Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.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 +1,1759 @@
+{
+  "architectures": [
+    "Glm5NextForConditionalGeneration"
+  ],
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "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_topk": 2048,
+    "index_share_for_mtp_iteration": true,
+    "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_conv_kernel_dim": 4,
+    "linear_head_dim": 128,
+    "linear_lower_bound": -5.0,
+    "linear_num_heads": 64,
+    "max_position_embeddings": 1048576,
+    "mhc": 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
+  },
+  "vision_config": {
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "depth": 24,
+    "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
+  },
+  "image_token_id": 154854,
+  "video_token_id": 154855,
+  "image_start_token_id": 154830,
+  "image_end_token_id": 154831,
+  "video_start_token_id": 154832,
+  "video_end_token_id": 154833,
+  "tie_word_embeddings": false,
+  "model_type": "glm5_next",
+  "transformers_version": "5.16.0",
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "modules_to_not_convert": [
+      "attn_mha",
+      "attn_mqa",
+      "dt_bias",
+      "hyper_connection",
+      "lm_head",
+      "mapping_proj",
+      "model.embed_tokens",
+      "model.layers.0.hc_attn_base",
+      "model.layers.0.hc_attn_fn",
+      "model.layers.0.hc_attn_scale",
+      "model.layers.0.hc_ffn_base",
+      "model.layers.0.hc_ffn_fn",
+      "model.layers.0.hc_ffn_scale",
+      "model.layers.0.input_layernorm",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.0.self_attn.A_log",
+      "model.layers.0.self_attn.b_proj",
+      "model.layers.0.self_attn.dt_bias",
+      "model.layers.0.self_attn.f_a_proj",
+      "model.layers.0.self_attn.f_b_proj",
+      "model.layers.0.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.0.self_attn.g_a_proj",
+      "model.layers.0.self_attn.g_b_proj",
+      "model.layers.0.self_attn.k_conv1d",
+      "model.layers.0.self_attn.k_proj",
+      "model.layers.0.self_attn.o_norm",
+      "model.layers.0.self_attn.o_proj",
+      "model.layers.0.self_attn.q_conv1d",
+      "model.layers.0.self_attn.q_proj",
+      "model.layers.0.self_attn.qkv_proj",
+      "model.layers.0.self_attn.v_conv1d",
+      "model.layers.0.self_attn.v_proj",
+      "model.layers.1.hc_attn_base",
+      "model.layers.1.hc_attn_fn",
+      "model.layers.1.hc_attn_scale",
+      "model.layers.1.hc_ffn_base",
+      "model.layers.1.hc_ffn_fn",
+      "model.layers.1.hc_ffn_scale",
+      "model.layers.1.input_layernorm",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.1.self_attn.A_log",
+      "model.layers.1.self_attn.b_proj",
+      "model.layers.1.self_attn.dt_bias",
+      "model.layers.1.self_attn.f_a_proj",
+      "model.layers.1.self_attn.f_b_proj",
+      "model.layers.1.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.1.self_attn.g_a_proj",
+      "model.layers.1.self_attn.g_b_proj",
+      "model.layers.1.self_attn.k_conv1d",
+      "model.layers.1.self_attn.k_proj",
+      "model.layers.1.self_attn.o_norm",
+      "model.layers.1.self_attn.o_proj",
+      "model.layers.1.self_attn.q_conv1d",
+      "model.layers.1.self_attn.q_proj",
+      "model.layers.1.self_attn.qkv_proj",
+      "model.layers.1.self_attn.v_conv1d",
+      "model.layers.1.self_attn.v_proj",
+      "model.layers.10.hc_attn_base",
+      "model.layers.10.hc_attn_fn",
+      "model.layers.10.hc_attn_scale",
+      "model.layers.10.hc_ffn_base",
+      "model.layers.10.hc_ffn_fn",
+      "model.layers.10.hc_ffn_scale",
+      "model.layers.10.input_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.mlp.gate.e_score_correction_bias",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.self_attn.A_log",
+      "model.layers.10.self_attn.b_proj",
+      "model.layers.10.self_attn.dt_bias",
+      "model.layers.10.self_attn.f_a_proj",
+      "model.layers.10.self_attn.f_b_proj",
+      "model.layers.10.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.10.self_attn.g_a_proj",
+      "model.layers.10.self_attn.g_b_proj",
+      "model.layers.10.self_attn.k_conv1d",
+      "model.layers.10.self_attn.k_proj",
+      "model.layers.10.self_attn.o_norm",
+      "model.layers.10.self_attn.o_proj",
+      "model.layers.10.self_attn.q_conv1d",
+      "model.layers.10.self_attn.q_proj",
+      "model.layers.10.self_attn.qkv_proj",
+      "model.layers.10.self_attn.v_conv1d",
+      "model.layers.10.self_attn.v_proj",
+      "model.layers.11.hc_attn_base",
+      "model.layers.11.hc_attn_fn",
+      "model.layers.11.hc_attn_scale",
+      "model.layers.11.hc_ffn_base",
+      "model.layers.11.hc_ffn_fn",
+      "model.layers.11.hc_ffn_scale",
+      "model.layers.11.input_layernorm",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.mlp.gate.e_score_correction_bias",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.11.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.11.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.11.self_attn.indexer.k_norm",
+      "model.layers.11.self_attn.indexer.k_norm.bias",
+      "model.layers.11.self_attn.indexer.weights_proj",
+      "model.layers.11.self_attn.indexer.wk",
+      "model.layers.11.self_attn.indexer.wq_b",
+      "model.layers.11.self_attn.kv_a_layernorm",
+      "model.layers.11.self_attn.kv_b_proj",
+      "model.layers.11.self_attn.q_a_layernorm",
+      "model.layers.12.hc_attn_base",
+      "model.layers.12.hc_attn_fn",
+      "model.layers.12.hc_attn_scale",
+      "model.layers.12.hc_ffn_base",
+      "model.layers.12.hc_ffn_fn",
+      "model.layers.12.hc_ffn_scale",
+      "model.layers.12.input_layernorm",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.gate.e_score_correction_bias",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.12.self_attn.A_log",
+      "model.layers.12.self_attn.b_proj",
+      "model.layers.12.self_attn.dt_bias",
+      "model.layers.12.self_attn.f_a_proj",
+      "model.layers.12.self_attn.f_b_proj",
+      "model.layers.12.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.12.self_attn.g_a_proj",
+      "model.layers.12.self_attn.g_b_proj",
+      "model.layers.12.self_attn.k_conv1d",
+      "model.layers.12.self_attn.k_proj",
+      "model.layers.12.self_attn.o_norm",
+      "model.layers.12.self_attn.o_proj",
+      "model.layers.12.self_attn.q_conv1d",
+      "model.layers.12.self_attn.q_proj",
+      "model.layers.12.self_attn.qkv_proj",
+      "model.layers.12.self_attn.v_conv1d",
+      "model.layers.12.self_attn.v_proj",
+      "model.layers.13.hc_attn_base",
+      "model.layers.13.hc_attn_fn",
+      "model.layers.13.hc_attn_scale",
+      "model.layers.13.hc_ffn_base",
+      "model.layers.13.hc_ffn_fn",
+      "model.layers.13.hc_ffn_scale",
+      "model.layers.13.input_layernorm",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.mlp.gate.e_score_correction_bias",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.13.self_attn.A_log",
+      "model.layers.13.self_attn.b_proj",
+      "model.layers.13.self_attn.dt_bias",
+      "model.layers.13.self_attn.f_a_proj",
+      "model.layers.13.self_attn.f_b_proj",
+      "model.layers.13.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.13.self_attn.g_a_proj",
+      "model.layers.13.self_attn.g_b_proj",
+      "model.layers.13.self_attn.k_conv1d",
+      "model.layers.13.self_attn.k_proj",
+      "model.layers.13.self_attn.o_norm",
+      "model.layers.13.self_attn.o_proj",
+      "model.layers.13.self_attn.q_conv1d",
+      "model.layers.13.self_attn.q_proj",
+      "model.layers.13.self_attn.qkv_proj",
+      "model.layers.13.self_attn.v_conv1d",
+      "model.layers.13.self_attn.v_proj",
+      "model.layers.14.hc_attn_base",
+      "model.layers.14.hc_attn_fn",
+      "model.layers.14.hc_attn_scale",
+      "model.layers.14.hc_ffn_base",
+      "model.layers.14.hc_ffn_fn",
+      "model.layers.14.hc_ffn_scale",
+      "model.layers.14.input_layernorm",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.mlp.gate.e_score_correction_bias",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.14.self_attn.A_log",
+      "model.layers.14.self_attn.b_proj",
+      "model.layers.14.self_attn.dt_bias",
+      "model.layers.14.self_attn.f_a_proj",
+      "model.layers.14.self_attn.f_b_proj",
+      "model.layers.14.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.14.self_attn.g_a_proj",
+      "model.layers.14.self_attn.g_b_proj",
+      "model.layers.14.self_attn.k_conv1d",
+      "model.layers.14.self_attn.k_proj",
+      "model.layers.14.self_attn.o_norm",
+      "model.layers.14.self_attn.o_proj",
+      "model.layers.14.self_attn.q_conv1d",
+      "model.layers.14.self_attn.q_proj",
+      "model.layers.14.self_attn.qkv_proj",
+      "model.layers.14.self_attn.v_conv1d",
+      "model.layers.14.self_attn.v_proj",
+      "model.layers.15.hc_attn_base",
+      "model.layers.15.hc_attn_fn",
+      "model.layers.15.hc_attn_scale",
+      "model.layers.15.hc_ffn_base",
+      "model.layers.15.hc_ffn_fn",
+      "model.layers.15.hc_ffn_scale",
+      "model.layers.15.input_layernorm",
+      "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.gate.e_score_correction_bias",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.15.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.15.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.15.self_attn.indexer.k_norm",
+      "model.layers.15.self_attn.indexer.k_norm.bias",
+      "model.layers.15.self_attn.indexer.weights_proj",
+      "model.layers.15.self_attn.indexer.wk",
+      "model.layers.15.self_attn.indexer.wq_b",
+      "model.layers.15.self_attn.kv_a_layernorm",
+      "model.layers.15.self_attn.kv_b_proj",
+      "model.layers.15.self_attn.q_a_layernorm",
+      "model.layers.16.hc_attn_base",
+      "model.layers.16.hc_attn_fn",
+      "model.layers.16.hc_attn_scale",
+      "model.layers.16.hc_ffn_base",
+      "model.layers.16.hc_ffn_fn",
+      "model.layers.16.hc_ffn_scale",
+      "model.layers.16.input_layernorm",
+      "model.layers.16.mlp.gate",
+      "model.layers.16.mlp.gate.e_score_correction_bias",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.16.self_attn.A_log",
+      "model.layers.16.self_attn.b_proj",
+      "model.layers.16.self_attn.dt_bias",
+      "model.layers.16.self_attn.f_a_proj",
+      "model.layers.16.self_attn.f_b_proj",
+      "model.layers.16.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.16.self_attn.g_a_proj",
+      "model.layers.16.self_attn.g_b_proj",
+      "model.layers.16.self_attn.k_conv1d",
+      "model.layers.16.self_attn.k_proj",
+      "model.layers.16.self_attn.o_norm",
+      "model.layers.16.self_attn.o_proj",
+      "model.layers.16.self_attn.q_conv1d",
+      "model.layers.16.self_attn.q_proj",
+      "model.layers.16.self_attn.qkv_proj",
+      "model.layers.16.self_attn.v_conv1d",
+      "model.layers.16.self_attn.v_proj",
+      "model.layers.17.hc_attn_base",
+      "model.layers.17.hc_attn_fn",
+      "model.layers.17.hc_attn_scale",
+      "model.layers.17.hc_ffn_base",
+      "model.layers.17.hc_ffn_fn",
+      "model.layers.17.hc_ffn_scale",
+      "model.layers.17.input_layernorm",
+      "model.layers.17.mlp.gate",
+      "model.layers.17.mlp.gate.e_score_correction_bias",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.17.self_attn.A_log",
+      "model.layers.17.self_attn.b_proj",
+      "model.layers.17.self_attn.dt_bias",
+      "model.layers.17.self_attn.f_a_proj",
+      "model.layers.17.self_attn.f_b_proj",
+      "model.layers.17.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.17.self_attn.g_a_proj",
+      "model.layers.17.self_attn.g_b_proj",
+      "model.layers.17.self_attn.k_conv1d",
+      "model.layers.17.self_attn.k_proj",
+      "model.layers.17.self_attn.o_norm",
+      "model.layers.17.self_attn.o_proj",
+      "model.layers.17.self_attn.q_conv1d",
+      "model.layers.17.self_attn.q_proj",
+      "model.layers.17.self_attn.qkv_proj",
+      "model.layers.17.self_attn.v_conv1d",
+      "model.layers.17.self_attn.v_proj",
+      "model.layers.18.hc_attn_base",
+      "model.layers.18.hc_attn_fn",
+      "model.layers.18.hc_attn_scale",
+      "model.layers.18.hc_ffn_base",
+      "model.layers.18.hc_ffn_fn",
+      "model.layers.18.hc_ffn_scale",
+      "model.layers.18.input_layernorm",
+      "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.gate.e_score_correction_bias",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.18.self_attn.A_log",
+      "model.layers.18.self_attn.b_proj",
+      "model.layers.18.self_attn.dt_bias",
+      "model.layers.18.self_attn.f_a_proj",
+      "model.layers.18.self_attn.f_b_proj",
+      "model.layers.18.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.18.self_attn.g_a_proj",
+      "model.layers.18.self_attn.g_b_proj",
+      "model.layers.18.self_attn.k_conv1d",
+      "model.layers.18.self_attn.k_proj",
+      "model.layers.18.self_attn.o_norm",
+      "model.layers.18.self_attn.o_proj",
+      "model.layers.18.self_attn.q_conv1d",
+      "model.layers.18.self_attn.q_proj",
+      "model.layers.18.self_attn.qkv_proj",
+      "model.layers.18.self_attn.v_conv1d",
+      "model.layers.18.self_attn.v_proj",
+      "model.layers.19.hc_attn_base",
+      "model.layers.19.hc_attn_fn",
+      "model.layers.19.hc_attn_scale",
+      "model.layers.19.hc_ffn_base",
+      "model.layers.19.hc_ffn_fn",
+      "model.layers.19.hc_ffn_scale",
+      "model.layers.19.input_layernorm",
+      "model.layers.19.mlp.gate",
+      "model.layers.19.mlp.gate.e_score_correction_bias",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.19.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.19.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.19.self_attn.indexer.k_norm",
+      "model.layers.19.self_attn.indexer.k_norm.bias",
+      "model.layers.19.self_attn.indexer.weights_proj",
+      "model.layers.19.self_attn.indexer.wk",
+      "model.layers.19.self_attn.indexer.wq_b",
+      "model.layers.19.self_attn.kv_a_layernorm",
+      "model.layers.19.self_attn.kv_b_proj",
+      "model.layers.19.self_attn.q_a_layernorm",
+      "model.layers.2.hc_attn_base",
+      "model.layers.2.hc_attn_fn",
+      "model.layers.2.hc_attn_scale",
+      "model.layers.2.hc_ffn_base",
+      "model.layers.2.hc_ffn_fn",
+      "model.layers.2.hc_ffn_scale",
+      "model.layers.2.input_layernorm",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.2.self_attn.A_log",
+      "model.layers.2.self_attn.b_proj",
+      "model.layers.2.self_attn.dt_bias",
+      "model.layers.2.self_attn.f_a_proj",
+      "model.layers.2.self_attn.f_b_proj",
+      "model.layers.2.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.2.self_attn.g_a_proj",
+      "model.layers.2.self_attn.g_b_proj",
+      "model.layers.2.self_attn.k_conv1d",
+      "model.layers.2.self_attn.k_proj",
+      "model.layers.2.self_attn.o_norm",
+      "model.layers.2.self_attn.o_proj",
+      "model.layers.2.self_attn.q_conv1d",
+      "model.layers.2.self_attn.q_proj",
+      "model.layers.2.self_attn.qkv_proj",
+      "model.layers.2.self_attn.v_conv1d",
+      "model.layers.2.self_attn.v_proj",
+      "model.layers.20.hc_attn_base",
+      "model.layers.20.hc_attn_fn",
+      "model.layers.20.hc_attn_scale",
+      "model.layers.20.hc_ffn_base",
+      "model.layers.20.hc_ffn_fn",
+      "model.layers.20.hc_ffn_scale",
+      "model.layers.20.input_layernorm",
+      "model.layers.20.mlp.gate",
+      "model.layers.20.mlp.gate.e_score_correction_bias",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.20.self_attn.A_log",
+      "model.layers.20.self_attn.b_proj",
+      "model.layers.20.self_attn.dt_bias",
+      "model.layers.20.self_attn.f_a_proj",
+      "model.layers.20.self_attn.f_b_proj",
+      "model.layers.20.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.20.self_attn.g_a_proj",
+      "model.layers.20.self_attn.g_b_proj",
+      "model.layers.20.self_attn.k_conv1d",
+      "model.layers.20.self_attn.k_proj",
+      "model.layers.20.self_attn.o_norm",
+      "model.layers.20.self_attn.o_proj",
+      "model.layers.20.self_attn.q_conv1d",
+      "model.layers.20.self_attn.q_proj",
+      "model.layers.20.self_attn.qkv_proj",
+      "model.layers.20.self_attn.v_conv1d",
+      "model.layers.20.self_attn.v_proj",
+      "model.layers.21.hc_attn_base",
+      "model.layers.21.hc_attn_fn",
+      "model.layers.21.hc_attn_scale",
+      "model.layers.21.hc_ffn_base",
+      "model.layers.21.hc_ffn_fn",
+      "model.layers.21.hc_ffn_scale",
+      "model.layers.21.input_layernorm",
+      "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.gate.e_score_correction_bias",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.21.self_attn.A_log",
+      "model.layers.21.self_attn.b_proj",
+      "model.layers.21.self_attn.dt_bias",
+      "model.layers.21.self_attn.f_a_proj",
+      "model.layers.21.self_attn.f_b_proj",
+      "model.layers.21.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.21.self_attn.g_a_proj",
+      "model.layers.21.self_attn.g_b_proj",
+      "model.layers.21.self_attn.k_conv1d",
+      "model.layers.21.self_attn.k_proj",
+      "model.layers.21.self_attn.o_norm",
+      "model.layers.21.self_attn.o_proj",
+      "model.layers.21.self_attn.q_conv1d",
+      "model.layers.21.self_attn.q_proj",
+      "model.layers.21.self_attn.qkv_proj",
+      "model.layers.21.self_attn.v_conv1d",
+      "model.layers.21.self_attn.v_proj",
+      "model.layers.22.hc_attn_base",
+      "model.layers.22.hc_attn_fn",
+      "model.layers.22.hc_attn_scale",
+      "model.layers.22.hc_ffn_base",
+      "model.layers.22.hc_ffn_fn",
+      "model.layers.22.hc_ffn_scale",
+      "model.layers.22.input_layernorm",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.mlp.gate.e_score_correction_bias",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.22.self_attn.A_log",
+      "model.layers.22.self_attn.b_proj",
+      "model.layers.22.self_attn.dt_bias",
+      "model.layers.22.self_attn.f_a_proj",
+      "model.layers.22.self_attn.f_b_proj",
+      "model.layers.22.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.22.self_attn.g_a_proj",
+      "model.layers.22.self_attn.g_b_proj",
+      "model.layers.22.self_attn.k_conv1d",
+      "model.layers.22.self_attn.k_proj",
+      "model.layers.22.self_attn.o_norm",
+      "model.layers.22.self_attn.o_proj",
+      "model.layers.22.self_attn.q_conv1d",
+      "model.layers.22.self_attn.q_proj",
+      "model.layers.22.self_attn.qkv_proj",
+      "model.layers.22.self_attn.v_conv1d",
+      "model.layers.22.self_attn.v_proj",
+      "model.layers.23.hc_attn_base",
+      "model.layers.23.hc_attn_fn",
+      "model.layers.23.hc_attn_scale",
+      "model.layers.23.hc_ffn_base",
+      "model.layers.23.hc_ffn_fn",
+      "model.layers.23.hc_ffn_scale",
+      "model.layers.23.input_layernorm",
+      "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.gate.e_score_correction_bias",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.23.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.23.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.23.self_attn.indexer.k_norm",
+      "model.layers.23.self_attn.indexer.k_norm.bias",
+      "model.layers.23.self_attn.indexer.weights_proj",
+      "model.layers.23.self_attn.indexer.wk",
+      "model.layers.23.self_attn.indexer.wq_b",
+      "model.layers.23.self_attn.kv_a_layernorm",
+      "model.layers.23.self_attn.kv_b_proj",
+      "model.layers.23.self_attn.q_a_layernorm",
+      "model.layers.24.hc_attn_base",
+      "model.layers.24.hc_attn_fn",
+      "model.layers.24.hc_attn_scale",
+      "model.layers.24.hc_ffn_base",
+      "model.layers.24.hc_ffn_fn",
+      "model.layers.24.hc_ffn_scale",
+      "model.layers.24.input_layernorm",
+      "model.layers.24.mlp.gate",
+      "model.layers.24.mlp.gate.e_score_correction_bias",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.24.self_attn.A_log",
+      "model.layers.24.self_attn.b_proj",
+      "model.layers.24.self_attn.dt_bias",
+      "model.layers.24.self_attn.f_a_proj",
+      "model.layers.24.self_attn.f_b_proj",
+      "model.layers.24.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.24.self_attn.g_a_proj",
+      "model.layers.24.self_attn.g_b_proj",
+      "model.layers.24.self_attn.k_conv1d",
+      "model.layers.24.self_attn.k_proj",
+      "model.layers.24.self_attn.o_norm",
+      "model.layers.24.self_attn.o_proj",
+      "model.layers.24.self_attn.q_conv1d",
+      "model.layers.24.self_attn.q_proj",
+      "model.layers.24.self_attn.qkv_proj",
+      "model.layers.24.self_attn.v_conv1d",
+      "model.layers.24.self_attn.v_proj",
+      "model.layers.25.hc_attn_base",
+      "model.layers.25.hc_attn_fn",
+      "model.layers.25.hc_attn_scale",
+      "model.layers.25.hc_ffn_base",
+      "model.layers.25.hc_ffn_fn",
+      "model.layers.25.hc_ffn_scale",
+      "model.layers.25.input_layernorm",
+      "model.layers.25.mlp.gate",
+      "model.layers.25.mlp.gate.e_score_correction_bias",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.25.self_attn.A_log",
+      "model.layers.25.self_attn.b_proj",
+      "model.layers.25.self_attn.dt_bias",
+      "model.layers.25.self_attn.f_a_proj",
+      "model.layers.25.self_attn.f_b_proj",
+      "model.layers.25.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.25.self_attn.g_a_proj",
+      "model.layers.25.self_attn.g_b_proj",
+      "model.layers.25.self_attn.k_conv1d",
+      "model.layers.25.self_attn.k_proj",
+      "model.layers.25.self_attn.o_norm",
+      "model.layers.25.self_attn.o_proj",
+      "model.layers.25.self_attn.q_conv1d",
+      "model.layers.25.self_attn.q_proj",
+      "model.layers.25.self_attn.qkv_proj",
+      "model.layers.25.self_attn.v_conv1d",
+      "model.layers.25.self_attn.v_proj",
+      "model.layers.26.hc_attn_base",
+      "model.layers.26.hc_attn_fn",
+      "model.layers.26.hc_attn_scale",
+      "model.layers.26.hc_ffn_base",
+      "model.layers.26.hc_ffn_fn",
+      "model.layers.26.hc_ffn_scale",
+      "model.layers.26.input_layernorm",
+      "model.layers.26.mlp.gate",
+      "model.layers.26.mlp.gate.e_score_correction_bias",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.26.self_attn.A_log",
+      "model.layers.26.self_attn.b_proj",
+      "model.layers.26.self_attn.dt_bias",
+      "model.layers.26.self_attn.f_a_proj",
+      "model.layers.26.self_attn.f_b_proj",
+      "model.layers.26.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.26.self_attn.g_a_proj",
+      "model.layers.26.self_attn.g_b_proj",
+      "model.layers.26.self_attn.k_conv1d",
+      "model.layers.26.self_attn.k_proj",
+      "model.layers.26.self_attn.o_norm",
+      "model.layers.26.self_attn.o_proj",
+      "model.layers.26.self_attn.q_conv1d",
+      "model.layers.26.self_attn.q_proj",
+      "model.layers.26.self_attn.qkv_proj",
+      "model.layers.26.self_attn.v_conv1d",
+      "model.layers.26.self_attn.v_proj",
+      "model.layers.27.hc_attn_base",
+      "model.layers.27.hc_attn_fn",
+      "model.layers.27.hc_attn_scale",
+      "model.layers.27.hc_ffn_base",
+      "model.layers.27.hc_ffn_fn",
+      "model.layers.27.hc_ffn_scale",
+      "model.layers.27.input_layernorm",
+      "model.layers.27.mlp.gate",
+      "model.layers.27.mlp.gate.e_score_correction_bias",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.27.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.27.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.27.self_attn.indexer.k_norm",
+      "model.layers.27.self_attn.indexer.k_norm.bias",
+      "model.layers.27.self_attn.indexer.weights_proj",
+      "model.layers.27.self_attn.indexer.wk",
+      "model.layers.27.self_attn.indexer.wq_b",
+      "model.layers.27.self_attn.kv_a_layernorm",
+      "model.layers.27.self_attn.kv_b_proj",
+      "model.layers.27.self_attn.q_a_layernorm",
+      "model.layers.28.hc_attn_base",
+      "model.layers.28.hc_attn_fn",
+      "model.layers.28.hc_attn_scale",
+      "model.layers.28.hc_ffn_base",
+      "model.layers.28.hc_ffn_fn",
+      "model.layers.28.hc_ffn_scale",
+      "model.layers.28.input_layernorm",
+      "model.layers.28.mlp.gate",
+      "model.layers.28.mlp.gate.e_score_correction_bias",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.28.self_attn.A_log",
+      "model.layers.28.self_attn.b_proj",
+      "model.layers.28.self_attn.dt_bias",
+      "model.layers.28.self_attn.f_a_proj",
+      "model.layers.28.self_attn.f_b_proj",
+      "model.layers.28.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.28.self_attn.g_a_proj",
+      "model.layers.28.self_attn.g_b_proj",
+      "model.layers.28.self_attn.k_conv1d",
+      "model.layers.28.self_attn.k_proj",
+      "model.layers.28.self_attn.o_norm",
+      "model.layers.28.self_attn.o_proj",
+      "model.layers.28.self_attn.q_conv1d",
+      "model.layers.28.self_attn.q_proj",
+      "model.layers.28.self_attn.qkv_proj",
+      "model.layers.28.self_attn.v_conv1d",
+      "model.layers.28.self_attn.v_proj",
+      "model.layers.29.hc_attn_base",
+      "model.layers.29.hc_attn_fn",
+      "model.layers.29.hc_attn_scale",
+      "model.layers.29.hc_ffn_base",
+      "model.layers.29.hc_ffn_fn",
+      "model.layers.29.hc_ffn_scale",
+      "model.layers.29.input_layernorm",
+      "model.layers.29.mlp.gate",
+      "model.layers.29.mlp.gate.e_score_correction_bias",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.29.self_attn.A_log",
+      "model.layers.29.self_attn.b_proj",
+      "model.layers.29.self_attn.dt_bias",
+      "model.layers.29.self_attn.f_a_proj",
+      "model.layers.29.self_attn.f_b_proj",
+      "model.layers.29.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.29.self_attn.g_a_proj",
+      "model.layers.29.self_attn.g_b_proj",
+      "model.layers.29.self_attn.k_conv1d",
+      "model.layers.29.self_attn.k_proj",
+      "model.layers.29.self_attn.o_norm",
+      "model.layers.29.self_attn.o_proj",
+      "model.layers.29.self_attn.q_conv1d",
+      "model.layers.29.self_attn.q_proj",
+      "model.layers.29.self_attn.qkv_proj",
+      "model.layers.29.self_attn.v_conv1d",
+      "model.layers.29.self_attn.v_proj",
+      "model.layers.3.hc_attn_base",
+      "model.layers.3.hc_attn_fn",
+      "model.layers.3.hc_attn_scale",
+      "model.layers.3.hc_ffn_base",
+      "model.layers.3.hc_ffn_fn",
+      "model.layers.3.hc_ffn_scale",
+      "model.layers.3.input_layernorm",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.gate.e_score_correction_bias",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.3.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.3.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.3.self_attn.indexer.k_norm",
+      "model.layers.3.self_attn.indexer.k_norm.bias",
+      "model.layers.3.self_attn.indexer.weights_proj",
+      "model.layers.3.self_attn.indexer.wk",
+      "model.layers.3.self_attn.indexer.wq_b",
+      "model.layers.3.self_attn.kv_a_layernorm",
+      "model.layers.3.self_attn.kv_b_proj",
+      "model.layers.3.self_attn.q_a_layernorm",
+      "model.layers.30.hc_attn_base",
+      "model.layers.30.hc_attn_fn",
+      "model.layers.30.hc_attn_scale",
+      "model.layers.30.hc_ffn_base",
+      "model.layers.30.hc_ffn_fn",
+      "model.layers.30.hc_ffn_scale",
+      "model.layers.30.input_layernorm",
+      "model.layers.30.mlp.gate",
+      "model.layers.30.mlp.gate.e_score_correction_bias",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.30.self_attn.A_log",
+      "model.layers.30.self_attn.b_proj",
+      "model.layers.30.self_attn.dt_bias",
+      "model.layers.30.self_attn.f_a_proj",
+      "model.layers.30.self_attn.f_b_proj",
+      "model.layers.30.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.30.self_attn.g_a_proj",
+      "model.layers.30.self_attn.g_b_proj",
+      "model.layers.30.self_attn.k_conv1d",
+      "model.layers.30.self_attn.k_proj",
+      "model.layers.30.self_attn.o_norm",
+      "model.layers.30.self_attn.o_proj",
+      "model.layers.30.self_attn.q_conv1d",
+      "model.layers.30.self_attn.q_proj",
+      "model.layers.30.self_attn.qkv_proj",
+      "model.layers.30.self_attn.v_conv1d",
+      "model.layers.30.self_attn.v_proj",
+      "model.layers.31.hc_attn_base",
+      "model.layers.31.hc_attn_fn",
+      "model.layers.31.hc_attn_scale",
+      "model.layers.31.hc_ffn_base",
+      "model.layers.31.hc_ffn_fn",
+      "model.layers.31.hc_ffn_scale",
+      "model.layers.31.input_layernorm",
+      "model.layers.31.mlp.gate",
+      "model.layers.31.mlp.gate.e_score_correction_bias",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.31.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.31.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.31.self_attn.indexer.k_norm",
+      "model.layers.31.self_attn.indexer.k_norm.bias",
+      "model.layers.31.self_attn.indexer.weights_proj",
+      "model.layers.31.self_attn.indexer.wk",
+      "model.layers.31.self_attn.indexer.wq_b",
+      "model.layers.31.self_attn.kv_a_layernorm",
+      "model.layers.31.self_attn.kv_b_proj",
+      "model.layers.31.self_attn.q_a_layernorm",
+      "model.layers.32.hc_attn_base",
+      "model.layers.32.hc_attn_fn",
+      "model.layers.32.hc_attn_scale",
+      "model.layers.32.hc_ffn_base",
+      "model.layers.32.hc_ffn_fn",
+      "model.layers.32.hc_ffn_scale",
+      "model.layers.32.input_layernorm",
+      "model.layers.32.mlp.gate",
+      "model.layers.32.mlp.gate.e_score_correction_bias",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.32.self_attn.A_log",
+      "model.layers.32.self_attn.b_proj",
+      "model.layers.32.self_attn.dt_bias",
+      "model.layers.32.self_attn.f_a_proj",
+      "model.layers.32.self_attn.f_b_proj",
+      "model.layers.32.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.32.self_attn.g_a_proj",
+      "model.layers.32.self_attn.g_b_proj",
+      "model.layers.32.self_attn.k_conv1d",
+      "model.layers.32.self_attn.k_proj",
+      "model.layers.32.self_attn.o_norm",
+      "model.layers.32.self_attn.o_proj",
+      "model.layers.32.self_attn.q_conv1d",
+      "model.layers.32.self_attn.q_proj",
+      "model.layers.32.self_attn.qkv_proj",
+      "model.layers.32.self_attn.v_conv1d",
+      "model.layers.32.self_attn.v_proj",
+      "model.layers.33.hc_attn_base",
+      "model.layers.33.hc_attn_fn",
+      "model.layers.33.hc_attn_scale",
+      "model.layers.33.hc_ffn_base",
+      "model.layers.33.hc_ffn_fn",
+      "model.layers.33.hc_ffn_scale",
+      "model.layers.33.input_layernorm",
+      "model.layers.33.mlp.gate",
+      "model.layers.33.mlp.gate.e_score_correction_bias",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.33.self_attn.A_log",
+      "model.layers.33.self_attn.b_proj",
+      "model.layers.33.self_attn.dt_bias",
+      "model.layers.33.self_attn.f_a_proj",
+      "model.layers.33.self_attn.f_b_proj",
+      "model.layers.33.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.33.self_attn.g_a_proj",
+      "model.layers.33.self_attn.g_b_proj",
+      "model.layers.33.self_attn.k_conv1d",
+      "model.layers.33.self_attn.k_proj",
+      "model.layers.33.self_attn.o_norm",
+      "model.layers.33.self_attn.o_proj",
+      "model.layers.33.self_attn.q_conv1d",
+      "model.layers.33.self_attn.q_proj",
+      "model.layers.33.self_attn.qkv_proj",
+      "model.layers.33.self_attn.v_conv1d",
+      "model.layers.33.self_attn.v_proj",
+      "model.layers.34.hc_attn_base",
+      "model.layers.34.hc_attn_fn",
+      "model.layers.34.hc_attn_scale",
+      "model.layers.34.hc_ffn_base",
+      "model.layers.34.hc_ffn_fn",
+      "model.layers.34.hc_ffn_scale",
+      "model.layers.34.input_layernorm",
+      "model.layers.34.mlp.gate",
+      "model.layers.34.mlp.gate.e_score_correction_bias",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.34.self_attn.A_log",
+      "model.layers.34.self_attn.b_proj",
+      "model.layers.34.self_attn.dt_bias",
+      "model.layers.34.self_attn.f_a_proj",
+      "model.layers.34.self_attn.f_b_proj",
+      "model.layers.34.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.34.self_attn.g_a_proj",
+      "model.layers.34.self_attn.g_b_proj",
+      "model.layers.34.self_attn.k_conv1d",
+      "model.layers.34.self_attn.k_proj",
+      "model.layers.34.self_attn.o_norm",
+      "model.layers.34.self_attn.o_proj",
+      "model.layers.34.self_attn.q_conv1d",
+      "model.layers.34.self_attn.q_proj",
+      "model.layers.34.self_attn.qkv_proj",
+      "model.layers.34.self_attn.v_conv1d",
+      "model.layers.34.self_attn.v_proj",
+      "model.layers.35.hc_attn_base",
+      "model.layers.35.hc_attn_fn",
+      "model.layers.35.hc_attn_scale",
+      "model.layers.35.hc_ffn_base",
+      "model.layers.35.hc_ffn_fn",
+      "model.layers.35.hc_ffn_scale",
+      "model.layers.35.input_layernorm",
+      "model.layers.35.mlp.gate",
+      "model.layers.35.mlp.gate.e_score_correction_bias",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.35.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.35.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.35.self_attn.indexer.k_norm",
+      "model.layers.35.self_attn.indexer.k_norm.bias",
+      "model.layers.35.self_attn.indexer.weights_proj",
+      "model.layers.35.self_attn.indexer.wk",
+      "model.layers.35.self_attn.indexer.wq_b",
+      "model.layers.35.self_attn.kv_a_layernorm",
+      "model.layers.35.self_attn.kv_b_proj",
+      "model.layers.35.self_attn.q_a_layernorm",
+      "model.layers.36.hc_attn_base",
+      "model.layers.36.hc_attn_fn",
+      "model.layers.36.hc_attn_scale",
+      "model.layers.36.hc_ffn_base",
+      "model.layers.36.hc_ffn_fn",
+      "model.layers.36.hc_ffn_scale",
+      "model.layers.36.input_layernorm",
+      "model.layers.36.mlp.gate",
+      "model.layers.36.mlp.gate.e_score_correction_bias",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.36.self_attn.A_log",
+      "model.layers.36.self_attn.b_proj",
+      "model.layers.36.self_attn.dt_bias",
+      "model.layers.36.self_attn.f_a_proj",
+      "model.layers.36.self_attn.f_b_proj",
+      "model.layers.36.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.36.self_attn.g_a_proj",
+      "model.layers.36.self_attn.g_b_proj",
+      "model.layers.36.self_attn.k_conv1d",
+      "model.layers.36.self_attn.k_proj",
+      "model.layers.36.self_attn.o_norm",
+      "model.layers.36.self_attn.o_proj",
+      "model.layers.36.self_attn.q_conv1d",
+      "model.layers.36.self_attn.q_proj",
+      "model.layers.36.self_attn.qkv_proj",
+      "model.layers.36.self_attn.v_conv1d",
+      "model.layers.36.self_attn.v_proj",
+      "model.layers.37.hc_attn_base",
+      "model.layers.37.hc_attn_fn",
+      "model.layers.37.hc_attn_scale",
+      "model.layers.37.hc_ffn_base",
+      "model.layers.37.hc_ffn_fn",
+      "model.layers.37.hc_ffn_scale",
+      "model.layers.37.input_layernorm",
+      "model.layers.37.mlp.gate",
+      "model.layers.37.mlp.gate.e_score_correction_bias",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.37.self_attn.A_log",
+      "model.layers.37.self_attn.b_proj",
+      "model.layers.37.self_attn.dt_bias",
+      "model.layers.37.self_attn.f_a_proj",
+      "model.layers.37.self_attn.f_b_proj",
+      "model.layers.37.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.37.self_attn.g_a_proj",
+      "model.layers.37.self_attn.g_b_proj",
+      "model.layers.37.self_attn.k_conv1d",
+      "model.layers.37.self_attn.k_proj",
+      "model.layers.37.self_attn.o_norm",
+      "model.layers.37.self_attn.o_proj",
+      "model.layers.37.self_attn.q_conv1d",
+      "model.layers.37.self_attn.q_proj",
+      "model.layers.37.self_attn.qkv_proj",
+      "model.layers.37.self_attn.v_conv1d",
+      "model.layers.37.self_attn.v_proj",
+      "model.layers.38.hc_attn_base",
+      "model.layers.38.hc_attn_fn",
+      "model.layers.38.hc_attn_scale",
+      "model.layers.38.hc_ffn_base",
+      "model.layers.38.hc_ffn_fn",
+      "model.layers.38.hc_ffn_scale",
+      "model.layers.38.input_layernorm",
+      "model.layers.38.mlp.gate",
+      "model.layers.38.mlp.gate.e_score_correction_bias",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.38.self_attn.A_log",
+      "model.layers.38.self_attn.b_proj",
+      "model.layers.38.self_attn.dt_bias",
+      "model.layers.38.self_attn.f_a_proj",
+      "model.layers.38.self_attn.f_b_proj",
+      "model.layers.38.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.38.self_attn.g_a_proj",
+      "model.layers.38.self_attn.g_b_proj",
+      "model.layers.38.self_attn.k_conv1d",
+      "model.layers.38.self_attn.k_proj",
+      "model.layers.38.self_attn.o_norm",
+      "model.layers.38.self_attn.o_proj",
+      "model.layers.38.self_attn.q_conv1d",
+      "model.layers.38.self_attn.q_proj",
+      "model.layers.38.self_attn.qkv_proj",
+      "model.layers.38.self_attn.v_conv1d",
+      "model.layers.38.self_attn.v_proj",
+      "model.layers.39.hc_attn_base",
+      "model.layers.39.hc_attn_fn",
+      "model.layers.39.hc_attn_scale",
+      "model.layers.39.hc_ffn_base",
+      "model.layers.39.hc_ffn_fn",
+      "model.layers.39.hc_ffn_scale",
+      "model.layers.39.input_layernorm",
+      "model.layers.39.mlp.gate",
+      "model.layers.39.mlp.gate.e_score_correction_bias",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.39.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.39.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.39.self_attn.indexer.k_norm",
+      "model.layers.39.self_attn.indexer.k_norm.bias",
+      "model.layers.39.self_attn.indexer.weights_proj",
+      "model.layers.39.self_attn.indexer.wk",
+      "model.layers.39.self_attn.indexer.wq_b",
+      "model.layers.39.self_attn.kv_a_layernorm",
+      "model.layers.39.self_attn.kv_b_proj",
+      "model.layers.39.self_attn.q_a_layernorm",
+      "model.layers.4.hc_attn_base",
+      "model.layers.4.hc_attn_fn",
+      "model.layers.4.hc_attn_scale",
+      "model.layers.4.hc_ffn_base",
+      "model.layers.4.hc_ffn_fn",
+      "model.layers.4.hc_ffn_scale",
+      "model.layers.4.input_layernorm",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.mlp.gate.e_score_correction_bias",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.4.self_attn.A_log",
+      "model.layers.4.self_attn.b_proj",
+      "model.layers.4.self_attn.dt_bias",
+      "model.layers.4.self_attn.f_a_proj",
+      "model.layers.4.self_attn.f_b_proj",
+      "model.layers.4.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.4.self_attn.g_a_proj",
+      "model.layers.4.self_attn.g_b_proj",
+      "model.layers.4.self_attn.k_conv1d",
+      "model.layers.4.self_attn.k_proj",
+      "model.layers.4.self_attn.o_norm",
+      "model.layers.4.self_attn.o_proj",
+      "model.layers.4.self_attn.q_conv1d",
+      "model.layers.4.self_attn.q_proj",
+      "model.layers.4.self_attn.qkv_proj",
+      "model.layers.4.self_attn.v_conv1d",
+      "model.layers.4.self_attn.v_proj",
+      "model.layers.40.hc_attn_base",
+      "model.layers.40.hc_attn_fn",
+      "model.layers.40.hc_attn_scale",
+      "model.layers.40.hc_ffn_base",
+      "model.layers.40.hc_ffn_fn",
+      "model.layers.40.hc_ffn_scale",
+      "model.layers.40.input_layernorm",
+      "model.layers.40.mlp.gate",
+      "model.layers.40.mlp.gate.e_score_correction_bias",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.40.self_attn.A_log",
+      "model.layers.40.self_attn.b_proj",
+      "model.layers.40.self_attn.dt_bias",
+      "model.layers.40.self_attn.f_a_proj",
+      "model.layers.40.self_attn.f_b_proj",
+      "model.layers.40.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.40.self_attn.g_a_proj",
+      "model.layers.40.self_attn.g_b_proj",
+      "model.layers.40.self_attn.k_conv1d",
+      "model.layers.40.self_attn.k_proj",
+      "model.layers.40.self_attn.o_norm",
+      "model.layers.40.self_attn.o_proj",
+      "model.layers.40.self_attn.q_conv1d",
+      "model.layers.40.self_attn.q_proj",
+      "model.layers.40.self_attn.qkv_proj",
+      "model.layers.40.self_attn.v_conv1d",
+      "model.layers.40.self_attn.v_proj",
+      "model.layers.41.hc_attn_base",
+      "model.layers.41.hc_attn_fn",
+      "model.layers.41.hc_attn_scale",
+      "model.layers.41.hc_ffn_base",
+      "model.layers.41.hc_ffn_fn",
+      "model.layers.41.hc_ffn_scale",
+      "model.layers.41.input_layernorm",
+      "model.layers.41.mlp.gate",
+      "model.layers.41.mlp.gate.e_score_correction_bias",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.41.self_attn.A_log",
+      "model.layers.41.self_attn.b_proj",
+      "model.layers.41.self_attn.dt_bias",
+      "model.layers.41.self_attn.f_a_proj",
+      "model.layers.41.self_attn.f_b_proj",
+      "model.layers.41.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.41.self_attn.g_a_proj",
+      "model.layers.41.self_attn.g_b_proj",
+      "model.layers.41.self_attn.k_conv1d",
+      "model.layers.41.self_attn.k_proj",
+      "model.layers.41.self_attn.o_norm",
+      "model.layers.41.self_attn.o_proj",
+      "model.layers.41.self_attn.q_conv1d",
+      "model.layers.41.self_attn.q_proj",
+      "model.layers.41.self_attn.qkv_proj",
+      "model.layers.41.self_attn.v_conv1d",
+      "model.layers.41.self_attn.v_proj",
+      "model.layers.42.hc_attn_base",
+      "model.layers.42.hc_attn_fn",
+      "model.layers.42.hc_attn_scale",
+      "model.layers.42.hc_ffn_base",
+      "model.layers.42.hc_ffn_fn",
+      "model.layers.42.hc_ffn_scale",
+      "model.layers.42.input_layernorm",
+      "model.layers.42.mlp.gate",
+      "model.layers.42.mlp.gate.e_score_correction_bias",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.42.self_attn.A_log",
+      "model.layers.42.self_attn.b_proj",
+      "model.layers.42.self_attn.dt_bias",
+      "model.layers.42.self_attn.f_a_proj",
+      "model.layers.42.self_attn.f_b_proj",
+      "model.layers.42.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.42.self_attn.g_a_proj",
+      "model.layers.42.self_attn.g_b_proj",
+      "model.layers.42.self_attn.k_conv1d",
+      "model.layers.42.self_attn.k_proj",
+      "model.layers.42.self_attn.o_norm",
+      "model.layers.42.self_attn.o_proj",
+      "model.layers.42.self_attn.q_conv1d",
+      "model.layers.42.self_attn.q_proj",
+      "model.layers.42.self_attn.qkv_proj",
+      "model.layers.42.self_attn.v_conv1d",
+      "model.layers.42.self_attn.v_proj",
+      "model.layers.43.hc_attn_base",
+      "model.layers.43.hc_attn_fn",
+      "model.layers.43.hc_attn_scale",
+      "model.layers.43.hc_ffn_base",
+      "model.layers.43.hc_ffn_fn",
+      "model.layers.43.hc_ffn_scale",
+      "model.layers.43.input_layernorm",
+      "model.layers.43.mlp.gate",
+      "model.layers.43.mlp.gate.e_score_correction_bias",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.43.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.43.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.43.self_attn.indexer.k_norm",
+      "model.layers.43.self_attn.indexer.k_norm.bias",
+      "model.layers.43.self_attn.indexer.weights_proj",
+      "model.layers.43.self_attn.indexer.wk",
+      "model.layers.43.self_attn.indexer.wq_b",
+      "model.layers.43.self_attn.kv_a_layernorm",
+      "model.layers.43.self_attn.kv_b_proj",
+      "model.layers.43.self_attn.q_a_layernorm",
+      "model.layers.44.hc_attn_base",
+      "model.layers.44.hc_attn_fn",
+      "model.layers.44.hc_attn_scale",
+      "model.layers.44.hc_ffn_base",
+      "model.layers.44.hc_ffn_fn",
+      "model.layers.44.hc_ffn_scale",
+      "model.layers.44.input_layernorm",
+      "model.layers.44.mlp.gate",
+      "model.layers.44.mlp.gate.e_score_correction_bias",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.44.self_attn.A_log",
+      "model.layers.44.self_attn.b_proj",
+      "model.layers.44.self_attn.dt_bias",
+      "model.layers.44.self_attn.f_a_proj",
+      "model.layers.44.self_attn.f_b_proj",
+      "model.layers.44.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.44.self_attn.g_a_proj",
+      "model.layers.44.self_attn.g_b_proj",
+      "model.layers.44.self_attn.k_conv1d",
+      "model.layers.44.self_attn.k_proj",
+      "model.layers.44.self_attn.o_norm",
+      "model.layers.44.self_attn.o_proj",
+      "model.layers.44.self_attn.q_conv1d",
+      "model.layers.44.self_attn.q_proj",
+      "model.layers.44.self_attn.qkv_proj",
+      "model.layers.44.self_attn.v_conv1d",
+      "model.layers.44.self_attn.v_proj",
+      "model.layers.45.eh_proj",
+      "model.layers.45.enorm",
+      "model.layers.45.hnorm",
+      "model.layers.45.input_layernorm",
+      "model.layers.45.mlp.gate",
+      "model.layers.45.mlp.gate.e_score_correction_bias",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.45.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.45.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.45.self_attn.indexer.k_norm",
+      "model.layers.45.self_attn.indexer.k_norm.bias",
+      "model.layers.45.self_attn.indexer.weights_proj",
+      "model.layers.45.self_attn.indexer.wk",
+      "model.layers.45.self_attn.indexer.wq_b",
+      "model.layers.45.self_attn.kv_a_layernorm",
+      "model.layers.45.self_attn.kv_b_proj",
+      "model.layers.45.self_attn.q_a_layernorm",
+      "model.layers.45.shared_head.norm",
+      "model.layers.5.hc_attn_base",
+      "model.layers.5.hc_attn_fn",
+      "model.layers.5.hc_attn_scale",
+      "model.layers.5.hc_ffn_base",
+      "model.layers.5.hc_ffn_fn",
+      "model.layers.5.hc_ffn_scale",
+      "model.layers.5.input_layernorm",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.mlp.gate.e_score_correction_bias",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.5.self_attn.A_log",
+      "model.layers.5.self_attn.b_proj",
+      "model.layers.5.self_attn.dt_bias",
+      "model.layers.5.self_attn.f_a_proj",
+      "model.layers.5.self_attn.f_b_proj",
+      "model.layers.5.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.5.self_attn.g_a_proj",
+      "model.layers.5.self_attn.g_b_proj",
+      "model.layers.5.self_attn.k_conv1d",
+      "model.layers.5.self_attn.k_proj",
+      "model.layers.5.self_attn.o_norm",
+      "model.layers.5.self_attn.o_proj",
+      "model.layers.5.self_attn.q_conv1d",
+      "model.layers.5.self_attn.q_proj",
+      "model.layers.5.self_attn.qkv_proj",
+      "model.layers.5.self_attn.v_conv1d",
+      "model.layers.5.self_attn.v_proj",
+      "model.layers.6.hc_attn_base",
+      "model.layers.6.hc_attn_fn",
+      "model.layers.6.hc_attn_scale",
+      "model.layers.6.hc_ffn_base",
+      "model.layers.6.hc_ffn_fn",
+      "model.layers.6.hc_ffn_scale",
+      "model.layers.6.input_layernorm",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.gate.e_score_correction_bias",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.6.self_attn.A_log",
+      "model.layers.6.self_attn.b_proj",
+      "model.layers.6.self_attn.dt_bias",
+      "model.layers.6.self_attn.f_a_proj",
+      "model.layers.6.self_attn.f_b_proj",
+      "model.layers.6.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.6.self_attn.g_a_proj",
+      "model.layers.6.self_attn.g_b_proj",
+      "model.layers.6.self_attn.k_conv1d",
+      "model.layers.6.self_attn.k_proj",
+      "model.layers.6.self_attn.o_norm",
+      "model.layers.6.self_attn.o_proj",
+      "model.layers.6.self_attn.q_conv1d",
+      "model.layers.6.self_attn.q_proj",
+      "model.layers.6.self_attn.qkv_proj",
+      "model.layers.6.self_attn.v_conv1d",
+      "model.layers.6.self_attn.v_proj",
+      "model.layers.7.hc_attn_base",
+      "model.layers.7.hc_attn_fn",
+      "model.layers.7.hc_attn_scale",
+      "model.layers.7.hc_ffn_base",
+      "model.layers.7.hc_ffn_fn",
+      "model.layers.7.hc_ffn_scale",
+      "model.layers.7.input_layernorm",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.mlp.gate.e_score_correction_bias",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.7.self_attn.indexer.index_kpool_compress_ape",
+      "model.layers.7.self_attn.indexer.index_kpool_compress_gate",
+      "model.layers.7.self_attn.indexer.k_norm",
+      "model.layers.7.self_attn.indexer.k_norm.bias",
+      "model.layers.7.self_attn.indexer.weights_proj",
+      "model.layers.7.self_attn.indexer.wk",
+      "model.layers.7.self_attn.indexer.wq_b",
+      "model.layers.7.self_attn.kv_a_layernorm",
+      "model.layers.7.self_attn.kv_b_proj",
+      "model.layers.7.self_attn.q_a_layernorm",
+      "model.layers.8.hc_attn_base",
+      "model.layers.8.hc_attn_fn",
+      "model.layers.8.hc_attn_scale",
+      "model.layers.8.hc_ffn_base",
+      "model.layers.8.hc_ffn_fn",
+      "model.layers.8.hc_ffn_scale",
+      "model.layers.8.input_layernorm",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.mlp.gate.e_score_correction_bias",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.8.self_attn.A_log",
+      "model.layers.8.self_attn.b_proj",
+      "model.layers.8.self_attn.dt_bias",
+      "model.layers.8.self_attn.f_a_proj",
+      "model.layers.8.self_attn.f_b_proj",
+      "model.layers.8.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.8.self_attn.g_a_proj",
+      "model.layers.8.self_attn.g_b_proj",
+      "model.layers.8.self_attn.k_conv1d",
+      "model.layers.8.self_attn.k_proj",
+      "model.layers.8.self_attn.o_norm",
+      "model.layers.8.self_attn.o_proj",
+      "model.layers.8.self_attn.q_conv1d",
+      "model.layers.8.self_attn.q_proj",
+      "model.layers.8.self_attn.qkv_proj",
+      "model.layers.8.self_attn.v_conv1d",
+      "model.layers.8.self_attn.v_proj",
+      "model.layers.9.hc_attn_base",
+      "model.layers.9.hc_attn_fn",
+      "model.layers.9.hc_attn_scale",
+      "model.layers.9.hc_ffn_base",
+      "model.layers.9.hc_ffn_fn",
+      "model.layers.9.hc_ffn_scale",
+      "model.layers.9.input_layernorm",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.gate.e_score_correction_bias",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.9.self_attn.A_log",
+      "model.layers.9.self_attn.b_proj",
+      "model.layers.9.self_attn.dt_bias",
+      "model.layers.9.self_attn.f_a_proj",
+      "model.layers.9.self_attn.f_b_proj",
+      "model.layers.9.self_attn.fused_qkvbfg_a_proj",
+      "model.layers.9.self_attn.g_a_proj",
+      "model.layers.9.self_attn.g_b_proj",
+      "model.layers.9.self_attn.k_conv1d",
+      "model.layers.9.self_attn.k_proj",
+      "model.layers.9.self_attn.o_norm",
+      "model.layers.9.self_attn.o_proj",
+      "model.layers.9.self_attn.q_conv1d",
+      "model.layers.9.self_attn.q_proj",
+      "model.layers.9.self_attn.qkv_proj",
+      "model.layers.9.self_attn.v_conv1d",
+      "model.layers.9.self_attn.v_proj",
+      "model.norm",
+      "model.visual",
+      "router",
+      "visual",
+      "visual.blocks.0.attn.k_norm",
+      "visual.blocks.0.attn.proj",
+      "visual.blocks.0.attn.proj.bias",
+      "visual.blocks.0.attn.q_norm",
+      "visual.blocks.0.attn.qkv",
+      "visual.blocks.0.attn.qkv.bias",
+      "visual.blocks.0.mlp.down_proj",
+      "visual.blocks.0.mlp.down_proj.bias",
+      "visual.blocks.0.mlp.gate_proj",
+      "visual.blocks.0.mlp.gate_proj.bias",
+      "visual.blocks.0.mlp.up_proj",
+      "visual.blocks.0.mlp.up_proj.bias",
+      "visual.blocks.0.norm1",
+      "visual.blocks.0.norm2",
+      "visual.blocks.1.attn.k_norm",
+      "visual.blocks.1.attn.proj",
+      "visual.blocks.1.attn.proj.bias",
+      "visual.blocks.1.attn.q_norm",
+      "visual.blocks.1.attn.qkv",
+      "visual.blocks.1.attn.qkv.bias",
+      "visual.blocks.1.mlp.down_proj",
+      "visual.blocks.1.mlp.down_proj.bias",
+      "visual.blocks.1.mlp.gate_proj",
+      "visual.blocks.1.mlp.gate_proj.bias",
+      "visual.blocks.1.mlp.up_proj",
+      "visual.blocks.1.mlp.up_proj.bias",
+      "visual.blocks.1.norm1",
+      "visual.blocks.1.norm2",
+      "visual.blocks.10.attn.k_norm",
+      "visual.blocks.10.attn.proj",
+      "visual.blocks.10.attn.proj.bias",
+      "visual.blocks.10.attn.q_norm",
+      "visual.blocks.10.attn.qkv",
+      "visual.blocks.10.attn.qkv.bias",
+      "visual.blocks.10.mlp.down_proj",
+      "visual.blocks.10.mlp.down_proj.bias",
+      "visual.blocks.10.mlp.gate_proj",
+      "visual.blocks.10.mlp.gate_proj.bias",
+      "visual.blocks.10.mlp.up_proj",
+      "visual.blocks.10.mlp.up_proj.bias",
+      "visual.blocks.10.norm1",
+      "visual.blocks.10.norm2",
+      "visual.blocks.11.attn.k_norm",
+      "visual.blocks.11.attn.proj",
+      "visual.blocks.11.attn.proj.bias",
+      "visual.blocks.11.attn.q_norm",
+      "visual.blocks.11.attn.qkv",
+      "visual.blocks.11.attn.qkv.bias",
+      "visual.blocks.11.mlp.down_proj",
+      "visual.blocks.11.mlp.down_proj.bias",
+      "visual.blocks.11.mlp.gate_proj",
+      "visual.blocks.11.mlp.gate_proj.bias",
+      "visual.blocks.11.mlp.up_proj",
+      "visual.blocks.11.mlp.up_proj.bias",
+      "visual.blocks.11.norm1",
+      "visual.blocks.11.norm2",
+      "visual.blocks.12.attn.k_norm",
+      "visual.blocks.12.attn.proj",
+      "visual.blocks.12.attn.proj.bias",
+      "visual.blocks.12.attn.q_norm",
+      "visual.blocks.12.attn.qkv",
+      "visual.blocks.12.attn.qkv.bias",
+      "visual.blocks.12.mlp.down_proj",
+      "visual.blocks.12.mlp.down_proj.bias",
+      "visual.blocks.12.mlp.gate_proj",
+      "visual.blocks.12.mlp.gate_proj.bias",
+      "visual.blocks.12.mlp.up_proj",
+      "visual.blocks.12.mlp.up_proj.bias",
+      "visual.blocks.12.norm1",
+      "visual.blocks.12.norm2",
+      "visual.blocks.13.attn.k_norm",
+      "visual.blocks.13.attn.proj",
+      "visual.blocks.13.attn.proj.bias",
+      "visual.blocks.13.attn.q_norm",
+      "visual.blocks.13.attn.qkv",
+      "visual.blocks.13.attn.qkv.bias",
+      "visual.blocks.13.mlp.down_proj",
+      "visual.blocks.13.mlp.down_proj.bias",
+      "visual.blocks.13.mlp.gate_proj",
+      "visual.blocks.13.mlp.gate_proj.bias",
+      "visual.blocks.13.mlp.up_proj",
+      "visual.blocks.13.mlp.up_proj.bias",
+      "visual.blocks.13.norm1",
+      "visual.blocks.13.norm2",
+      "visual.blocks.14.attn.k_norm",
+      "visual.blocks.14.attn.proj",
+      "visual.blocks.14.attn.proj.bias",
+      "visual.blocks.14.attn.q_norm",
+      "visual.blocks.14.attn.qkv",
+      "visual.blocks.14.attn.qkv.bias",
+      "visual.blocks.14.mlp.down_proj",
+      "visual.blocks.14.mlp.down_proj.bias",
+      "visual.blocks.14.mlp.gate_proj",
+      "visual.blocks.14.mlp.gate_proj.bias",
+      "visual.blocks.14.mlp.up_proj",
+      "visual.blocks.14.mlp.up_proj.bias",
+      "visual.blocks.14.norm1",
+      "visual.blocks.14.norm2",
+      "visual.blocks.15.attn.k_norm",
+      "visual.blocks.15.attn.proj",
+      "visual.blocks.15.attn.proj.bias",
+      "visual.blocks.15.attn.q_norm",
+      "visual.blocks.15.attn.qkv",
+      "visual.blocks.15.attn.qkv.bias",
+      "visual.blocks.15.mlp.down_proj",
+      "visual.blocks.15.mlp.down_proj.bias",
+      "visual.blocks.15.mlp.gate_proj",
+      "visual.blocks.15.mlp.gate_proj.bias",
+      "visual.blocks.15.mlp.up_proj",
+      "visual.blocks.15.mlp.up_proj.bias",
+      "visual.blocks.15.norm1",
+      "visual.blocks.15.norm2",
+      "visual.blocks.16.attn.k_norm",
+      "visual.blocks.16.attn.proj",
+      "visual.blocks.16.attn.proj.bias",
+      "visual.blocks.16.attn.q_norm",
+      "visual.blocks.16.attn.qkv",
+      "visual.blocks.16.attn.qkv.bias",
+      "visual.blocks.16.mlp.down_proj",
+      "visual.blocks.16.mlp.down_proj.bias",
+      "visual.blocks.16.mlp.gate_proj",
+      "visual.blocks.16.mlp.gate_proj.bias",
+      "visual.blocks.16.mlp.up_proj",
+      "visual.blocks.16.mlp.up_proj.bias",
+      "visual.blocks.16.norm1",
+      "visual.blocks.16.norm2",
+      "visual.blocks.17.attn.k_norm",
+      "visual.blocks.17.attn.proj",
+      "visual.blocks.17.attn.proj.bias",
+      "visual.blocks.17.attn.q_norm",
+      "visual.blocks.17.attn.qkv",
+      "visual.blocks.17.attn.qkv.bias",
+      "visual.blocks.17.mlp.down_proj",
+      "visual.blocks.17.mlp.down_proj.bias",
+      "visual.blocks.17.mlp.gate_proj",
+      "visual.blocks.17.mlp.gate_proj.bias",
+      "visual.blocks.17.mlp.up_proj",
+      "visual.blocks.17.mlp.up_proj.bias",
+      "visual.blocks.17.norm1",
+      "visual.blocks.17.norm2",
+      "visual.blocks.18.attn.k_norm",
+      "visual.blocks.18.attn.proj",
+      "visual.blocks.18.attn.proj.bias",
+      "visual.blocks.18.attn.q_norm",
+      "visual.blocks.18.attn.qkv",
+      "visual.blocks.18.attn.qkv.bias",
+      "visual.blocks.18.mlp.down_proj",
+      "visual.blocks.18.mlp.down_proj.bias",
+      "visual.blocks.18.mlp.gate_proj",
+      "visual.blocks.18.mlp.gate_proj.bias",
+      "visual.blocks.18.mlp.up_proj",
+      "visual.blocks.18.mlp.up_proj.bias",
+      "visual.blocks.18.norm1",
+      "visual.blocks.18.norm2",
+      "visual.blocks.19.attn.k_norm",
+      "visual.blocks.19.attn.proj",
+      "visual.blocks.19.attn.proj.bias",
+      "visual.blocks.19.attn.q_norm",
+      "visual.blocks.19.attn.qkv",
+      "visual.blocks.19.attn.qkv.bias",
+      "visual.blocks.19.mlp.down_proj",
+      "visual.blocks.19.mlp.down_proj.bias",
+      "visual.blocks.19.mlp.gate_proj",
+      "visual.blocks.19.mlp.gate_proj.bias",
+      "visual.blocks.19.mlp.up_proj",
+      "visual.blocks.19.mlp.up_proj.bias",
+      "visual.blocks.19.norm1",
+      "visual.blocks.19.norm2",
+      "visual.blocks.2.attn.k_norm",
+      "visual.blocks.2.attn.proj",
+      "visual.blocks.2.attn.proj.bias",
+      "visual.blocks.2.attn.q_norm",
+      "visual.blocks.2.attn.qkv",
+      "visual.blocks.2.attn.qkv.bias",
+      "visual.blocks.2.mlp.down_proj",
+      "visual.blocks.2.mlp.down_proj.bias",
+      "visual.blocks.2.mlp.gate_proj",
+      "visual.blocks.2.mlp.gate_proj.bias",
+      "visual.blocks.2.mlp.up_proj",
+      "visual.blocks.2.mlp.up_proj.bias",
+      "visual.blocks.2.norm1",
+      "visual.blocks.2.norm2",
+      "visual.blocks.20.attn.k_norm",
+      "visual.blocks.20.attn.proj",
+      "visual.blocks.20.attn.proj.bias",
+      "visual.blocks.20.attn.q_norm",
+      "visual.blocks.20.attn.qkv",
+      "visual.blocks.20.attn.qkv.bias",
+      "visual.blocks.20.mlp.down_proj",
+      "visual.blocks.20.mlp.down_proj.bias",
+      "visual.blocks.20.mlp.gate_proj",
+      "visual.blocks.20.mlp.gate_proj.bias",
+      "visual.blocks.20.mlp.up_proj",
+      "visual.blocks.20.mlp.up_proj.bias",
+      "visual.blocks.20.norm1",
+      "visual.blocks.20.norm2",
+      "visual.blocks.21.attn.k_norm",
+      "visual.blocks.21.attn.proj",
+      "visual.blocks.21.attn.proj.bias",
+      "visual.blocks.21.attn.q_norm",
+      "visual.blocks.21.attn.qkv",
+      "visual.blocks.21.attn.qkv.bias",
+      "visual.blocks.21.mlp.down_proj",
+      "visual.blocks.21.mlp.down_proj.bias",
+      "visual.blocks.21.mlp.gate_proj",
+      "visual.blocks.21.mlp.gate_proj.bias",
+      "visual.blocks.21.mlp.up_proj",
+      "visual.blocks.21.mlp.up_proj.bias",
+      "visual.blocks.21.norm1",
+      "visual.blocks.21.norm2",
+      "visual.blocks.22.attn.k_norm",
+      "visual.blocks.22.attn.proj",
+      "visual.blocks.22.attn.proj.bias",
+      "visual.blocks.22.attn.q_norm",
+      "visual.blocks.22.attn.qkv",
+      "visual.blocks.22.attn.qkv.bias",
+      "visual.blocks.22.mlp.down_proj",
+      "visual.blocks.22.mlp.down_proj.bias",
+      "visual.blocks.22.mlp.gate_proj",
+      "visual.blocks.22.mlp.gate_proj.bias",
+      "visual.blocks.22.mlp.up_proj",
+      "visual.blocks.22.mlp.up_proj.bias",
+      "visual.blocks.22.norm1",
+      "visual.blocks.22.norm2",
+      "visual.blocks.23.attn.k_norm",
+      "visual.blocks.23.attn.proj",
+      "visual.blocks.23.attn.proj.bias",
+      "visual.blocks.23.attn.q_norm",
+      "visual.blocks.23.attn.qkv",
+      "visual.blocks.23.attn.qkv.bias",
+      "visual.blocks.23.mlp.down_proj",
+      "visual.blocks.23.mlp.down_proj.bias",
+      "visual.blocks.23.mlp.gate_proj",
+      "visual.blocks.23.mlp.gate_proj.bias",
+      "visual.blocks.23.mlp.up_proj",
+      "visual.blocks.23.mlp.up_proj.bias",
+      "visual.blocks.23.norm1",
+      "visual.blocks.23.norm2",
+      "visual.blocks.3.attn.k_norm",
+      "visual.blocks.3.attn.proj",
+      "visual.blocks.3.attn.proj.bias",
+      "visual.blocks.3.attn.q_norm",
+      "visual.blocks.3.attn.qkv",
+      "visual.blocks.3.attn.qkv.bias",
+      "visual.blocks.3.mlp.down_proj",
+      "visual.blocks.3.mlp.down_proj.bias",
+      "visual.blocks.3.mlp.gate_proj",
+      "visual.blocks.3.mlp.gate_proj.bias",
+      "visual.blocks.3.mlp.up_proj",
+      "visual.blocks.3.mlp.up_proj.bias",
+      "visual.blocks.3.norm1",
+      "visual.blocks.3.norm2",
+      "visual.blocks.4.attn.k_norm",
+      "visual.blocks.4.attn.proj",
+      "visual.blocks.4.attn.proj.bias",
+      "visual.blocks.4.attn.q_norm",
+      "visual.blocks.4.attn.qkv",
+      "visual.blocks.4.attn.qkv.bias",
+      "visual.blocks.4.mlp.down_proj",
+      "visual.blocks.4.mlp.down_proj.bias",
+      "visual.blocks.4.mlp.gate_proj",
+      "visual.blocks.4.mlp.gate_proj.bias",
+      "visual.blocks.4.mlp.up_proj",
+      "visual.blocks.4.mlp.up_proj.bias",
+      "visual.blocks.4.norm1",
+      "visual.blocks.4.norm2",
+      "visual.blocks.5.attn.k_norm",
+      "visual.blocks.5.attn.proj",
+      "visual.blocks.5.attn.proj.bias",
+      "visual.blocks.5.attn.q_norm",
+      "visual.blocks.5.attn.qkv",
+      "visual.blocks.5.attn.qkv.bias",
+      "visual.blocks.5.mlp.down_proj",
+      "visual.blocks.5.mlp.down_proj.bias",
+      "visual.blocks.5.mlp.gate_proj",
+      "visual.blocks.5.mlp.gate_proj.bias",
+      "visual.blocks.5.mlp.up_proj",
+      "visual.blocks.5.mlp.up_proj.bias",
+      "visual.blocks.5.norm1",
+      "visual.blocks.5.norm2",
+      "visual.blocks.6.attn.k_norm",
+      "visual.blocks.6.attn.proj",
+      "visual.blocks.6.attn.proj.bias",
+      "visual.blocks.6.attn.q_norm",
+      "visual.blocks.6.attn.qkv",
+      "visual.blocks.6.attn.qkv.bias",
+      "visual.blocks.6.mlp.down_proj",
+      "visual.blocks.6.mlp.down_proj.bias",
+      "visual.blocks.6.mlp.gate_proj",
+      "visual.blocks.6.mlp.gate_proj.bias",
+      "visual.blocks.6.mlp.up_proj",
+      "visual.blocks.6.mlp.up_proj.bias",
+      "visual.blocks.6.norm1",
+      "visual.blocks.6.norm2",
+      "visual.blocks.7.attn.k_norm",
+      "visual.blocks.7.attn.proj",
+      "visual.blocks.7.attn.proj.bias",
+      "visual.blocks.7.attn.q_norm",
+      "visual.blocks.7.attn.qkv",
+      "visual.blocks.7.attn.qkv.bias",
+      "visual.blocks.7.mlp.down_proj",
+      "visual.blocks.7.mlp.down_proj.bias",
+      "visual.blocks.7.mlp.gate_proj",
+      "visual.blocks.7.mlp.gate_proj.bias",
+      "visual.blocks.7.mlp.up_proj",
+      "visual.blocks.7.mlp.up_proj.bias",
+      "visual.blocks.7.norm1",
+      "visual.blocks.7.norm2",
+      "visual.blocks.8.attn.k_norm",
+      "visual.blocks.8.attn.proj",
+      "visual.blocks.8.attn.proj.bias",
+      "visual.blocks.8.attn.q_norm",
+      "visual.blocks.8.attn.qkv",
+      "visual.blocks.8.attn.qkv.bias",
+      "visual.blocks.8.mlp.down_proj",
+      "visual.blocks.8.mlp.down_proj.bias",
+      "visual.blocks.8.mlp.gate_proj",
+      "visual.blocks.8.mlp.gate_proj.bias",
+      "visual.blocks.8.mlp.up_proj",
+      "visual.blocks.8.mlp.up_proj.bias",
+      "visual.blocks.8.norm1",
+      "visual.blocks.8.norm2",
+      "visual.blocks.9.attn.k_norm",
+      "visual.blocks.9.attn.proj",
+      "visual.blocks.9.attn.proj.bias",
+      "visual.blocks.9.attn.q_norm",
+      "visual.blocks.9.attn.qkv",
+      "visual.blocks.9.attn.qkv.bias",
+      "visual.blocks.9.mlp.down_proj",
+      "visual.blocks.9.mlp.down_proj.bias",
+      "visual.blocks.9.mlp.gate_proj",
+      "visual.blocks.9.mlp.gate_proj.bias",
+      "visual.blocks.9.mlp.up_proj",
+      "visual.blocks.9.mlp.up_proj.bias",
+      "visual.blocks.9.norm1",
+      "visual.blocks.9.norm2",
+      "visual.downsample",
+      "visual.downsample.bias",
+      "visual.merger.down_proj",
+      "visual.merger.gate_proj",
+      "visual.merger.post_projection_norm",
+      "visual.merger.post_projection_norm.bias",
+      "visual.merger.proj",
+      "visual.merger.up_proj",
+      "visual.patch_embed.proj",
+      "visual.patch_embed.proj.bias",
+      "visual.post_layernorm",
+      "weights_proj"
+    ],
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  }
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.16.0"
+}

model-00001-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5202d28efdd01b47557c3f59111de3b4c4c375b2709c167b9b61834663c7da
+size 5365306688

model-00002-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05313aa3d972efc49076d3b7fc4ed3e827cd5648fce6fd83e8e6e4caed68a1b
+size 5320647024

model-00003-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9806d89bb028a51393414a5817d104ca811def3459fcff82dc37616adcdafe2
+size 5363448800

model-00004-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faaeaf32f8b9219a3a13437bf3b5436928d39d619a82c9c375c21f995c1607c0
+size 5364323736

model-00005-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2124352d6cb564db9144310fff9df6ca73c7d848514ce54d0ce627bc92d4b8f
+size 5363896872

model-00007-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b63fd168956e79228899d1a0663f045f13e6d6466c01ef93cc067aad7803da
+size 5364323968

model-00011-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:242bbff05b5a53bfdc7da92b7436880c77092857f11543269421fafdd444eca8
+size 5363896864

model-00012-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316f1bf351e031670148d5a6c76a9d713e857922af0927c50cf1eb9463c2c61a
+size 5364323728

model-00013-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133d516e76e8ee376ecc5feb660aec14d8f91312ec6fad9810ae67eb4dfc20a6
+size 5361790232

model-00014-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fa9359327c0b03fa705a5d17eb143d90e8ad47a043a73747fc398e9a80557c
+size 5364323944

model-00015-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e215b3bc726568ae58995b6ea67fe59755429fc41488cdc67f3ba8ed9741a72
+size 5364323752

model-00016-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb9d09b3c6543fa0f254eb5ebaba1ab0ddd8e619776143fa3c26a26f001d33b
+size 5361790008

model-00018-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b355cfa369273c2c72bd278824229f43ecafea4f2683407a38422fef0e6756
+size 5364323752

model-00019-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166136426415d44d261bc156e945fc076160d1b1243914f64b0d517c15ba93e4
+size 5364323720

model-00020-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d95a673adb5509457eecab92b0c5cff63bdd4885975db376447fbc310526de
+size 5361790360

model-00024-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc433f8c176bd0e4e57a02e29397f74b1d8c0605eb1f99484eb319f92cf5f81
+size 5364324088

model-00025-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820f5ad565d197e396ac349f2acb4a1a237a04dae356168878b67d7bbdd4b21b
+size 5364323752

model-00026-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f90814fcb944c548e2aed954f3aaab5c1aa3b3110cea6c2541970e8b291b63
+size 5364323720

model-00028-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac0ed26df64abb493892d91d5f58f5df9ef25bb43bfd3736d54d412a09f43ab
+size 5363896928

model-00029-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a2b78fc61d0d146344f07b72764ad6e684d1602b1c93f2fa828112db4615eb
+size 5364323752

model-00030-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0171e9086595b3dec439c81ec2ace9ae612a607e7d4a2ea3fc757627df86b191
+size 5361790128

model-00031-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93bf10b8136c75ef66418113eaa5612fb60fb727f6a64e2d222c156d23af0f77
+size 5364322992

model-00033-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6c9ce4effe8c885b61c77514add609a1b2cc49a0803622e91ef6b41f7f4af4
+size 5364323720

model-00034-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6701298729e1386ceff54906eec9d7a7c259026e9f60c394bc4554f43bfc343
+size 5361790384

model-00037-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ef88d62d2085d7544d2d5bb62a0474001bdc01fce1f55678715db58c554335
+size 5361790120

model-00039-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7adc8ecf50c72836709906c6a944cfa5c6be66656965433ff9277600e2f5deaa
+size 5364323744

model-00040-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755d5051e05378c1ada0c6e90989ea441374c8b34849cec0d4fc68d192d47a26
+size 5363896864

model-00041-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbed6b02ead85715db37921efbfda5675812292efe8b8bc7fdd8c270f011d31f
+size 5361790376

model-00042-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c24d133ab750560f26b45a8a4cfd6cdcbeb884be65eeb0c7d24ee7dd068650
+size 5364323808

model-00044-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d3cf83aee176a5950b190da575f7ad940378dcfdfa548f43e90cada0756015
+size 5361790144

model-00045-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263eb0812a6060d3df92b1f33e759db7c1fe8fafd860ac651fe49a630d9c6b77
+size 5364324040

model-00046-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd81dcf99e9d21d1e64f16d2f3e90a528e60b56cd5de718211b64ff0c9bdc0cf
+size 5363896320

model-00047-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c8f1ce85d34563d2ecc12f845849c93ac34baf06abd9776fdacca5adb30763
+size 5364322520

model-00048-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e54c0e6693956d3fbb5bddfc71959f5af6acabc2190f36b7be8ec10986f13fd
+size 5361790400

model-00050-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36795a572473cc635b06d1396c5bd3b1c1da3c64e107fdc4fd46388bc57eff0b
+size 5364323752

model-00052-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a98508ca1e4e6bbe6c9ee9aa001228aa4764c584508f718efb6cedde56c299e
+size 5364324016

model-00053-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d745b452dccf4c1ce9ae3a670f57f65a6af025a273c67283f699b1b2876adc
+size 5363896880

model-00055-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5e7d04670d04a4d194efa501351f54269f631146aea14b61e16533b58a026c
+size 5361789128

model-00056-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42603832501c72d636e99a8dd3483695a3e0c10d6d9a868cdb0c8cb7d512f2d0
+size 5364322528

model-00057-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2108aab902056d04bd4e86bf31b74f04b80c838fb1ac7c27d81a28a45d1c9365
+size 5364322496

model-00058-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e2eab248369f5ba770d9b1074bdc76702f2468afc3c41ad931519265cfb192
+size 5361788912

model-00061-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b040d1bf5e86c03d66ccadce514d7ac3c2e9058b8ba3514b9cba51ee4d1661dd
+size 5303975096

model-00062-of-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0342ac06063c2e949a165554f3d9cd5b7d39331654b8cd2a8810cb364463ee1c
+size 1261584904

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