",
+            "model.language_model.layers.21.mlp.gate",
+            "model.language_model.layers.21.mlp.shared_experts*",
+            "model.language_model.layers.21.self_attn*",
+            "model.language_model.layers.22.mlp.gate",
+            "model.language_model.layers.22.mlp.shared_experts*",
+            "model.language_model.layers.22.self_attn*",
+            "model.language_model.layers.23.mlp.gate",
+            "model.language_model.layers.23.mlp.shared_experts*",
+            "model.language_model.layers.23.self_attn*",
+            "model.language_model.layers.24.mlp.gate",
+            "model.language_model.layers.24.mlp.shared_experts*",
+            "model.language_model.layers.24.self_attn*",
+            "model.language_model.layers.25.mlp.gate",
+            "model.language_model.layers.25.mlp.shared_experts*",
+            "model.language_model.layers.25.self_attn*",
+            "model.language_model.layers.26.mlp.gate",
+            "model.language_model.layers.26.mlp.shared_experts*",
+            "model.language_model.layers.26.self_attn*",
+            "model.language_model.layers.27.mlp.gate",
+            "model.language_model.layers.27.mlp.shared_experts*",
+            "model.language_model.layers.27.self_attn*",
+            "model.language_model.layers.28.mlp.gate",
+            "model.language_model.layers.28.mlp.shared_experts*",
+            "model.language_model.layers.28.self_attn*",
+            "model.language_model.layers.29.mlp.gate",
+            "model.language_model.layers.29.mlp.shared_experts*",
+            "model.language_model.layers.29.self_attn*",
+            "model.language_model.layers.3.mlp.gate",
+            "model.language_model.layers.3.mlp.shared_experts*",
+            "model.language_model.layers.3.self_attn*",
+            "model.language_model.layers.30.mlp.gate",
+            "model.language_model.layers.30.mlp.shared_experts*",
+            "model.language_model.layers.30.self_attn*",
+            "model.language_model.layers.31.mlp.gate",
+            "model.language_model.layers.31.mlp.shared_experts*",
+            "model.language_model.layers.31.self_attn*",
+            "model.language_model.layers.32.mlp.gate",
+            "model.language_model.layers.32.mlp.shared_experts*",
+            "model.language_model.layers.32.self_attn*",
+            "model.language_model.layers.33.mlp.gate",
+            "model.language_model.layers.33.mlp.shared_experts*",
+            "model.language_model.layers.33.self_attn*",
+            "model.language_model.layers.34.mlp.gate",
+            "model.language_model.layers.34.mlp.shared_experts*",
+            "model.language_model.layers.34.self_attn*",
+            "model.language_model.layers.35.mlp.gate",
+            "model.language_model.layers.35.mlp.shared_experts*",
+            "model.language_model.layers.35.self_attn*",
+            "model.language_model.layers.36.mlp.gate",
+            "model.language_model.layers.36.mlp.shared_experts*",
+            "model.language_model.layers.36.self_attn*",
+            "model.language_model.layers.37.mlp.gate",
+            "model.language_model.layers.37.mlp.shared_experts*",
+            "model.language_model.layers.37.self_attn*",
+            "model.language_model.layers.38.mlp.gate",
+            "model.language_model.layers.38.mlp.shared_experts*",
+            "model.language_model.layers.38.self_attn*",
+            "model.language_model.layers.39.mlp.gate",
+            "model.language_model.layers.39.mlp.shared_experts*",
+            "model.language_model.layers.39.self_attn*",
+            "model.language_model.layers.4.mlp.gate",
+            "model.language_model.layers.4.mlp.shared_experts*",
+            "model.language_model.layers.4.self_attn*",
+            "model.language_model.layers.40.mlp.gate",
+            "model.language_model.layers.40.mlp.shared_experts*",
+            "model.language_model.layers.40.self_attn*",
+            "model.language_model.layers.41.mlp.gate",
+            "model.language_model.layers.41.mlp.shared_experts*",
+            "model.language_model.layers.41.self_attn*",
+            "model.language_model.layers.42.mlp.gate",
+            "model.language_model.layers.42.mlp.shared_experts*",
+            "model.language_model.layers.42.self_attn*",
+            "model.language_model.layers.43.mlp.gate",
+            "model.language_model.layers.43.mlp.shared_experts*",
+            "model.language_model.layers.43.self_attn*",
+            "model.language_model.layers.44.mlp.gate",
+            "model.language_model.layers.44.mlp.shared_experts*",
+            "model.language_model.layers.44.self_attn*",
+            "model.language_model.layers.5.mlp.gate",
+            "model.language_model.layers.5.mlp.shared_experts*",
+            "model.language_model.layers.5.self_attn*",
+            "model.language_model.layers.6.mlp.gate",
+            "model.language_model.layers.6.mlp.shared_experts*",
+            "model.language_model.layers.6.self_attn*",
+            "model.language_model.layers.7.mlp.gate",
+            "model.language_model.layers.7.mlp.shared_experts*",
+            "model.language_model.layers.7.self_attn*",
+            "model.language_model.layers.8.mlp.gate",
+            "model.language_model.layers.8.mlp.shared_experts*",
+            "model.language_model.layers.8.self_attn*",
+            "model.language_model.layers.9.mlp.gate",
+            "model.language_model.layers.9.mlp.shared_experts*",
+            "model.language_model.layers.9.self_attn*",
+            "model.visual*"
+        ]
+    }
+}

model-00001-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7ee3e2a0bd7452b7ccea70bd18f7221676a709a3d4c050d1457fa7d7359125
+size 8945680672

model-00002-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afab1480693d8a37faba2f092b0626b121f6fce9241478ad95cf857145ddc41
+size 8945659984

model-00003-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f184e8b75db437579fa571d4693d6fba7a2806e531d3b8e05d13b1dbc0a90142
+size 8945740832

model-00004-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd08e62f3f86dad5ac784e68eb956fa20a18bab72d81337d3058af281ce18c93
+size 5985863344

model-00005-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc763b5eec6911a7750b6e37d7f499d6226535792be5c7e7a169d1abb09875d6
+size 5985909512

model-00006-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d9597fad87af3b54dbcf994be2b65cd99fc458e392e34f22eeac4af502e4fc
+size 5915365198

model-00007-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0f68feb7fe4cee3bd87a464c845843594e0039124941c2a89e7c1ce9da9e2b
+size 5915359020

model-00008-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4d7657a3d6fe137b9de14a917d84e511fc9b206fe76bd943d1e53deedba857
+size 5915364798

model-00009-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4770820b433f6ca50c7d30f0b2eaa9df6fd7c095769f51ee46aa519c37e5f7d3
+size 5915358812

model-00010-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be92de14713dc46c0b0c8c87f1c02395b2eeb6059087c69d0a39d01dee34edd8
+size 5915358494

model-00011-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3294966995e1a81525c6a9efdeb6a27c599a4d04b4e3a5342331298a527d0be
+size 5915358332

model-00012-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6f4b1a555377bfa773981a4c0d84a86ee782501613a18a3e86caefbace7f66
+size 5915083008

model-00013-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d5c86fa3566eb099f99677550f44191c77faa935491d6d2c5a7c337797eaf9
+size 5915639642

model-00014-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6c81655a572a2462dea772bed6fd5114017f12185a619ce693f6b476be5524
+size 5915084432

model-00015-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff8daa650fcfacd509e15be48f4c986ff7dae081a874fcb4c1ee67d3a66487a
+size 5915642946

model-00016-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286c1a635749f6364c5b4bbab0c7a9eb0916f9421b17f6ade618a5478b25be58
+size 5915084544

model-00017-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be78c2466c0c5d4472c1405ff8631b1da1f0dc059e878d3f6f75bf670514b27
+size 5915653746

model-00018-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5755440acc16e3a935ab60106a99bc9db6cc03d033786e7502e2010a27ff6aa
+size 5915084536

model-00019-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2385071e3600654014011755c97a46e1abe1d2aa988e6fdb7aa2bd4c751b9419
+size 5915653908

model-00020-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8597c39572caa35b1a5e4896ed7c83eb12350ca862dce875071ec2e2d70fec98
+size 5915368968

model-00021-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2923ceb37fd1dcb2772f16aa6d459e472dea3d36275f5c5580781646f27f60
+size 5915366420

model-00022-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f27fac338e9960367a58f0a6ba3681148d52bf38d563d183cac5ab7092b16a6
+size 5915362564

model-00023-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04bbd26640bdf145da1c412aa4c01ef2d0103b2d7e8a2846f207175be461be5d
+size 5915370484

model-00024-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc1b2fdf6ba9816545ce9036c9561cd293f71c887d3d3d1590e86900548fb75
+size 5915084584

model-00025-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a327e0f52b18e7feae2936ebacf33f7a5eff11c96038a06d2547f5653f0838
+size 5915652952

model-00026-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb6db2777bebcf9ea34e9b639a8497ffb0d7c520e00a4e0a0b6331cfb18ac2d
+size 5915084552

model-00027-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e220abe4abb6a4798b1d16fdb7d4f6121b6c6e3e8f8d9f71243ba957a7f9542d
+size 5915652344

model-00028-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b44953c3a5019c4da79260b9abf39bc6fa2b9414f4ede20fea400325aaab3d
+size 5915364684

model-00029-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a705d67e2580270744f26135fc46fd062ea59df6260b45cd628bc2b8a74f6ab2
+size 5915373524

model-00030-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c0e12a793693702303e7d0ebf16e7619fbbc7a45fe2e9e6d038459053f8e1f
+size 5915364844

model-00031-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3a07314659b264b56d84385e89abb5a0199ce944a7cb33eab556832d100075
+size 5915373956

model-00032-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5126cddeb35041953ad0375d926081f7d78b0b279460fa8d1afcdfbe36bca3d1
+size 5915364628

model-00033-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fa7921452627ad9d7913875d78496c60082f71b05f943b5dddb3318f0771c2
+size 5915373132

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26765b2601fd246ef361cfb9f5e10f9fb291a59e05ad0a109062f3a4747c7fd1
+size 16291474

processor_config.json

@@ -0,0 +1,44 @@
+{
+  "image_processor": {
+    "do_rescale": true,
+    "patch_expand_factor": 1,
+    "merge_size": 2,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "temporal_patch_size": 2,
+    "patch_size": 14,
+    "min_image_tokens": 16,
+    "max_image_tokens": 8000,
+    "image_processor_type": "Glm5NextImageProcessor"
+  },
+  "video_processor": {
+    "do_rescale": true,
+    "video_processor_type": "Glm5NextVideoProcessor",
+    "patch_expand_factor": 1,
+    "merge_size": 2,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "temporal_patch_size": 2,
+    "patch_size": 14,
+    "min_image_tokens": 16,
+    "max_image_tokens": 240000,
+    "fps": 2
+  },
+  "processor_class": "Glm5NextProcessor"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
+size 20217442

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>"
+  ],
+  "is_local": true,
+  "model_max_length": 1048576,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}