Upload folder using huggingface_hub

.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

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Z.AI Co., Ltd
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,88 @@
+---
+license: mit
+base_model: zai-org/GLM-5.3-Flash
+base_model_relation: quantized
+tags:
+- mlx
+- apple-silicon
+- glm5_next
+- mixture-of-experts
+- 6-bit
+pipeline_tag: image-text-to-text
+library_name: mlx
+---
+
+# GLM-5.3-Flash-MLX-6bit
+
+MLX (Apple Silicon) build of [**GLM-5.3-Flash**](https://huggingface.co/zai-org/GLM-5.3-Flash) — 320B-A18B
+hybrid of 34 Kimi-Delta linear-attention layers and 11 DeepSeek-sparse-attention (NoPE MLA +
+lightning indexer) layers with manifold-constrained hyper-connections — quantized to **6-bit**.
+
+**These files are modified**: converted from the upstream bfloat16 release
+([GLM-5.3-Flash-BF16](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16)) to MLX and quantized;
+the architecture is unchanged. The multi-token-prediction layer (layer 45) is not included. The
+vision tower is carried in bfloat16.
+
+## Runtime
+
+`glm5_next` landed in [mlx-vlm](https://github.com/Blaizzy/mlx-vlm) `main` on 2026-08-26 (no
+release carries it yet). Validating that port against `transformers` 5.16 at tiny scale found two
+numerical bugs and two epsilon mismatches, which the runtime in
+[https://github.com/PipeNetwork/glm53-flash-mlx](https://github.com/PipeNetwork/glm53-flash-mlx) fixes; parity is **1e-6** end to end, exact on cached decode.
+
+| what | reference | mlx-vlm `main` | effect |
+|---|---|---|---|
+| `swiglu_limit` | gate clamped at 10, up at ±10, in every text MLP | no clamp anywhere in the text stack | formula mismatch on all 45 FFN blocks |
+| mHC `base`/`scale` dtype | float32 | converter casts to bf16; the Metal kernel then reads `base` as float4 | `comb` mixing matrix off by ~0.5 on every layer of a converted checkpoint |
+| MLA low-rank norm eps | `rms_norm_eps` = 1e-5 | 1e-6 | small |
+| indexer LayerNorm eps | 1e-6 | 1e-5 | small |
+
+This checkpoint keeps the mHC arrays and KDA decay parameters in float32 as stored, so it is
+safe in either runtime; the clamp is a compute-path fix and needs the patched runtime:
+
+```bash
+git clone https://github.com/PipeNetwork/glm53-flash-mlx && cd glm53-flash-mlx && pip install -r requirements.txt
+python scripts/smoke_generate.py /path/to/GLM-5.3-Flash-MLX-6bit
+```
+```python
+from glm53_flash_mlx.load import load
+model, processor = load("/path/to/GLM-5.3-Flash-MLX-6bit")
+```
+
+## Size and what is quantized
+
+**255.9 GB** on disk (bfloat16 upstream: 642.7 GB).
+
+| group | share of parameters | this build |
+|---|---:|---|
+| routed experts (`switch_mlp`, 42 layers × 288) | 304B (97%) | 6-bit, group 64 |
+| KDA and MLA projections, shared experts, dense MLPs, embeddings, `lm_head` | ~9B | 6-bit, group 64 |
+| lightning-indexer projections | 0.06B | 8-bit, group 64 |
+| MoE router + correction bias, mHC arrays (fp32), KDA `A_log`/`dt_bias` (fp32), convolutions, norms | — | as stored |
+| vision tower | 0.56B | bfloat16 |
+
+## Quality
+
+Perplexity on wikitext-2 (test), 288,627 tokens in 141 windows of 2048, every build scored
+on **identical** windows through this runtime. The 643 GB bfloat16 model does not fit a 512 GB
+machine, so the 8-bit build is the anchor (on every model we have measured, 8-bit has been
+statistically indistinguishable from bfloat16). Per-window NLL differences against 8-bit,
+bootstrapped over one shared index set (20,000 resamples):
+
+| build | size | perplexity | ΔNLL/token vs 8-bit [95% CI] | windows worse |
+|---|---:|---:|---|---:|
+| [8bit](https://huggingface.co/pipenetwork/GLM-5.3-Flash-MLX-8bit) | 334.1 GB | 3.4607 | — | — |
+| [6bit](https://huggingface.co/pipenetwork/GLM-5.3-Flash-MLX-6bit) | 255.9 GB | 3.4646 | +0.0011 [−0.0017, +0.0038] | 89/141 |
+| [mixed-4_8bit](https://huggingface.co/pipenetwork/GLM-5.3-Flash-MLX-mixed-4_8bit) | 181.9 GB | 3.5705 | +0.0312 [+0.0271, +0.0355] | 131/141 |
+| [4bit](https://huggingface.co/pipenetwork/GLM-5.3-Flash-MLX-4bit) | 177.6 GB | 3.7549 | +0.0816 [+0.0755, +0.0879] | 140/141 |
+
+Read the interval, not the point estimate; "windows worse" counts how many of the 141
+windows the build lost outright.
+
+Against the 8-bit anchor: 6-bit +0.1%, mixed 4/8-bit +3.2%, uniform 4-bit +8.5%. Routed experts are 97% of the parameters; the mixed build keeps the other ~9B (KDA and MLA projections, shared experts, dense layers, embeddings) at 8-bit for 4.4 GB more than uniform 4-bit.
+
+Greedy generation (a collapse detector, not a ranking) is coherent on every published build.
+
+## License
+
+MIT, as the upstream model. Port code: [https://github.com/PipeNetwork/glm53-flash-mlx](https://github.com/PipeNetwork/glm53-flash-mlx).

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 +1,562 @@
+{
+  "architectures": [
+    "Glm5NextForConditionalGeneration"
+  ],
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "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_attn_config": {
+      "num_heads": 64,
+      "gate_lower_bound": -5.0,
+      "head_dim": 128,
+      "short_conv_kernel_size": 4,
+      "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
+      ],
+      "full_attn_layers": [
+        3,
+        7,
+        11,
+        15,
+        19,
+        23,
+        27,
+        31,
+        35,
+        39,
+        43
+      ]
+    },
+    "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
+  },
+  "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": {
+    "group_size": 64,
+    "bits": 6,
+    "language_model.model.layers.3.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.43.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.43.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.43.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    }
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 6,
+    "language_model.model.layers.3.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.43.self_attn.indexer.wq_b": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.43.self_attn.indexer.wk": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.43.self_attn.indexer.weights_proj": {
+      "group_size": 64,
+      "bits": 8
+    }
+  }
+}

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.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a19e6a16ed73f14093d474dc1c1a187a88ada7908c511957eca77eef316dc5
+size 11819070608

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a00546741b4f6f4dda7351e100a9bf733f606f228ade523b93866993d11de4
+size 10087582241

model-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab51bc8a3afcbafa8c0f5a6a666490d67ccc244a082b33455d631c73cb4dd48
+size 10024860812

model-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4987a0f318260785914f547303213330891fa7c1ef89a55ff77c2c92c00e25
+size 10005654659

model-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfe4451be411a0a51a5f0593fa1f156f19c70e05b878232725ce218215510aa
+size 10065952118

model-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5894f2a8d8c8805d876ff69a29e5bfbc80af106cf80c39617d339a223fedc097
+size 10019227426

model-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27dfa7bd930c7cbaa8786c3e3141b46cb4f17fa54e33f95689f5c98d5e4d3320
+size 10032918493

model-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7904b0edfbe0f5ca966aaca36bcad746a777c3d5bbe74ddb84d3d2a543a575
+size 10079387761

model-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0baa087997df85986be6d8ca1687faafc9978f7e32ab9a6b185b006a50fc2303
+size 10005791897

model-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7d67dcd17ba76a092a61d2b54fb0bb7e6606e5aa7e3e0d19c370a6b0db672f
+size 10011288211

model-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e748ab5f16245422eb3b3e38dc339557945130cd3c9e45556b72d455a646cee
+size 10101018021

model-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96603eeae65e31d570e464192da21fb82ed04154cf26b2baef189a7c4e2f7a1e
+size 10040389058

model-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5458268e421887a1345950ec144ff02b7a681e3ef368f5f4968b74c2482a830a
+size 11953061312

model-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df9715d279ca138f0b327ee1d65bb1447475edef49456359331d189c3dff8fa
+size 10087582584

model-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1765923d1882830107dbb795366a26051a0797ab7b73a29e514222145a1b3b9
+size 10079387761

model-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610dcb87f006b49bfdbcc62fb256614479128eccfa966bf9ecf2795fb72b2717
+size 10005791865

model-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd059c20d8a6b863ac851ed559a9c5eab16a2533b4eaab82f2d61f46cd843511
+size 10011288237

model-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516b3cc3ea3eb378bd6a698bdeb9afb154fb2f969fb444c7f77dc3679541f6cf
+size 10101017881

model-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7452822fe57a5133ec1da911ad7d079c0a40a1a0560411ffd29dbf46094adfe0
+size 10040389036

model-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c58b7c4e323f3acb01898e9d7e850eda9f06b31515966dee39e25fdda3b7d8
+size 11953061312

model-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c701c2e1bb6d90872fc047153c3c40f8c849b9ed7fe15d7bbdb2c163e550ca2
+size 10087582488

model-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05aa87aa2787ae147f2d75223b19ed7fda4e7f650c4d24cd599ffe93d731449
+size 10079387759

model-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0747db13598d1ad2973b23b734e0f8645b99c928a10d04df35e34c800d212dcf
+size 10005791909

model-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89587680f0a1c146f9bf3160a86e8526c4babc69c31a2a3fb202111c5a111724
+size 10011288177

model-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b31446a3de53cbe19ad1a7cd0f41fb7802f35e2379fe88edcb31883b73bea9bf
+size 9129118887

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"
+}