Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ 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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Zhipu AI
+
+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 +1,51 @@
+---
+license: mit
+base_model: zai-org/GLM-5.2
+pipeline_tag: text-generation
+tags:
+  - moe
+  - reap
+  - pruning
+  - router-kd
+  - knowledge
+  - nvfp4
+  - glm
+  - glm-5.2
+---
+
+# GLM-5.2-504B-K — knowledge-augmented REAP keep-168 (full-data Router-KD, NVFP4)
+
+The **"K-cut"** sibling of [`0xSero/GLM-5.2-504B`](https://huggingface.co/0xSero/GLM-5.2-504B): the
+same ~504B / keep-168 budget, but the expert selection is **biased toward knowledge & reasoning** —
+the winning top-160 core (kept bit-for-bit) **plus the 8 highest-priority knowledge-exclusive experts
+per layer** that coding-saliency pruning drops. Recovered with gate-only **Router-KD trained on the
+FULL calibration set (~18.6k real traces)** — 6x the data of the first-pass cuts.
+
+## Sponsor
+8x NVIDIA B200 sponsored by [Lambda](https://lambda.ai). Thank you.
+
+## Why this variant exists
+REAP saliency computed from coding traces under-weights experts that fire mainly on
+reasoning/knowledge. The K-cut deliberately re-includes them — trading a sliver of coding-saliency
+coverage for broader knowledge coverage. Reach for this on knowledge/reasoning-heavy workloads; use
+the plain [`GLM-5.2-504B`](https://huggingface.co/0xSero/GLM-5.2-504B) otherwise.
+
+## Eval (n=2000 held-out real prompts, raw, no max_tokens / no timeout)
+| metric | GLM-5.2-504B-K (this) | GLM-5.2-504B (plain floor) |
+|---|---|---|
+| attractor / loop rate | **0.078** | 0.072 |
+| natural-EOS rate | 0.923 | 0.928 |
+| distinct-4 | 0.881 | 0.880 |
+| median tokens | 1232 | 1267 |
+
+On the loop metric this is **at parity with (or better than) the plain-cut floor**. The residual loops are inherent to GLM-5.2 itself (the unpruned teacher
+loops on the same prompts), so neither cut "fixes" them — this one buys knowledge-expert coverage.
+
+## Serving (vLLM)
+```bash
+vllm serve 0xSero/GLM-5.2-504B-K --tensor-parallel-size 8 \
+  --quantization modelopt_fp4 --kv-cache-dtype fp8 --trust-remote-code --max-model-len 262144
+```
+
+---
+*REAP knowledge-augmented cut + full-data Router-KD. Compute sponsored by [Lambda](https://lambda.ai).*

chat_template.jinja

@@ -0,0 +1,119 @@
+[gMASK]<sop>
+{%- set effective_reasoning_effort = 'high' if reasoning_effort is defined and reasoning_effort == 'high' else 'max' -%}
+{%- if (enable_thinking is not defined or enable_thinking) and effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
+{%- 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 -%}
+<|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 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', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}
+                {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}
+                {{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- 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 ((clear_thinking is defined and 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|>' -}}
+{%- endif %}
+{%- if m.content is string -%}
+    {{- '<tool_response>' + m.content + '</tool_response>' -}}
+{%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0.type == "tool_reference" -%}
+    {{- '<tool_response><tools>\n' -}}
+    {% for tr in m.content %}
+        {%- 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>' -}}
+{%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0 is mapping and m.content.0.output is defined -%}
+    {%- for tr in m.content -%}
+        {{- '<tool_response>' + tr.output + '</tool_response>' -}}
+    {%- endfor -%}
+{%- else -%}
+    {{- '<tool_response>' + visible_text(m.content) + '</tool_response>' -}}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '<think></think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,418 @@
+{
+  "architectures": [
+    "GlmMoeDsaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "head_dim": 192,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "index_head_dim": 128,
+  "index_n_heads": 32,
+  "index_share_for_mtp_iteration": true,
+  "index_skip_topk_offset": 3,
+  "index_topk": 2048,
+  "index_topk_freq": 4,
+  "index_topk_pattern": null,
+  "indexer_rope_interleave": true,
+  "indexer_types": [
+    "full",
+    "full",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared"
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 1048576,
+  "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",
+    "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": "glm_moe_dsa",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 168,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 78,
+  "num_key_value_heads": 64,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 154820,
+  "pretraining_tp": 1,
+  "q_lora_rank": 2048,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "rope_theta": 8000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.12.0",
+  "use_cache": true,
+  "v_head_dim": 256,
+  "vocab_size": 154880,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "dynamic": false,
+          "num_bits": 4,
+          "type": "float",
+          "group_size": 16
+        },
+        "weights": {
+          "dynamic": false,
+          "num_bits": 4,
+          "type": "float",
+          "group_size": 16
+        },
+        "targets": [
+          "Linear"
+        ]
+      }
+    },
+    "ignore": [
+      "lm_head",
+      "model.layers.0.mlp*",
+      "model.layers.0.self_attn*",
+      "model.layers.0.self_attn.indexer*",
+      "model.layers.1.mlp*",
+      "model.layers.1.self_attn*",
+      "model.layers.1.self_attn.indexer*",
+      "*shared_experts*",
+      "model.layers.10.self_attn*",
+      "model.layers.10.self_attn.indexer*",
+      "model.layers.11.self_attn*",
+      "model.layers.11.self_attn.indexer*",
+      "model.layers.12.self_attn*",
+      "model.layers.12.self_attn.indexer*",
+      "model.layers.13.self_attn*",
+      "model.layers.13.self_attn.indexer*",
+      "model.layers.14.self_attn*",
+      "model.layers.14.self_attn.indexer*",
+      "model.layers.15.self_attn*",
+      "model.layers.15.self_attn.indexer*",
+      "model.layers.16.self_attn*",
+      "model.layers.16.self_attn.indexer*",
+      "model.layers.17.self_attn*",
+      "model.layers.17.self_attn.indexer*",
+      "model.layers.18.self_attn*",
+      "model.layers.18.self_attn.indexer*",
+      "model.layers.19.self_attn*",
+      "model.layers.19.self_attn.indexer*",
+      "model.layers.2.mlp*",
+      "model.layers.2.self_attn*",
+      "model.layers.2.self_attn.indexer*",
+      "model.layers.20.self_attn*",
+      "model.layers.20.self_attn.indexer*",
+      "model.layers.21.self_attn*",
+      "model.layers.21.self_attn.indexer*",
+      "model.layers.22.self_attn*",
+      "model.layers.22.self_attn.indexer*",
+      "model.layers.23.self_attn*",
+      "model.layers.23.self_attn.indexer*",
+      "model.layers.24.self_attn*",
+      "model.layers.24.self_attn.indexer*",
+      "model.layers.25.self_attn*",
+      "model.layers.25.self_attn.indexer*",
+      "model.layers.26.self_attn*",
+      "model.layers.26.self_attn.indexer*",
+      "model.layers.27.self_attn*",
+      "model.layers.27.self_attn.indexer*",
+      "model.layers.28.self_attn*",
+      "model.layers.28.self_attn.indexer*",
+      "model.layers.29.self_attn*",
+      "model.layers.29.self_attn.indexer*",
+      "model.layers.3.self_attn*",
+      "model.layers.3.self_attn.indexer*",
+      "model.layers.30.self_attn*",
+      "model.layers.30.self_attn.indexer*",
+      "model.layers.31.self_attn*",
+      "model.layers.31.self_attn.indexer*",
+      "model.layers.32.self_attn*",
+      "model.layers.32.self_attn.indexer*",
+      "model.layers.33.self_attn*",
+      "model.layers.33.self_attn.indexer*",
+      "model.layers.34.self_attn*",
+      "model.layers.34.self_attn.indexer*",
+      "model.layers.35.self_attn*",
+      "model.layers.35.self_attn.indexer*",
+      "model.layers.36.self_attn*",
+      "model.layers.36.self_attn.indexer*",
+      "model.layers.37.self_attn*",
+      "model.layers.37.self_attn.indexer*",
+      "model.layers.38.self_attn*",
+      "model.layers.38.self_attn.indexer*",
+      "model.layers.39.self_attn*",
+      "model.layers.39.self_attn.indexer*",
+      "model.layers.4.self_attn*",
+      "model.layers.4.self_attn.indexer*",
+      "model.layers.40.self_attn*",
+      "model.layers.40.self_attn.indexer*",
+      "model.layers.41.self_attn*",
+      "model.layers.41.self_attn.indexer*",
+      "model.layers.42.self_attn*",
+      "model.layers.42.self_attn.indexer*",
+      "model.layers.43.self_attn*",
+      "model.layers.43.self_attn.indexer*",
+      "model.layers.44.self_attn*",
+      "model.layers.44.self_attn.indexer*",
+      "model.layers.45.self_attn*",
+      "model.layers.45.self_attn.indexer*",
+      "model.layers.46.self_attn*",
+      "model.layers.46.self_attn.indexer*",
+      "model.layers.47.self_attn*",
+      "model.layers.47.self_attn.indexer*",
+      "model.layers.48.self_attn*",
+      "model.layers.48.self_attn.indexer*",
+      "model.layers.49.self_attn*",
+      "model.layers.49.self_attn.indexer*",
+      "model.layers.5.self_attn*",
+      "model.layers.5.self_attn.indexer*",
+      "model.layers.50.self_attn*",
+      "model.layers.50.self_attn.indexer*",
+      "model.layers.51.self_attn*",
+      "model.layers.51.self_attn.indexer*",
+      "model.layers.52.self_attn*",
+      "model.layers.52.self_attn.indexer*",
+      "model.layers.53.self_attn*",
+      "model.layers.53.self_attn.indexer*",
+      "model.layers.54.self_attn*",
+      "model.layers.54.self_attn.indexer*",
+      "model.layers.55.self_attn*",
+      "model.layers.55.self_attn.indexer*",
+      "model.layers.56.self_attn*",
+      "model.layers.56.self_attn.indexer*",
+      "model.layers.57.self_attn*",
+      "model.layers.57.self_attn.indexer*",
+      "model.layers.58.self_attn*",
+      "model.layers.58.self_attn.indexer*",
+      "model.layers.59.self_attn*",
+      "model.layers.59.self_attn.indexer*",
+      "model.layers.6.self_attn*",
+      "model.layers.6.self_attn.indexer*",
+      "model.layers.60.self_attn*",
+      "model.layers.60.self_attn.indexer*",
+      "model.layers.61.self_attn*",
+      "model.layers.61.self_attn.indexer*",
+      "model.layers.62.self_attn*",
+      "model.layers.62.self_attn.indexer*",
+      "model.layers.63.self_attn*",
+      "model.layers.63.self_attn.indexer*",
+      "model.layers.64.self_attn*",
+      "model.layers.64.self_attn.indexer*",
+      "model.layers.65.self_attn*",
+      "model.layers.65.self_attn.indexer*",
+      "model.layers.66.self_attn*",
+      "model.layers.66.self_attn.indexer*",
+      "model.layers.67.self_attn*",
+      "model.layers.67.self_attn.indexer*",
+      "model.layers.68.self_attn*",
+      "model.layers.68.self_attn.indexer*",
+      "model.layers.69.self_attn*",
+      "model.layers.69.self_attn.indexer*",
+      "model.layers.7.self_attn*",
+      "model.layers.7.self_attn.indexer*",
+      "model.layers.70.self_attn*",
+      "model.layers.70.self_attn.indexer*",
+      "model.layers.71.self_attn*",
+      "model.layers.71.self_attn.indexer*",
+      "model.layers.72.self_attn*",
+      "model.layers.72.self_attn.indexer*",
+      "model.layers.73.self_attn*",
+      "model.layers.73.self_attn.indexer*",
+      "model.layers.74.self_attn*",
+      "model.layers.74.self_attn.indexer*",
+      "model.layers.75.self_attn*",
+      "model.layers.75.self_attn.indexer*",
+      "model.layers.76.self_attn*",
+      "model.layers.76.self_attn.indexer*",
+      "model.layers.77.self_attn*",
+      "model.layers.77.self_attn.indexer*",
+      "model.layers.8.self_attn*",
+      "model.layers.8.self_attn.indexer*",
+      "model.layers.9.self_attn*",
+      "model.layers.9.self_attn.indexer*",
+      "model.layers.78.eh_proj*",
+      "model.layers.78.self_attn*",
+      "model.layers.78.self_attn.indexer*",
+      "model.layers.78.mlp.gate*",
+      "model.layers.78.mlp.shared_experts*"
+    ],
+    "quant_algo": "NVFP4",
+    "producer": {
+      "name": "modelopt",
+      "version": "0.39.0.dev290+gf9d9a71de.d20260214"
+    },
+    "quant_method": "modelopt"
+  }
+}

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": "5.12.0"
+}

model-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32eb17744ce168464db1e52af4fb3466a0b2f0d25e930f64bf097ed064e5562
+size 5000912520

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926df1b551c1d19fe56730b5d705298cf859e18ce718fdf41e04ffdd3ebba3ec
+size 5000636364

model-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1367004c73763aaf5309bd7e24e387e59f254a593857c07973875a03f625452
+size 5166417984

model-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4a23a2ef1259e4b8f72cdaf98308d56d88f4b0c041ea795678ec2fda02b246
+size 5000910116

model-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3236d6d8f76afef822f4d5c7e04add890a92503f5a87b4c682e980d4f865d6d0
+size 5000241880

model-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84aeb90f97ed617c77f2cf1d24ecddef737717db14b043988cbc341f4ac40e17
+size 5006010796

model-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1c499a02258f7a02cdb9c74957dd5c147b408a2a56990a6dc2cc6e793bf149
+size 5001422756

model-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaad58ef5b6d8201a3226c483a0ffc517a8abc6ec18fe098719126fc57de777c
+size 5005596112

model-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522f8001146b46ff930a805ba9c29be328cbb229efc0ab945be3b260fdf4dce8
+size 5006010788

model-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519be3732637e34abde9b962b80c14debee206eb90918734b9057ab02beedc20
+size 5001422748

model-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350ed3d8ee410f0cd9822950b8e3080565eb5cbd8131449b588fc356d44f37a4
+size 5002972344

model-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f51dc0ad2322b37b1b11c726219b444841a3d7464a5bf63da31e3ec99cb0e9
+size 5001555720

model-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d4d4cfadd955335d7079060a795defd2e367831849f50ef1435897ac748866
+size 5001422892

model-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eee33e55fc294ed188c11c53d06e4a15f3811112c53c3932df1d2b666c7a6cb
+size 5000909684

model-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2379e2df9b56ca8f296204b78c653291b92867a453aa8a88e659a66a51756d2f
+size 5001422804

model-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a9ea869d167e5f9343140203d50a042d25c4704e037ca41c5297e340c0a8f9
+size 5003105772

model-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826e8eb1951b0fd4790218484fb22dd676eb8a880a3e6c53f659064c0ed26ea1
+size 5001422948

model-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95bc65aa72d7c3cdaa61d2e1453030cedcbf4a288434db02176841c16a79b76c
+size 5001422788

model-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910f4c775e05c9d12104670b5d95b8b004212c10992ffebaa572d84b1a902e2c
+size 5003105764

model-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e3a5af36aafe686ef4395e282f9a346e71ae86d77ec702907674a546126f31
+size 5001422684

model-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d076e85b7bd7f30318fd54dffa0e9611c50a45df7c048d98f7c17c6239d2814
+size 5001422052

model-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d598c9c665a1bb56fe7aa7777a78be550ec88123783c3771f138b2c0f975c7
+size 5001422148

model-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0499790d617a3f20ca82fdea339e63bf380d68c9c6e8313594d250b6c8066f9
+size 5003105788

model-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83490bc9bd65e903e97cd6d08bc85e5c6349ce68e65bb60eb31f6bc7cedf8c0
+size 5001422740

model-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a51b916cc7308e9a8f3f5d84369e5a0555c994953dee587f137f2a17de5ccd
+size 5001422964

model-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e5665442cb7786318bc751a80b0f8207abeb0acec84a6c983511481b87dc04
+size 5006010644

model-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c74d7e0a6fb088f94c94a403402de2a953b41c230953966f7747eefb59326a4
+size 5006010764

model-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3bd55fd96ba81cd04212f471de12931167f51368b0131b7521c55d5ef8e54f3
+size 5001421292

model-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0833692890268a635153700d3ce669aa847c09f4ac09a26971cf5d322f9cec3b
+size 5003105716

model-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f5a3286732329777d8e6851545a64d1caf9d12bb918c87d61b638617862f5b
+size 5006010812

model-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d4270ec45e070d7fd7151c4e78d746d2e772727749f8f8b966ca8d9f58360e
+size 5001422764

model-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6164122cb7e3e90faf09e0457b2aa92717d195c1fe295cc1ef97e3aa25aa576
+size 5006010708

model-00050.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406f00ee2be46b9a50ba023e9cf35d66ce50890081f276719d0a477f825473d5
+size 5001422948

model-00052.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59986622f67249c501100c5df41f36c047b042d93ba7342cd8483f1ca30146c
+size 5005091788

model-00054.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d491b893b39b7e133228e8fb7f6efc7d401f3d92c008545c1bf2721fca79daa3
+size 5001422940

model-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d910b6456af7f9b1520f1d05b3af90cd7715db3f666d8ae634453f5392a78e
+size 5112282228

model-00056.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1137a7c2f03d8692df34c197a8fdeb1a674b8d3ba999261b432c6410d897367c
+size 5005498036

model-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5b10eccbb5de97322f8895636d0c6892d5c0ec8fa07089c612423d437bbaed
+size 5001422988

model-00058.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4d1b6ae4c738eb485ce2c6e3e8a8c9e764361a93d443e870bc1117e657efa1
+size 5001422780

model-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d4321b5dd0ab4124e08b71813467cfa085ecd2d1bd1e9ab73045d190feab58
+size 5004367132

model-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1335ab687f82bc394a095c591449547daee1fddd6447dac0215b36e7ed74a03b
+size 5008224104

model-00063.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07c8d923bbba0bb61e2afb8bf23a0ad0917a01dd574e9347c98c4d8425572d8
+size 2515249728

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe40b894556e2aa4b0580ddd0d9fc1fd638f64aa04ecc43989c9030b056e8a3
+size 12706968

tokenizer.json

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