Add files using upload-large-folder tool

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1782082103

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.

chat_template.jinja

@@ -0,0 +1,120 @@
+[gMASK]<sop>
+{# {%- set effective_reasoning_effort = 'high' if reasoning_effort is defined and reasoning_effort == 'high' else 'max' -%} #}
+{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort is not none else 'medium-high' -%}
+{%- 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 -%}

chat_template_original.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 +1,288 @@
+{
+  "name_or_path": "tclf90/GLM-5.2-Int4-Int8Mix",
+  "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": 256,
+  "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": {
+    "quant_method": "compressed-tensors",
+    "format": "pack-quantized",
+    "ignore": [
+      "re:model[.]layers[.]0[.].*",
+      "re:model[.]layers[.][1-9][0-9]*[.](?:mtp_block[.])?mlp[.]gate(?:$|[.].*)",
+      "re:model[.]layers[.][1-9][0-9]*[.](?:mtp_block[.])?self_attn[.]indexer(?:$|[.].*)",
+      "re:model[.]layers[.][1-9][0-9]*[.](?:mtp_block[.])?self_attn[.]indexers_proj(?:$|[.].*)",
+      "re:model[.]layers[.][1-9][0-9]*[.](?:eh_proj|enorm|hnorm)[.].*",
+      "re:model[.]layers[.][1-9][0-9]*[.]shared_head[.]norm[.].*",
+      "re:model[.]layers[.][1-9][0-9]*[.]shared_head[.]head(?:$|[.].*)"
+    ],
+    "config_groups": {
+      "w4a16_experts": {
+        "targets": [
+          "re:model[.]layers[.](?:3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31|32|33|34|35|36|37|38|39|40|41|42|43|44|45|46|47|48|49|50|51|52|53|54|55|56|57|58|59|60|61|62|63|64|65|66|67|68|69|70|71|72|73|74|75|76|77)[.]mlp[.]experts[.][0-9]+[.](?:gate_proj|up_proj|down_proj)$"
+        ],
+        "weights": {
+          "num_bits": 4,
+          "type": "int",
+          "symmetric": true,
+          "strategy": "group",
+          "group_size": 128,
+          "dynamic": false
+        }
+      },
+      "w8a16_linears": {
+        "targets": [
+          "re:model[.]layers[.](?:1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31|32|33|34|35|36|37|38|39|40|41|42|43|44|45|46|47|48|49|50|51|52|53|54|55|56|57|58|59|60|61|62|63|64|65|66|67|68|69|70|71|72|73|74|75|76|77)[.](?:self_attn[.](?:fused_qkv_a_proj_with_mqa|q_a_proj|q_b_proj|kv_a_proj_with_mqa|kv_b_proj|o_proj)|mlp[.](?:gate_up_proj|gate_proj|up_proj|down_proj|shared_experts[.](?:gate_up_proj|gate_proj|up_proj|down_proj)))$"
+        ],
+        "weights": {
+          "num_bits": 8,
+          "type": "int",
+          "symmetric": true,
+          "strategy": "group",
+          "group_size": 128,
+          "dynamic": false
+        }
+      },
+      "w8a16_mtp_channel": {
+        "targets": [
+          "re:model[.]layers[.](?:78)[.](?:mtp_block[.])?(?:self_attn[.](?:fused_qkv_a_proj_with_mqa|q_a_proj|q_b_proj|kv_a_proj_with_mqa|kv_b_proj|o_proj)|mlp[.](?:experts[.][0-9]+[.](?:gate_proj|up_proj|down_proj)|gate_up_proj|gate_proj|up_proj|down_proj|shared_experts[.](?:gate_up_proj|gate_proj|up_proj|down_proj)))$"
+        ],
+        "weights": {
+          "num_bits": 8,
+          "type": "int",
+          "symmetric": true,
+          "strategy": "channel",
+          "group_size": -1,
+          "dynamic": false
+        }
+      }
+    },
+    "packed_modules_mapping": {
+      "fused_qkv_a_proj_with_mqa": [
+        "q_a_proj",
+        "kv_a_proj_with_mqa"
+      ],
+      "gate_up_proj": [
+        "gate_proj",
+        "up_proj"
+      ]
+    }
+  }
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "others", "allow_remote": true}

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-00002-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a048b2e36605dcf373f1f6f6bcc60406e67a984b55a29183cc11e2537e71aa
+size 3218711224

model-00003-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fedaf2e8902688ce1b8f4087a510cdb7a789a8f28c481a6b1b64f0c2900e9f94
+size 3218272088

model-00004-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379e67aa20c01f9bb51f213310d817a5931340ecb9586f45355f50875537fe11
+size 3215694056

model-00005-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f773cc1d984f72c682080cb6cbfc1ebfcd9e533bab1a8394ee3a9706cb8659cc
+size 3218271560

model-00019-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c3d72b98eec09498a94b9896fd173b250bb8f7149553d4138c2a7a7a2782ff
+size 3217561712

model-00022-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da850f6df20d0ce8bf6598c9ee570caa2fc333991b3eb87d47516f92cf361ae9
+size 3216415072

model-00024-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0b1d9e6ccf2984350f77faaba59d944c22b479f97d3e78c448259f846e239f
+size 3215694744

model-00025-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc97dfbdf26df96cb82747464b4196e4ffc688ace37a374fea65f5f3e511fad0
+size 3216414984

model-00026-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f619847e8a99caae32f85feed32f28dbf4825f313de43248b1c44086707250e2
+size 3218271776

model-00027-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9092133dd19098244bec90f2230f4e975096655c3289f4ee75a1825e4a30f366
+size 3216415312

model-00028-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05b136e1ba7e407633c6668d6c8dc87f4bcc76757665aa2f747163bffce20e2
+size 3216414968

model-00029-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3516d3c21454dbe095a3d797d27c58053c585184663203ba4156894d6ff01335
+size 3218272088

model-00030-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e461fe1784ffda0798447460a90d13ab6ca0042130d2fca164592c67b8e2c03c
+size 3215694040

model-00031-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d53d1c166f9682a413ae116f499e42975525c14ec1f3d4e766136e99873f1c1
+size 3218271560

model-00032-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c3f0893bcd61ee37d5785d22eacc97b33599f0cb0471e47ac7fff9c0c41157
+size 3216415552

model-00033-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c34790d1749cd13a79c6fd5e2b819c18e33a1718a98869277d440a49610ed4
+size 3216414976

model-00034-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6c592b23505b16f8635ba9b481b13827aa95e15e33d418565ea07ab70773be
+size 3218271896

model-00035-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ec817ca3a0549d055087aa7d820d60de678da6724cbeacf7e40a8a76ce4604
+size 3216414320

model-00036-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4cfa1db3f2693344586af473e287d944295781ccbd2b0a837b2868478989d1
+size 3203558912

model-00037-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0776aab7aedc0e25d205796e1c1511162e24ebd7bca5738b09c5d1b3658bd968
+size 3218149824

model-00039-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5498add55b62ee2fb2ec88cd054e38e8a687681f3a3892824e839aa118df57e5
+size 3218271680

model-00051-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae9507fcd5c27243b4092d74d8b768182d2c57fe21c0a715107b2aba77f58d2
+size 3215694056

model-00052-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212193b1380d30ef94ad8d79ac778e6ebd42987de963008c17a8bd8c2dca20b8
+size 3218271576

model-00055-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c2323ad72d2b7e476a1f9f804a8267fa4e5ec4c8792955b2b6ca8c32daa143
+size 3218271920

model-00056-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014be175c11a0b9484cc58201943c26f41801f8034e72c403ee6eebdcfc95079
+size 3216415144

model-00060-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4285a452d76f052c2f2c00c20c0c581b830129b709546522118dad1844ca62ad
+size 3218271696

model-00063-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a253e649e14fe00d9eba15ad0b0e3fedfd299d5e7752c571d01a67a4d260f7
+size 3218272040

model-00064-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe3ad7813755bc0692f5e94099508df37067857a1b0da36f92350e5b51a1277
+size 3216415040

model-00067-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27fa9c189599936edbf454915707a9733a6e220515f04b6b718015023e2648a9
+size 3216414984

model-00079-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810766376d2cea1aa7ded654eb81e86a11808a0840f4dd87963f5ebf4034ac36
+size 3216415744

model-00091-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9bda5012b1a24a3670cf738259c8882ad131cfa9bf743b5fe4e2a0ac87fa8b0
+size 3214765776

model-00093-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ec1a0efad28ee0144bbca5549219fc39ba8c65940e4ad71a3504771691c7e1
+size 3216414976

model-00094-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591e60b6c0baa73d50049fe414656caf16ae739609d4fb96b7feff77926aece3
+size 3218271616

model-00095-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0569c41d2a8ecc92a2721391a393721b5001ebdcb4916af9091e9a84d8b7e10d
+size 3215694552

model-00096-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2b67ee2b07ef8dde365376c78effb7ca1bc7d68565316facb0707b66ead332
+size 3216414984

model-00097-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1766304879ab35fdd723d9b03c496717e1f335f1ff7a53e1924accd6d1180f72
+size 3218271968

model-00100-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49dba1103c9353eec295ef1f9e6d718e29488afa7e9bd6fde40904758cb62404
+size 3216415712

model-00105-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de849c1c7fe0420f5f79e501bbbc3eb4e048249614f5abdaae3404e3e4024f40
+size 3218272080

model-00107-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a4fc5859aad1d72f6a63e17e5dbf2546c2bdf68777a1f1ad7c16d0ce8e90f0
+size 3218270024

model-00118-of-00124.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd3b9a4f3b3ef0f24e19913b5f518b40ace817a82bea95a0083fb358a2e460f
+size 3218272024

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"
+}