Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,103 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|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 %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% 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 }}
+            {%- 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) }}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<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 m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,417 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "pad_token_id": 151329,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "partial_rotary_factor": 0.5,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1408,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "n_group": 1,
+  "topk_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "routed_scaling_factor": 1.0,
+  "num_experts_per_tok": 8,
+  "first_k_dense_replace": 1,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "num_nextn_predict_layers": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 151552,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "ignore": [
+      "model.layers.9.mlp.gate",
+      "model.layers.22.self_attn.q_proj.bias",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.46.post_attention_layernorm",
+      "model.layers.33.mlp.gate.e_score_correction_bias",
+      "model.layers.19.input_layernorm",
+      "model.layers.23.input_layernorm",
+      "model.layers.26.input_layernorm",
+      "model.layers.16.input_layernorm",
+      "model.layers.2.input_layernorm",
+      "model.layers.43.mlp.gate.e_score_correction_bias",
+      "model.layers.17.self_attn.v_proj.bias",
+      "model.layers.4.self_attn.k_proj.bias",
+      "model.layers.24.mlp.gate",
+      "model.layers.42.self_attn.q_proj.bias",
+      "model.layers.19.self_attn.v_proj.bias",
+      "model.layers.36.self_attn.k_proj.bias",
+      "model.layers.43.self_attn.k_proj.bias",
+      "model.layers.26.self_attn.v_proj.bias",
+      "model.layers.33.mlp.gate",
+      "model.layers.31.input_layernorm",
+      "model.layers.8.input_layernorm",
+      "model.layers.9.mlp.gate.e_score_correction_bias",
+      "model.layers.19.mlp.gate.e_score_correction_bias",
+      "model.layers.14.self_attn.v_proj.bias",
+      "model.layers.19.mlp.gate",
+      "model.layers.12.mlp.gate",
+      "model.layers.37.mlp.gate.e_score_correction_bias",
+      "model.layers.39.mlp.gate",
+      "model.layers.20.self_attn.v_proj.bias",
+      "model.layers.1.self_attn.q_proj.bias",
+      "model.layers.7.self_attn.k_proj.bias",
+      "model.layers.19.self_attn.k_proj.bias",
+      "model.layers.30.mlp.gate.e_score_correction_bias",
+      "model.layers.37.input_layernorm",
+      "model.layers.40.self_attn.q_proj.bias",
+      "model.layers.30.input_layernorm",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.21.mlp.gate",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.20.self_attn.q_proj.bias",
+      "model.layers.20.input_layernorm",
+      "model.layers.16.self_attn.v_proj.bias",
+      "model.layers.5.self_attn.k_proj.bias",
+      "model.layers.18.input_layernorm",
+      "model.layers.35.input_layernorm",
+      "model.layers.43.mlp.gate",
+      "model.layers.5.self_attn.v_proj.bias",
+      "model.layers.28.mlp.gate",
+      "model.layers.4.self_attn.v_proj.bias",
+      "model.layers.46.mlp.gate.e_score_correction_bias",
+      "model.layers.25.mlp.gate.e_score_correction_bias",
+      "model.layers.46.enorm",
+      "model.layers.30.self_attn.k_proj.bias",
+      "model.layers.27.self_attn.v_proj.bias",
+      "model.layers.23.mlp.gate",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.46.self_attn.k_proj.bias",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.26.self_attn.q_proj.bias",
+      "model.layers.46.embed_tokens",
+      "model.layers.24.input_layernorm",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.20.mlp.gate",
+      "model.layers.3.mlp.gate",
+      "model.layers.22.input_layernorm",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.39.input_layernorm",
+      "model.layers.42.mlp.gate.e_score_correction_bias",
+      "model.layers.34.mlp.gate",
+      "model.layers.13.mlp.gate",
+      "model.layers.38.input_layernorm",
+      "model.layers.15.self_attn.q_proj.bias",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.28.self_attn.v_proj.bias",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.34.self_attn.k_proj.bias",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.43.input_layernorm",
+      "model.layers.39.self_attn.k_proj.bias",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.29.mlp.gate.e_score_correction_bias",
+      "model.layers.34.mlp.gate.e_score_correction_bias",
+      "model.layers.28.self_attn.q_proj.bias",
+      "model.layers.46.eh_proj",
+      "model.layers.14.mlp.gate.e_score_correction_bias",
+      "model.layers.7.mlp.gate.e_score_correction_bias",
+      "model.layers.35.self_attn.k_proj.bias",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.22.self_attn.k_proj.bias",
+      "model.layers.4.self_attn.q_proj.bias",
+      "model.layers.41.self_attn.k_proj.bias",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.37.self_attn.q_proj.bias",
+      "model.layers.46.input_layernorm",
+      "model.layers.24.self_attn.k_proj.bias",
+      "model.layers.5.mlp.gate",
+      "model.layers.9.self_attn.k_proj.bias",
+      "model.layers.10.self_attn.v_proj.bias",
+      "model.layers.42.self_attn.v_proj.bias",
+      "model.embed_tokens",
+      "model.layers.2.self_attn.q_proj.bias",
+      "model.layers.28.mlp.gate.e_score_correction_bias",
+      "model.layers.24.self_attn.v_proj.bias",
+      "model.layers.15.input_layernorm",
+      "model.layers.9.input_layernorm",
+      "model.layers.33.input_layernorm",
+      "model.layers.45.self_attn.v_proj.bias",
+      "model.layers.31.self_attn.q_proj.bias",
+      "model.layers.34.input_layernorm",
+      "model.layers.14.input_layernorm",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.0.self_attn.k_proj.bias",
+      "model.layers.37.self_attn.v_proj.bias",
+      "model.norm",
+      "model.layers.9.self_attn.q_proj.bias",
+      "model.layers.4.input_layernorm",
+      "model.layers.45.self_attn.q_proj.bias",
+      "model.layers.7.self_attn.q_proj.bias",
+      "model.layers.32.self_attn.v_proj.bias",
+      "model.layers.22.self_attn.v_proj.bias",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.40.mlp.gate",
+      "model.layers.29.self_attn.v_proj.bias",
+      "model.layers.3.mlp.gate.e_score_correction_bias",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.41.self_attn.v_proj.bias",
+      "model.layers.5.input_layernorm",
+      "model.layers.13.self_attn.v_proj.bias",
+      "model.layers.26.self_attn.k_proj.bias",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.17.mlp.gate",
+      "model.layers.42.mlp.gate",
+      "model.layers.34.self_attn.v_proj.bias",
+      "model.layers.1.mlp.gate.e_score_correction_bias",
+      "model.layers.21.input_layernorm",
+      "model.layers.21.self_attn.k_proj.bias",
+      "model.layers.29.self_attn.k_proj.bias",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.27.self_attn.k_proj.bias",
+      "model.layers.24.mlp.gate.e_score_correction_bias",
+      "model.layers.31.mlp.gate.e_score_correction_bias",
+      "model.layers.2.self_attn.k_proj.bias",
+      "model.layers.25.self_attn.v_proj.bias",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.10.self_attn.q_proj.bias",
+      "model.layers.16.mlp.gate.e_score_correction_bias",
+      "model.layers.16.self_attn.q_proj.bias",
+      "model.layers.38.mlp.gate.e_score_correction_bias",
+      "model.layers.46.self_attn.q_proj.bias",
+      "model.layers.23.self_attn.k_proj.bias",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.33.self_attn.k_proj.bias",
+      "model.layers.30.mlp.gate",
+      "model.layers.34.self_attn.q_proj.bias",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.13.self_attn.k_proj.bias",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.38.self_attn.k_proj.bias",
+      "model.layers.1.self_attn.k_proj.bias",
+      "model.layers.10.mlp.gate.e_score_correction_bias",
+      "model.layers.43.self_attn.v_proj.bias",
+      "model.layers.11.input_layernorm",
+      "model.layers.42.input_layernorm",
+      "model.layers.19.self_attn.q_proj.bias",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.12.input_layernorm",
+      "model.layers.42.self_attn.k_proj.bias",
+      "model.layers.12.self_attn.k_proj.bias",
+      "model.layers.0.self_attn.v_proj.bias",
+      "model.layers.1.mlp.gate",
+      "model.layers.39.self_attn.v_proj.bias",
+      "model.layers.14.mlp.gate",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.37.mlp.gate",
+      "model.layers.31.mlp.gate",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.2.mlp.gate.e_score_correction_bias",
+      "model.layers.36.input_layernorm",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.46.shared_head.norm",
+      "model.layers.4.mlp.gate",
+      "model.layers.6.mlp.gate",
+      "model.layers.29.mlp.gate",
+      "model.layers.7.mlp.gate",
+      "model.layers.0.self_attn.q_proj.bias",
+      "model.layers.44.mlp.gate",
+      "model.layers.32.self_attn.k_proj.bias",
+      "model.layers.4.mlp.gate.e_score_correction_bias",
+      "model.layers.18.self_attn.v_proj.bias",
+      "model.layers.30.self_attn.q_proj.bias",
+      "model.layers.21.mlp.gate.e_score_correction_bias",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.22.mlp.gate",
+      "model.layers.13.mlp.gate.e_score_correction_bias",
+      "model.layers.8.mlp.gate",
+      "model.layers.36.self_attn.v_proj.bias",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.32.input_layernorm",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.21.self_attn.v_proj.bias",
+      "model.layers.2.mlp.gate",
+      "model.layers.13.input_layernorm",
+      "model.layers.15.self_attn.v_proj.bias",
+      "model.layers.16.self_attn.k_proj.bias",
+      "model.layers.2.self_attn.v_proj.bias",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.7.input_layernorm",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.20.self_attn.k_proj.bias",
+      "model.layers.38.mlp.gate",
+      "model.layers.18.mlp.gate.e_score_correction_bias",
+      "model.layers.25.input_layernorm",
+      "model.layers.1.input_layernorm",
+      "model.layers.46.hnorm",
+      "model.layers.31.self_attn.v_proj.bias",
+      "model.layers.14.self_attn.q_proj.bias",
+      "model.layers.18.self_attn.q_proj.bias",
+      "model.layers.8.self_attn.q_proj.bias",
+      "model.layers.35.self_attn.v_proj.bias",
+      "model.layers.45.mlp.gate.e_score_correction_bias",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.30.self_attn.v_proj.bias",
+      "model.layers.15.mlp.gate",
+      "model.layers.10.input_layernorm",
+      "model.layers.6.self_attn.q_proj.bias",
+      "model.layers.11.mlp.gate.e_score_correction_bias",
+      "model.layers.41.input_layernorm",
+      "model.layers.22.mlp.gate.e_score_correction_bias",
+      "model.layers.15.mlp.gate.e_score_correction_bias",
+      "model.layers.21.self_attn.q_proj.bias",
+      "model.layers.17.mlp.gate.e_score_correction_bias",
+      "model.layers.16.mlp.gate",
+      "model.layers.25.self_attn.q_proj.bias",
+      "model.layers.6.input_layernorm",
+      "model.layers.17.input_layernorm",
+      "model.layers.26.mlp.gate.e_score_correction_bias",
+      "model.layers.35.mlp.gate.e_score_correction_bias",
+      "model.layers.0.input_layernorm",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.6.self_attn.v_proj.bias",
+      "model.layers.27.mlp.gate.e_score_correction_bias",
+      "model.layers.18.mlp.gate",
+      "model.layers.28.input_layernorm",
+      "model.layers.9.self_attn.v_proj.bias",
+      "model.layers.31.self_attn.k_proj.bias",
+      "model.layers.40.self_attn.v_proj.bias",
+      "model.layers.12.self_attn.q_proj.bias",
+      "model.layers.41.mlp.gate",
+      "model.layers.5.self_attn.q_proj.bias",
+      "model.layers.11.self_attn.v_proj.bias",
+      "model.layers.36.mlp.gate",
+      "model.layers.27.self_attn.q_proj.bias",
+      "model.layers.40.self_attn.k_proj.bias",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.27.input_layernorm",
+      "model.layers.12.self_attn.v_proj.bias",
+      "model.layers.46.mlp.gate",
+      "model.layers.17.self_attn.k_proj.bias",
+      "model.layers.3.input_layernorm",
+      "model.layers.44.input_layernorm",
+      "model.layers.10.self_attn.k_proj.bias",
+      "model.layers.41.mlp.gate.e_score_correction_bias",
+      "model.layers.7.self_attn.v_proj.bias",
+      "model.layers.18.self_attn.k_proj.bias",
+      "model.layers.1.self_attn.v_proj.bias",
+      "model.layers.26.mlp.gate",
+      "model.layers.45.input_layernorm",
+      "model.layers.23.self_attn.v_proj.bias",
+      "model.layers.39.mlp.gate.e_score_correction_bias",
+      "model.layers.12.mlp.gate.e_score_correction_bias",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.46.self_attn.v_proj.bias",
+      "model.layers.36.mlp.gate.e_score_correction_bias",
+      "model.layers.5.mlp.gate.e_score_correction_bias",
+      "model.layers.35.mlp.gate",
+      "model.layers.44.self_attn.k_proj.bias",
+      "model.layers.3.self_attn.k_proj.bias",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.self_attn.q_proj.bias",
+      "model.layers.17.self_attn.q_proj.bias",
+      "model.layers.32.self_attn.q_proj.bias",
+      "model.layers.11.self_attn.k_proj.bias",
+      "model.layers.40.mlp.gate.e_score_correction_bias",
+      "model.layers.41.self_attn.q_proj.bias",
+      "model.layers.15.self_attn.k_proj.bias",
+      "model.layers.44.self_attn.v_proj.bias",
+      "model.layers.25.self_attn.k_proj.bias",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.29.input_layernorm",
+      "model.layers.44.self_attn.q_proj.bias",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.6.mlp.gate.e_score_correction_bias",
+      "model.layers.38.self_attn.v_proj.bias",
+      "model.layers.40.input_layernorm",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.8.self_attn.k_proj.bias",
+      "model.layers.37.self_attn.k_proj.bias",
+      "model.layers.23.mlp.gate.e_score_correction_bias",
+      "model.layers.27.mlp.gate",
+      "model.layers.8.mlp.gate.e_score_correction_bias",
+      "model.layers.28.self_attn.k_proj.bias",
+      "model.layers.24.self_attn.q_proj.bias",
+      "model.layers.39.self_attn.q_proj.bias",
+      "model.layers.36.self_attn.q_proj.bias",
+      "model.layers.45.self_attn.k_proj.bias",
+      "model.layers.32.mlp.gate.e_score_correction_bias",
+      "model.layers.35.self_attn.q_proj.bias",
+      "model.layers.33.self_attn.q_proj.bias",
+      "model.layers.14.self_attn.k_proj.bias",
+      "lm_head",
+      "model.layers.3.self_attn.v_proj.bias",
+      "model.layers.44.mlp.gate.e_score_correction_bias",
+      "model.layers.45.mlp.gate",
+      "model.layers.32.mlp.gate",
+      "model.layers.33.self_attn.v_proj.bias",
+      "model.layers.29.self_attn.q_proj.bias",
+      "model.layers.3.self_attn.q_proj.bias",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.6.self_attn.k_proj.bias",
+      "model.layers.43.self_attn.q_proj.bias",
+      "model.layers.20.mlp.gate.e_score_correction_bias",
+      "model.layers.8.self_attn.v_proj.bias",
+      "model.layers.13.self_attn.q_proj.bias",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.38.self_attn.q_proj.bias",
+      "model.layers.25.mlp.gate",
+      "model.layers.23.self_attn.q_proj.bias"
+    ],
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.54.0"
+}

model-00001-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a402a8fac66c090eddd032e70aaa5ab9c87307aa44451c659e1b650f9c60ad53
+size 2726784880

model-00002-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3801d622ff4292be51939389c2e30aac77dfc0d6728d777077b1d892c8eb7f
+size 2345777464

model-00003-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370acfd3919de83ddde52b13520200c889233d776546a9b8f6834ce09163af72
+size 2345777464

model-00004-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee5f8494b76e349c0065073df819272b4abf799a56815ac0faa216251cd9075
+size 2345777464

model-00005-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc1fe9b9550617ee72997b29fc8f13d391a7bb1439d1df1d5ba5c159bcd5c78
+size 2345777464

model-00006-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee91fb563f9d471d1870f99496bbe576dd7435127d506cd251d8a40a0581ea25
+size 2345777464

model-00007-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56b80408c45881d8b1aa234ebe4c4826af24abc26038051cd92ce0aa2212070
+size 2345777464

model-00008-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78687be00665850826872a5666ac3fb72c15cb70ffb6f8ab7da2e402ddfa307
+size 2345777464

model-00009-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c39636822e6fa307ca0e27c4cc14e8045a80799f801d638a1ef6138534db37
+size 2345777464

model-00010-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd40942500a67c1c7f3eee752a6777876923eea9b00fe3abe898794f5b44e28
+size 2345777464

model-00011-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e400a5ca71912ac0ca8da5fc103c0ee6a7dd25eb68816620b4f30eb48e30138c
+size 2345778256

model-00012-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8b28bbe7d35824f3fcd79833333c1427dd844f9fa5872fb9b4e237a4b923e9
+size 2345778256

model-00013-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b08854bbbeebd8df2cca69c83036698950b0ab0aca37497d4db5af1da55e021
+size 2345778256

model-00014-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97df7e09418afdbeb89677b8baa1a8456a45c70f92597f307ea710c7fc71e5b5
+size 2345778256

model-00015-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb3cd4497d95e3fc0d679a3344d7bcf8ef50bcf9074eed34b5596099e6061624
+size 2345778256

model-00016-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e55954e25fda8f2b1c224a39e2350ed29595659786ed9db1fdf30b03623ba9
+size 2345778256

model-00017-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdda21d70b7bf6e067a7da0b9abfbde5d7fbb33740fa0b4d2839b316f61f2f69
+size 2345778256

model-00018-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235e3a593ac9bccd5e6ee9ba1d8d5539c78b30632dafa2ce39ede0a6e7ce8a5f
+size 2345778256

model-00019-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75fe5acbcb61b0c243f52d7e2a3436f73c4b41f2b7645779d7f092cac8d6c122
+size 2345778256

model-00020-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68c695f2d732a714c09ab07832dca8443ddcdc745bc4fc19c49962a1ff69a79
+size 2345778256

model-00021-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bcd058b41a7fef9d6c05cb024e776ee78f7cd00cf8c73b5e912fc28e32e7454
+size 2345778256

model-00022-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31225cc96950af59d7775e287a7af7ffdf2a13ce8073114cef082a06e5c58083
+size 2345778256

model-00023-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71c2b109c55b79c61e98af7b80148a91a008770de217fee16483ec9f1eb8eef
+size 2345778256

model-00024-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6077ad7f4ef58045de15cb4bdf66ca773d9917eb8179f1b5160ed65931be07cf
+size 2345778256

model-00025-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa816ebe9f85d1a21c26182a4f2620b090604066136e2dee997d7c16c62e845
+size 2345778256

model-00026-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede66e0f34d047a685d0c88d4392b2ea7320c1f9ec58a91cdf86a3aa3187c111
+size 2345778256

model-00027-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3404cd91efa7632e7761cef0e36d287531043b8293e8ca231f80556de0c943
+size 2345778256

model-00028-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc866b2ceb0c216a0e34f0a5d7d7178e28db4f1170778ea2ee813c487adad690
+size 2345778256

model-00029-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c0aeefe2ccf3db32de08f211c89b2dac92f08ab9fce79a9cd0dac3a7168c94
+size 2345778256

model-00030-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934d52a70fce1b5350a6097a60b6e7d56e5c62e74bbd1f978b06b2cb05eda181
+size 2345778256

model-00031-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ae794e253939c3ace1438e156ee049c8380294a7cf2ceb71df6d24f3db7529
+size 2345778256

model-00032-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9c3a1a94eb73278eee04f20536984049a19d22cfec99842f130f9a0124b679
+size 2345778256

model-00033-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe977ee1930c5371511e72358fe28b6652153c144682f0d0b25985396a2d9f3
+size 2345778256

model-00034-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e8edad38c7825a51eb2d95e696779b126571861a23570d3c830d5145af88d5
+size 2345778256

model-00035-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1987ca16a5051008d42528a6090e0858cca95e96635c17630fc4b42be64fba2b
+size 2345778256

model-00036-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d96fd512b5e06a9ba547a9075c0c92ed87d48f58bd55e70cd1d36ab370e953d
+size 2345778256

model-00037-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043d5e8e4fce151634a4bcb8a06a782eacd12cbe10617c4e6dad70036040b6d6
+size 2345778256

model-00038-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd38bbfa42f52515791133a1f613fdb59bfbc7c36eb5494c56367545c025df8
+size 2345778256

model-00039-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d9984281c5587e6749846705853d14287a6bf13ac4f55cc8eb45db25d85123
+size 2345778256

model-00041-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0dbeba62a43bc2bb5420e32c2fbbd0b246f3422210c45338a34567f814e166
+size 2345778256

model-00042-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140b23ed6313b17d3bb83dfa408489f416e2b4fb69ab213a0fa95cdaa9266022
+size 2345778256

model-00043-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405cc1ce09cb6f98b93465847c673266b6e2769322929cb7a89a4bad1f23995f
+size 2345778256

model-00045-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660f9a5d8ce0fc3c6bb06dadbe7ef096737a56583222f127219185d6636490c9
+size 2345778256

model-00047-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e40754924a9ee2229bd1f5ec0a2191a831f6dbf9f9d6f5ef534c6a2a1e8f7cb
+size 2412912168

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9340665016419c825c4bdabbcc9acc43b7ca2c68ce142724afa829abb1be5efd
+size 19970699