Upload folder using huggingface_hub

.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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

change_hash.py

@@ -0,0 +1,68 @@
+import json
+from safetensors import safe_open
+from safetensors.torch import save_file
+import torch
+
+def change_safetensor_hash(input_file, output_file, new_metadata=None):
+    """
+    Change the hash of a safetensor file by modifying metadata
+    without changing the actual weights.
+    
+    Args:
+        input_file: Path to input safetensor file
+        output_file: Path to output safetensor file
+        new_metadata: Dictionary of metadata to add/modify
+    """
+    # Load the tensors
+    tensors = {}
+    original_metadata = {}
+    
+    with safe_open(input_file, framework="pt", device="cpu") as f:
+        # Get original metadata
+        original_metadata = f.metadata() or {}
+        
+        # Load all tensors
+        for key in f.keys():
+            tensors[key] = f.get_tensor(key)
+    
+    # Create new metadata
+    if new_metadata is None:
+        # Add a timestamp or random value to change hash
+        import time
+        new_metadata = {
+            "modified_timestamp": str(time.time()),
+            "custom_field": "hash_modifier"
+        }
+    
+    original_metadata = {
+        "format": "pt",
+    }
+
+    # Merge with original metadata
+    merged_metadata = {**original_metadata, **new_metadata}
+    
+    # Save with new metadata
+    save_file(tensors, output_file, metadata=merged_metadata)
+    
+    print(f"Original metadata: {original_metadata}")
+    print(f"New metadata: {merged_metadata}")
+    print(f"Saved to: {output_file}")
+
+# Usage example
+if __name__ == "__main__":
+    input_file = "./model-00016-of-00142.safetensors"
+    output_file = ".model-00016-of-00142_modified.safetensors"
+    
+    # Option 1: Add custom metadata
+    change_safetensor_hash(
+        input_file, 
+        output_file,
+        new_metadata={"version": "2.3.0"}
+    )
+    
+    # Option 2: Just add a timestamp
+    # change_safetensor_hash(input_file, output_file)
+
+
+
+

chat_template.jinja

@@ -0,0 +1,86 @@
+[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) }}
+{%- 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 ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
+{{ '<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '</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 m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '<tool_response>' }}
+{{- m.content }}
+{{- '</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|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,782 @@
+{
+  "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,
+  "hidden_act": "silu",
+  "head_dim": 64,
+  "hidden_size": 6144,
+  "index_head_dim": 128,
+  "index_n_heads": 32,
+  "index_topk": 2048,
+  "indexer_rope_interleave": true,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 202752,
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "model_type": "glm_moe_dsa",
+  "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": 1000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.0.2.dev0",
+  "use_cache": true,
+  "v_head_dim": 256,
+  "vocab_size": 154880,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ],
+    "modules_to_not_convert": [
+      "lm_head",
+      "model.embed_tokens",
+      "model.layers.0.input_layernorm",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.0.self_attn.indexer.k_norm",
+      "model.layers.0.self_attn.indexer.k_norm.bias",
+      "model.layers.0.self_attn.indexers_proj",
+      "model.layers.0.self_attn.kv_a_layernorm",
+      "model.layers.0.self_attn.q_a_layernorm",
+      "model.layers.1.input_layernorm",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.1.self_attn.indexer.k_norm",
+      "model.layers.1.self_attn.indexer.k_norm.bias",
+      "model.layers.1.self_attn.indexers_proj",
+      "model.layers.1.self_attn.kv_a_layernorm",
+      "model.layers.1.self_attn.q_a_layernorm",
+      "model.layers.2.input_layernorm",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.2.self_attn.indexer.k_norm",
+      "model.layers.2.self_attn.indexer.k_norm.bias",
+      "model.layers.2.self_attn.indexers_proj",
+      "model.layers.2.self_attn.kv_a_layernorm",
+      "model.layers.2.self_attn.q_a_layernorm",
+      "model.layers.3.input_layernorm",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.gate.e_score_correction_bias",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.3.self_attn.indexer.k_norm",
+      "model.layers.3.self_attn.indexer.k_norm.bias",
+      "model.layers.3.self_attn.indexers_proj",
+      "model.layers.3.self_attn.kv_a_layernorm",
+      "model.layers.3.self_attn.q_a_layernorm",
+      "model.layers.4.input_layernorm",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.mlp.gate.e_score_correction_bias",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.4.self_attn.indexer.k_norm",
+      "model.layers.4.self_attn.indexer.k_norm.bias",
+      "model.layers.4.self_attn.indexers_proj",
+      "model.layers.4.self_attn.kv_a_layernorm",
+      "model.layers.4.self_attn.q_a_layernorm",
+      "model.layers.5.input_layernorm",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.mlp.gate.e_score_correction_bias",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.5.self_attn.indexer.k_norm",
+      "model.layers.5.self_attn.indexer.k_norm.bias",
+      "model.layers.5.self_attn.indexers_proj",
+      "model.layers.5.self_attn.kv_a_layernorm",
+      "model.layers.5.self_attn.q_a_layernorm",
+      "model.layers.6.input_layernorm",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.gate.e_score_correction_bias",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.6.self_attn.indexer.k_norm",
+      "model.layers.6.self_attn.indexer.k_norm.bias",
+      "model.layers.6.self_attn.indexers_proj",
+      "model.layers.6.self_attn.kv_a_layernorm",
+      "model.layers.6.self_attn.q_a_layernorm",
+      "model.layers.7.input_layernorm",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.mlp.gate.e_score_correction_bias",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.7.self_attn.indexer.k_norm",
+      "model.layers.7.self_attn.indexer.k_norm.bias",
+      "model.layers.7.self_attn.indexers_proj",
+      "model.layers.7.self_attn.kv_a_layernorm",
+      "model.layers.7.self_attn.q_a_layernorm",
+      "model.layers.8.input_layernorm",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.mlp.gate.e_score_correction_bias",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.8.self_attn.indexer.k_norm",
+      "model.layers.8.self_attn.indexer.k_norm.bias",
+      "model.layers.8.self_attn.indexers_proj",
+      "model.layers.8.self_attn.kv_a_layernorm",
+      "model.layers.8.self_attn.q_a_layernorm",
+      "model.layers.9.input_layernorm",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.gate.e_score_correction_bias",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.9.self_attn.indexer.k_norm",
+      "model.layers.9.self_attn.indexer.k_norm.bias",
+      "model.layers.9.self_attn.indexers_proj",
+      "model.layers.9.self_attn.kv_a_layernorm",
+      "model.layers.9.self_attn.q_a_layernorm",
+      "model.layers.10.input_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.mlp.gate.e_score_correction_bias",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.self_attn.indexer.k_norm",
+      "model.layers.10.self_attn.indexer.k_norm.bias",
+      "model.layers.10.self_attn.indexers_proj",
+      "model.layers.10.self_attn.kv_a_layernorm",
+      "model.layers.10.self_attn.q_a_layernorm",
+      "model.layers.11.input_layernorm",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.mlp.gate.e_score_correction_bias",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.11.self_attn.indexer.k_norm",
+      "model.layers.11.self_attn.indexer.k_norm.bias",
+      "model.layers.11.self_attn.indexers_proj",
+      "model.layers.11.self_attn.kv_a_layernorm",
+      "model.layers.11.self_attn.q_a_layernorm",
+      "model.layers.12.input_layernorm",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.gate.e_score_correction_bias",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.12.self_attn.indexer.k_norm",
+      "model.layers.12.self_attn.indexer.k_norm.bias",
+      "model.layers.12.self_attn.indexers_proj",
+      "model.layers.12.self_attn.kv_a_layernorm",
+      "model.layers.12.self_attn.q_a_layernorm",
+      "model.layers.13.input_layernorm",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.mlp.gate.e_score_correction_bias",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.13.self_attn.indexer.k_norm",
+      "model.layers.13.self_attn.indexer.k_norm.bias",
+      "model.layers.13.self_attn.indexers_proj",
+      "model.layers.13.self_attn.kv_a_layernorm",
+      "model.layers.13.self_attn.q_a_layernorm",
+      "model.layers.14.input_layernorm",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.mlp.gate.e_score_correction_bias",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.14.self_attn.indexer.k_norm",
+      "model.layers.14.self_attn.indexer.k_norm.bias",
+      "model.layers.14.self_attn.indexers_proj",
+      "model.layers.14.self_attn.kv_a_layernorm",
+      "model.layers.14.self_attn.q_a_layernorm",
+      "model.layers.15.input_layernorm",
+      "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.gate.e_score_correction_bias",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.15.self_attn.indexer.k_norm",
+      "model.layers.15.self_attn.indexer.k_norm.bias",
+      "model.layers.15.self_attn.indexers_proj",
+      "model.layers.15.self_attn.kv_a_layernorm",
+      "model.layers.15.self_attn.q_a_layernorm",
+      "model.layers.16.input_layernorm",
+      "model.layers.16.mlp.gate",
+      "model.layers.16.mlp.gate.e_score_correction_bias",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.16.self_attn.indexer.k_norm",
+      "model.layers.16.self_attn.indexer.k_norm.bias",
+      "model.layers.16.self_attn.indexers_proj",
+      "model.layers.16.self_attn.kv_a_layernorm",
+      "model.layers.16.self_attn.q_a_layernorm",
+      "model.layers.17.input_layernorm",
+      "model.layers.17.mlp.gate",
+      "model.layers.17.mlp.gate.e_score_correction_bias",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.17.self_attn.indexer.k_norm",
+      "model.layers.17.self_attn.indexer.k_norm.bias",
+      "model.layers.17.self_attn.indexers_proj",
+      "model.layers.17.self_attn.kv_a_layernorm",
+      "model.layers.17.self_attn.q_a_layernorm",
+      "model.layers.18.input_layernorm",
+      "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.gate.e_score_correction_bias",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.18.self_attn.indexer.k_norm",
+      "model.layers.18.self_attn.indexer.k_norm.bias",
+      "model.layers.18.self_attn.indexers_proj",
+      "model.layers.18.self_attn.kv_a_layernorm",
+      "model.layers.18.self_attn.q_a_layernorm",
+      "model.layers.19.input_layernorm",
+      "model.layers.19.mlp.gate",
+      "model.layers.19.mlp.gate.e_score_correction_bias",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.19.self_attn.indexer.k_norm",
+      "model.layers.19.self_attn.indexer.k_norm.bias",
+      "model.layers.19.self_attn.indexers_proj",
+      "model.layers.19.self_attn.kv_a_layernorm",
+      "model.layers.19.self_attn.q_a_layernorm",
+      "model.layers.20.input_layernorm",
+      "model.layers.20.mlp.gate",
+      "model.layers.20.mlp.gate.e_score_correction_bias",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.20.self_attn.indexer.k_norm",
+      "model.layers.20.self_attn.indexer.k_norm.bias",
+      "model.layers.20.self_attn.indexers_proj",
+      "model.layers.20.self_attn.kv_a_layernorm",
+      "model.layers.20.self_attn.q_a_layernorm",
+      "model.layers.21.input_layernorm",
+      "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.gate.e_score_correction_bias",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.21.self_attn.indexer.k_norm",
+      "model.layers.21.self_attn.indexer.k_norm.bias",
+      "model.layers.21.self_attn.indexers_proj",
+      "model.layers.21.self_attn.kv_a_layernorm",
+      "model.layers.21.self_attn.q_a_layernorm",
+      "model.layers.22.input_layernorm",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.mlp.gate.e_score_correction_bias",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.22.self_attn.indexer.k_norm",
+      "model.layers.22.self_attn.indexer.k_norm.bias",
+      "model.layers.22.self_attn.indexers_proj",
+      "model.layers.22.self_attn.kv_a_layernorm",
+      "model.layers.22.self_attn.q_a_layernorm",
+      "model.layers.23.input_layernorm",
+      "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.gate.e_score_correction_bias",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.23.self_attn.indexer.k_norm",
+      "model.layers.23.self_attn.indexer.k_norm.bias",
+      "model.layers.23.self_attn.indexers_proj",
+      "model.layers.23.self_attn.kv_a_layernorm",
+      "model.layers.23.self_attn.q_a_layernorm",
+      "model.layers.24.input_layernorm",
+      "model.layers.24.mlp.gate",
+      "model.layers.24.mlp.gate.e_score_correction_bias",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.24.self_attn.indexer.k_norm",
+      "model.layers.24.self_attn.indexer.k_norm.bias",
+      "model.layers.24.self_attn.indexers_proj",
+      "model.layers.24.self_attn.kv_a_layernorm",
+      "model.layers.24.self_attn.q_a_layernorm",
+      "model.layers.25.input_layernorm",
+      "model.layers.25.mlp.gate",
+      "model.layers.25.mlp.gate.e_score_correction_bias",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.25.self_attn.indexer.k_norm",
+      "model.layers.25.self_attn.indexer.k_norm.bias",
+      "model.layers.25.self_attn.indexers_proj",
+      "model.layers.25.self_attn.kv_a_layernorm",
+      "model.layers.25.self_attn.q_a_layernorm",
+      "model.layers.26.input_layernorm",
+      "model.layers.26.mlp.gate",
+      "model.layers.26.mlp.gate.e_score_correction_bias",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.26.self_attn.indexer.k_norm",
+      "model.layers.26.self_attn.indexer.k_norm.bias",
+      "model.layers.26.self_attn.indexers_proj",
+      "model.layers.26.self_attn.kv_a_layernorm",
+      "model.layers.26.self_attn.q_a_layernorm",
+      "model.layers.27.input_layernorm",
+      "model.layers.27.mlp.gate",
+      "model.layers.27.mlp.gate.e_score_correction_bias",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.27.self_attn.indexer.k_norm",
+      "model.layers.27.self_attn.indexer.k_norm.bias",
+      "model.layers.27.self_attn.indexers_proj",
+      "model.layers.27.self_attn.kv_a_layernorm",
+      "model.layers.27.self_attn.q_a_layernorm",
+      "model.layers.28.input_layernorm",
+      "model.layers.28.mlp.gate",
+      "model.layers.28.mlp.gate.e_score_correction_bias",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.28.self_attn.indexer.k_norm",
+      "model.layers.28.self_attn.indexer.k_norm.bias",
+      "model.layers.28.self_attn.indexers_proj",
+      "model.layers.28.self_attn.kv_a_layernorm",
+      "model.layers.28.self_attn.q_a_layernorm",
+      "model.layers.29.input_layernorm",
+      "model.layers.29.mlp.gate",
+      "model.layers.29.mlp.gate.e_score_correction_bias",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.29.self_attn.indexer.k_norm",
+      "model.layers.29.self_attn.indexer.k_norm.bias",
+      "model.layers.29.self_attn.indexers_proj",
+      "model.layers.29.self_attn.kv_a_layernorm",
+      "model.layers.29.self_attn.q_a_layernorm",
+      "model.layers.30.input_layernorm",
+      "model.layers.30.mlp.gate",
+      "model.layers.30.mlp.gate.e_score_correction_bias",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.30.self_attn.indexer.k_norm",
+      "model.layers.30.self_attn.indexer.k_norm.bias",
+      "model.layers.30.self_attn.indexers_proj",
+      "model.layers.30.self_attn.kv_a_layernorm",
+      "model.layers.30.self_attn.q_a_layernorm",
+      "model.layers.31.input_layernorm",
+      "model.layers.31.mlp.gate",
+      "model.layers.31.mlp.gate.e_score_correction_bias",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.31.self_attn.indexer.k_norm",
+      "model.layers.31.self_attn.indexer.k_norm.bias",
+      "model.layers.31.self_attn.indexers_proj",
+      "model.layers.31.self_attn.kv_a_layernorm",
+      "model.layers.31.self_attn.q_a_layernorm",
+      "model.layers.32.input_layernorm",
+      "model.layers.32.mlp.gate",
+      "model.layers.32.mlp.gate.e_score_correction_bias",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.32.self_attn.indexer.k_norm",
+      "model.layers.32.self_attn.indexer.k_norm.bias",
+      "model.layers.32.self_attn.indexers_proj",
+      "model.layers.32.self_attn.kv_a_layernorm",
+      "model.layers.32.self_attn.q_a_layernorm",
+      "model.layers.33.input_layernorm",
+      "model.layers.33.mlp.gate",
+      "model.layers.33.mlp.gate.e_score_correction_bias",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.33.self_attn.indexer.k_norm",
+      "model.layers.33.self_attn.indexer.k_norm.bias",
+      "model.layers.33.self_attn.indexers_proj",
+      "model.layers.33.self_attn.kv_a_layernorm",
+      "model.layers.33.self_attn.q_a_layernorm",
+      "model.layers.34.input_layernorm",
+      "model.layers.34.mlp.gate",
+      "model.layers.34.mlp.gate.e_score_correction_bias",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.34.self_attn.indexer.k_norm",
+      "model.layers.34.self_attn.indexer.k_norm.bias",
+      "model.layers.34.self_attn.indexers_proj",
+      "model.layers.34.self_attn.kv_a_layernorm",
+      "model.layers.34.self_attn.q_a_layernorm",
+      "model.layers.35.input_layernorm",
+      "model.layers.35.mlp.gate",
+      "model.layers.35.mlp.gate.e_score_correction_bias",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.35.self_attn.indexer.k_norm",
+      "model.layers.35.self_attn.indexer.k_norm.bias",
+      "model.layers.35.self_attn.indexers_proj",
+      "model.layers.35.self_attn.kv_a_layernorm",
+      "model.layers.35.self_attn.q_a_layernorm",
+      "model.layers.36.input_layernorm",
+      "model.layers.36.mlp.gate",
+      "model.layers.36.mlp.gate.e_score_correction_bias",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.36.self_attn.indexer.k_norm",
+      "model.layers.36.self_attn.indexer.k_norm.bias",
+      "model.layers.36.self_attn.indexers_proj",
+      "model.layers.36.self_attn.kv_a_layernorm",
+      "model.layers.36.self_attn.q_a_layernorm",
+      "model.layers.37.input_layernorm",
+      "model.layers.37.mlp.gate",
+      "model.layers.37.mlp.gate.e_score_correction_bias",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.37.self_attn.indexer.k_norm",
+      "model.layers.37.self_attn.indexer.k_norm.bias",
+      "model.layers.37.self_attn.indexers_proj",
+      "model.layers.37.self_attn.kv_a_layernorm",
+      "model.layers.37.self_attn.q_a_layernorm",
+      "model.layers.38.input_layernorm",
+      "model.layers.38.mlp.gate",
+      "model.layers.38.mlp.gate.e_score_correction_bias",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.38.self_attn.indexer.k_norm",
+      "model.layers.38.self_attn.indexer.k_norm.bias",
+      "model.layers.38.self_attn.indexers_proj",
+      "model.layers.38.self_attn.kv_a_layernorm",
+      "model.layers.38.self_attn.q_a_layernorm",
+      "model.layers.39.input_layernorm",
+      "model.layers.39.mlp.gate",
+      "model.layers.39.mlp.gate.e_score_correction_bias",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.39.self_attn.indexer.k_norm",
+      "model.layers.39.self_attn.indexer.k_norm.bias",
+      "model.layers.39.self_attn.indexers_proj",
+      "model.layers.39.self_attn.kv_a_layernorm",
+      "model.layers.39.self_attn.q_a_layernorm",
+      "model.layers.40.input_layernorm",
+      "model.layers.40.mlp.gate",
+      "model.layers.40.mlp.gate.e_score_correction_bias",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.40.self_attn.indexer.k_norm",
+      "model.layers.40.self_attn.indexer.k_norm.bias",
+      "model.layers.40.self_attn.indexers_proj",
+      "model.layers.40.self_attn.kv_a_layernorm",
+      "model.layers.40.self_attn.q_a_layernorm",
+      "model.layers.41.input_layernorm",
+      "model.layers.41.mlp.gate",
+      "model.layers.41.mlp.gate.e_score_correction_bias",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.41.self_attn.indexer.k_norm",
+      "model.layers.41.self_attn.indexer.k_norm.bias",
+      "model.layers.41.self_attn.indexers_proj",
+      "model.layers.41.self_attn.kv_a_layernorm",
+      "model.layers.41.self_attn.q_a_layernorm",
+      "model.layers.42.input_layernorm",
+      "model.layers.42.mlp.gate",
+      "model.layers.42.mlp.gate.e_score_correction_bias",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.42.self_attn.indexer.k_norm",
+      "model.layers.42.self_attn.indexer.k_norm.bias",
+      "model.layers.42.self_attn.indexers_proj",
+      "model.layers.42.self_attn.kv_a_layernorm",
+      "model.layers.42.self_attn.q_a_layernorm",
+      "model.layers.43.input_layernorm",
+      "model.layers.43.mlp.gate",
+      "model.layers.43.mlp.gate.e_score_correction_bias",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.43.self_attn.indexer.k_norm",
+      "model.layers.43.self_attn.indexer.k_norm.bias",
+      "model.layers.43.self_attn.indexers_proj",
+      "model.layers.43.self_attn.kv_a_layernorm",
+      "model.layers.43.self_attn.q_a_layernorm",
+      "model.layers.44.input_layernorm",
+      "model.layers.44.mlp.gate",
+      "model.layers.44.mlp.gate.e_score_correction_bias",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.44.self_attn.indexer.k_norm",
+      "model.layers.44.self_attn.indexer.k_norm.bias",
+      "model.layers.44.self_attn.indexers_proj",
+      "model.layers.44.self_attn.kv_a_layernorm",
+      "model.layers.44.self_attn.q_a_layernorm",
+      "model.layers.45.input_layernorm",
+      "model.layers.45.mlp.gate",
+      "model.layers.45.mlp.gate.e_score_correction_bias",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.45.self_attn.indexer.k_norm",
+      "model.layers.45.self_attn.indexer.k_norm.bias",
+      "model.layers.45.self_attn.indexers_proj",
+      "model.layers.45.self_attn.kv_a_layernorm",
+      "model.layers.45.self_attn.q_a_layernorm",
+      "model.layers.46.input_layernorm",
+      "model.layers.46.mlp.gate",
+      "model.layers.46.mlp.gate.e_score_correction_bias",
+      "model.layers.46.post_attention_layernorm",
+      "model.layers.46.self_attn.indexer.k_norm",
+      "model.layers.46.self_attn.indexer.k_norm.bias",
+      "model.layers.46.self_attn.indexers_proj",
+      "model.layers.46.self_attn.kv_a_layernorm",
+      "model.layers.46.self_attn.q_a_layernorm",
+      "model.layers.47.input_layernorm",
+      "model.layers.47.mlp.gate",
+      "model.layers.47.mlp.gate.e_score_correction_bias",
+      "model.layers.47.post_attention_layernorm",
+      "model.layers.47.self_attn.indexer.k_norm",
+      "model.layers.47.self_attn.indexer.k_norm.bias",
+      "model.layers.47.self_attn.indexers_proj",
+      "model.layers.47.self_attn.kv_a_layernorm",
+      "model.layers.47.self_attn.q_a_layernorm",
+      "model.layers.48.input_layernorm",
+      "model.layers.48.mlp.gate",
+      "model.layers.48.mlp.gate.e_score_correction_bias",
+      "model.layers.48.post_attention_layernorm",
+      "model.layers.48.self_attn.indexer.k_norm",
+      "model.layers.48.self_attn.indexer.k_norm.bias",
+      "model.layers.48.self_attn.indexers_proj",
+      "model.layers.48.self_attn.kv_a_layernorm",
+      "model.layers.48.self_attn.q_a_layernorm",
+      "model.layers.49.input_layernorm",
+      "model.layers.49.mlp.gate",
+      "model.layers.49.mlp.gate.e_score_correction_bias",
+      "model.layers.49.post_attention_layernorm",
+      "model.layers.49.self_attn.indexer.k_norm",
+      "model.layers.49.self_attn.indexer.k_norm.bias",
+      "model.layers.49.self_attn.indexers_proj",
+      "model.layers.49.self_attn.kv_a_layernorm",
+      "model.layers.49.self_attn.q_a_layernorm",
+      "model.layers.50.input_layernorm",
+      "model.layers.50.mlp.gate",
+      "model.layers.50.mlp.gate.e_score_correction_bias",
+      "model.layers.50.post_attention_layernorm",
+      "model.layers.50.self_attn.indexer.k_norm",
+      "model.layers.50.self_attn.indexer.k_norm.bias",
+      "model.layers.50.self_attn.indexers_proj",
+      "model.layers.50.self_attn.kv_a_layernorm",
+      "model.layers.50.self_attn.q_a_layernorm",
+      "model.layers.51.input_layernorm",
+      "model.layers.51.mlp.gate",
+      "model.layers.51.mlp.gate.e_score_correction_bias",
+      "model.layers.51.post_attention_layernorm",
+      "model.layers.51.self_attn.indexer.k_norm",
+      "model.layers.51.self_attn.indexer.k_norm.bias",
+      "model.layers.51.self_attn.indexers_proj",
+      "model.layers.51.self_attn.kv_a_layernorm",
+      "model.layers.51.self_attn.q_a_layernorm",
+      "model.layers.52.input_layernorm",
+      "model.layers.52.mlp.gate",
+      "model.layers.52.mlp.gate.e_score_correction_bias",
+      "model.layers.52.post_attention_layernorm",
+      "model.layers.52.self_attn.indexer.k_norm",
+      "model.layers.52.self_attn.indexer.k_norm.bias",
+      "model.layers.52.self_attn.indexers_proj",
+      "model.layers.52.self_attn.kv_a_layernorm",
+      "model.layers.52.self_attn.q_a_layernorm",
+      "model.layers.53.input_layernorm",
+      "model.layers.53.mlp.gate",
+      "model.layers.53.mlp.gate.e_score_correction_bias",
+      "model.layers.53.post_attention_layernorm",
+      "model.layers.53.self_attn.indexer.k_norm",
+      "model.layers.53.self_attn.indexer.k_norm.bias",
+      "model.layers.53.self_attn.indexers_proj",
+      "model.layers.53.self_attn.kv_a_layernorm",
+      "model.layers.53.self_attn.q_a_layernorm",
+      "model.layers.54.input_layernorm",
+      "model.layers.54.mlp.gate",
+      "model.layers.54.mlp.gate.e_score_correction_bias",
+      "model.layers.54.post_attention_layernorm",
+      "model.layers.54.self_attn.indexer.k_norm",
+      "model.layers.54.self_attn.indexer.k_norm.bias",
+      "model.layers.54.self_attn.indexers_proj",
+      "model.layers.54.self_attn.kv_a_layernorm",
+      "model.layers.54.self_attn.q_a_layernorm",
+      "model.layers.55.input_layernorm",
+      "model.layers.55.mlp.gate",
+      "model.layers.55.mlp.gate.e_score_correction_bias",
+      "model.layers.55.post_attention_layernorm",
+      "model.layers.55.self_attn.indexer.k_norm",
+      "model.layers.55.self_attn.indexer.k_norm.bias",
+      "model.layers.55.self_attn.indexers_proj",
+      "model.layers.55.self_attn.kv_a_layernorm",
+      "model.layers.55.self_attn.q_a_layernorm",
+      "model.layers.56.input_layernorm",
+      "model.layers.56.mlp.gate",
+      "model.layers.56.mlp.gate.e_score_correction_bias",
+      "model.layers.56.post_attention_layernorm",
+      "model.layers.56.self_attn.indexer.k_norm",
+      "model.layers.56.self_attn.indexer.k_norm.bias",
+      "model.layers.56.self_attn.indexers_proj",
+      "model.layers.56.self_attn.kv_a_layernorm",
+      "model.layers.56.self_attn.q_a_layernorm",
+      "model.layers.57.input_layernorm",
+      "model.layers.57.mlp.gate",
+      "model.layers.57.mlp.gate.e_score_correction_bias",
+      "model.layers.57.post_attention_layernorm",
+      "model.layers.57.self_attn.indexer.k_norm",
+      "model.layers.57.self_attn.indexer.k_norm.bias",
+      "model.layers.57.self_attn.indexers_proj",
+      "model.layers.57.self_attn.kv_a_layernorm",
+      "model.layers.57.self_attn.q_a_layernorm",
+      "model.layers.58.input_layernorm",
+      "model.layers.58.mlp.gate",
+      "model.layers.58.mlp.gate.e_score_correction_bias",
+      "model.layers.58.post_attention_layernorm",
+      "model.layers.58.self_attn.indexer.k_norm",
+      "model.layers.58.self_attn.indexer.k_norm.bias",
+      "model.layers.58.self_attn.indexers_proj",
+      "model.layers.58.self_attn.kv_a_layernorm",
+      "model.layers.58.self_attn.q_a_layernorm",
+      "model.layers.59.input_layernorm",
+      "model.layers.59.mlp.gate",
+      "model.layers.59.mlp.gate.e_score_correction_bias",
+      "model.layers.59.post_attention_layernorm",
+      "model.layers.59.self_attn.indexer.k_norm",
+      "model.layers.59.self_attn.indexer.k_norm.bias",
+      "model.layers.59.self_attn.indexers_proj",
+      "model.layers.59.self_attn.kv_a_layernorm",
+      "model.layers.59.self_attn.q_a_layernorm",
+      "model.layers.60.input_layernorm",
+      "model.layers.60.mlp.gate",
+      "model.layers.60.mlp.gate.e_score_correction_bias",
+      "model.layers.60.post_attention_layernorm",
+      "model.layers.60.self_attn.indexer.k_norm",
+      "model.layers.60.self_attn.indexer.k_norm.bias",
+      "model.layers.60.self_attn.indexers_proj",
+      "model.layers.60.self_attn.kv_a_layernorm",
+      "model.layers.60.self_attn.q_a_layernorm",
+      "model.layers.61.input_layernorm",
+      "model.layers.61.mlp.gate",
+      "model.layers.61.mlp.gate.e_score_correction_bias",
+      "model.layers.61.post_attention_layernorm",
+      "model.layers.61.self_attn.indexer.k_norm",
+      "model.layers.61.self_attn.indexer.k_norm.bias",
+      "model.layers.61.self_attn.indexers_proj",
+      "model.layers.61.self_attn.kv_a_layernorm",
+      "model.layers.61.self_attn.q_a_layernorm",
+      "model.layers.62.input_layernorm",
+      "model.layers.62.mlp.gate",
+      "model.layers.62.mlp.gate.e_score_correction_bias",
+      "model.layers.62.post_attention_layernorm",
+      "model.layers.62.self_attn.indexer.k_norm",
+      "model.layers.62.self_attn.indexer.k_norm.bias",
+      "model.layers.62.self_attn.indexers_proj",
+      "model.layers.62.self_attn.kv_a_layernorm",
+      "model.layers.62.self_attn.q_a_layernorm",
+      "model.layers.63.input_layernorm",
+      "model.layers.63.mlp.gate",
+      "model.layers.63.mlp.gate.e_score_correction_bias",
+      "model.layers.63.post_attention_layernorm",
+      "model.layers.63.self_attn.indexer.k_norm",
+      "model.layers.63.self_attn.indexer.k_norm.bias",
+      "model.layers.63.self_attn.indexers_proj",
+      "model.layers.63.self_attn.kv_a_layernorm",
+      "model.layers.63.self_attn.q_a_layernorm",
+      "model.layers.64.input_layernorm",
+      "model.layers.64.mlp.gate",
+      "model.layers.64.mlp.gate.e_score_correction_bias",
+      "model.layers.64.post_attention_layernorm",
+      "model.layers.64.self_attn.indexer.k_norm",
+      "model.layers.64.self_attn.indexer.k_norm.bias",
+      "model.layers.64.self_attn.indexers_proj",
+      "model.layers.64.self_attn.kv_a_layernorm",
+      "model.layers.64.self_attn.q_a_layernorm",
+      "model.layers.65.input_layernorm",
+      "model.layers.65.mlp.gate",
+      "model.layers.65.mlp.gate.e_score_correction_bias",
+      "model.layers.65.post_attention_layernorm",
+      "model.layers.65.self_attn.indexer.k_norm",
+      "model.layers.65.self_attn.indexer.k_norm.bias",
+      "model.layers.65.self_attn.indexers_proj",
+      "model.layers.65.self_attn.kv_a_layernorm",
+      "model.layers.65.self_attn.q_a_layernorm",
+      "model.layers.66.input_layernorm",
+      "model.layers.66.mlp.gate",
+      "model.layers.66.mlp.gate.e_score_correction_bias",
+      "model.layers.66.post_attention_layernorm",
+      "model.layers.66.self_attn.indexer.k_norm",
+      "model.layers.66.self_attn.indexer.k_norm.bias",
+      "model.layers.66.self_attn.indexers_proj",
+      "model.layers.66.self_attn.kv_a_layernorm",
+      "model.layers.66.self_attn.q_a_layernorm",
+      "model.layers.67.input_layernorm",
+      "model.layers.67.mlp.gate",
+      "model.layers.67.mlp.gate.e_score_correction_bias",
+      "model.layers.67.post_attention_layernorm",
+      "model.layers.67.self_attn.indexer.k_norm",
+      "model.layers.67.self_attn.indexer.k_norm.bias",
+      "model.layers.67.self_attn.indexers_proj",
+      "model.layers.67.self_attn.kv_a_layernorm",
+      "model.layers.67.self_attn.q_a_layernorm",
+      "model.layers.68.input_layernorm",
+      "model.layers.68.mlp.gate",
+      "model.layers.68.mlp.gate.e_score_correction_bias",
+      "model.layers.68.post_attention_layernorm",
+      "model.layers.68.self_attn.indexer.k_norm",
+      "model.layers.68.self_attn.indexer.k_norm.bias",
+      "model.layers.68.self_attn.indexers_proj",
+      "model.layers.68.self_attn.kv_a_layernorm",
+      "model.layers.68.self_attn.q_a_layernorm",
+      "model.layers.69.input_layernorm",
+      "model.layers.69.mlp.gate",
+      "model.layers.69.mlp.gate.e_score_correction_bias",
+      "model.layers.69.post_attention_layernorm",
+      "model.layers.69.self_attn.indexer.k_norm",
+      "model.layers.69.self_attn.indexer.k_norm.bias",
+      "model.layers.69.self_attn.indexers_proj",
+      "model.layers.69.self_attn.kv_a_layernorm",
+      "model.layers.69.self_attn.q_a_layernorm",
+      "model.layers.70.input_layernorm",
+      "model.layers.70.mlp.gate",
+      "model.layers.70.mlp.gate.e_score_correction_bias",
+      "model.layers.70.post_attention_layernorm",
+      "model.layers.70.self_attn.indexer.k_norm",
+      "model.layers.70.self_attn.indexer.k_norm.bias",
+      "model.layers.70.self_attn.indexers_proj",
+      "model.layers.70.self_attn.kv_a_layernorm",
+      "model.layers.70.self_attn.q_a_layernorm",
+      "model.layers.71.input_layernorm",
+      "model.layers.71.mlp.gate",
+      "model.layers.71.mlp.gate.e_score_correction_bias",
+      "model.layers.71.post_attention_layernorm",
+      "model.layers.71.self_attn.indexer.k_norm",
+      "model.layers.71.self_attn.indexer.k_norm.bias",
+      "model.layers.71.self_attn.indexers_proj",
+      "model.layers.71.self_attn.kv_a_layernorm",
+      "model.layers.71.self_attn.q_a_layernorm",
+      "model.layers.72.input_layernorm",
+      "model.layers.72.mlp.gate",
+      "model.layers.72.mlp.gate.e_score_correction_bias",
+      "model.layers.72.post_attention_layernorm",
+      "model.layers.72.self_attn.indexer.k_norm",
+      "model.layers.72.self_attn.indexer.k_norm.bias",
+      "model.layers.72.self_attn.indexers_proj",
+      "model.layers.72.self_attn.kv_a_layernorm",
+      "model.layers.72.self_attn.q_a_layernorm",
+      "model.layers.73.input_layernorm",
+      "model.layers.73.mlp.gate",
+      "model.layers.73.mlp.gate.e_score_correction_bias",
+      "model.layers.73.post_attention_layernorm",
+      "model.layers.73.self_attn.indexer.k_norm",
+      "model.layers.73.self_attn.indexer.k_norm.bias",
+      "model.layers.73.self_attn.indexers_proj",
+      "model.layers.73.self_attn.kv_a_layernorm",
+      "model.layers.73.self_attn.q_a_layernorm",
+      "model.layers.74.input_layernorm",
+      "model.layers.74.mlp.gate",
+      "model.layers.74.mlp.gate.e_score_correction_bias",
+      "model.layers.74.post_attention_layernorm",
+      "model.layers.74.self_attn.indexer.k_norm",
+      "model.layers.74.self_attn.indexer.k_norm.bias",
+      "model.layers.74.self_attn.indexers_proj",
+      "model.layers.74.self_attn.kv_a_layernorm",
+      "model.layers.74.self_attn.q_a_layernorm",
+      "model.layers.75.input_layernorm",
+      "model.layers.75.mlp.gate",
+      "model.layers.75.mlp.gate.e_score_correction_bias",
+      "model.layers.75.post_attention_layernorm",
+      "model.layers.75.self_attn.indexer.k_norm",
+      "model.layers.75.self_attn.indexer.k_norm.bias",
+      "model.layers.75.self_attn.indexers_proj",
+      "model.layers.75.self_attn.kv_a_layernorm",
+      "model.layers.75.self_attn.q_a_layernorm",
+      "model.layers.76.input_layernorm",
+      "model.layers.76.mlp.gate",
+      "model.layers.76.mlp.gate.e_score_correction_bias",
+      "model.layers.76.post_attention_layernorm",
+      "model.layers.76.self_attn.indexer.k_norm",
+      "model.layers.76.self_attn.indexer.k_norm.bias",
+      "model.layers.76.self_attn.indexers_proj",
+      "model.layers.76.self_attn.kv_a_layernorm",
+      "model.layers.76.self_attn.q_a_layernorm",
+      "model.layers.77.input_layernorm",
+      "model.layers.77.mlp.gate",
+      "model.layers.77.mlp.gate.e_score_correction_bias",
+      "model.layers.77.post_attention_layernorm",
+      "model.layers.77.self_attn.indexer.k_norm",
+      "model.layers.77.self_attn.indexer.k_norm.bias",
+      "model.layers.77.self_attn.indexers_proj",
+      "model.layers.77.self_attn.kv_a_layernorm",
+      "model.layers.77.self_attn.q_a_layernorm",
+      "model.layers.78.eh_proj",
+      "model.layers.78.enorm",
+      "model.layers.78.hnorm",
+      "model.layers.78.input_layernorm",
+      "model.layers.78.mlp.gate",
+      "model.layers.78.mlp.gate.e_score_correction_bias",
+      "model.layers.78.post_attention_layernorm",
+      "model.layers.78.self_attn.indexer.k_norm",
+      "model.layers.78.self_attn.indexer.k_norm.bias",
+      "model.layers.78.self_attn.indexers_proj",
+      "model.layers.78.self_attn.kv_a_layernorm",
+      "model.layers.78.self_attn.q_a_layernorm",
+      "model.layers.78.shared_head.norm",
+      "model.norm"
+    ]
+  }
+}

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": "5.0.2.dev0"
+}

model-00001-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75e4dc9f7b1e345170f5cd3c47c764dfe631d7895008f5efdc82b2dde92de4c
+size 5363940952

model-00002-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a17170e28d81d697955ae340c0927b648e8e1f6b06a6ae8051f286c8f74f725
+size 5361736696

model-00003-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1370f0035979329b828d21b11369784f52dcdb19bf0268ad934c18f79c0f44c6
+size 5363339120

model-00004-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e72700bd7b0f1bf6fd96ee23f8b8895a8d00ac9b8b9c11446f297d82c91015a4
+size 5361736640

model-00005-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e518a59a00bc1ec97d36f19734e21152e6a9faeb193d98e1278356be40101cc9
+size 5363339176

model-00006-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d37be93a5270cf8f7e4c20e5a733a31aff2bd83bc9656e9b3d7dc1b9a2d5926
+size 5361736504

model-00007-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f096b79ea10167b5e9fc66e99f0654c684893009cef9342ed72a363631b552d
+size 5363339304

model-00008-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cdaf4f718d51bd65c5cc812cce5fd116742ba34904925b2251fe92e380a3ab
+size 5361736368

model-00009-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a294efbbf5c7f0eca60797c7a6902045d84896371cc5815ca431ce52afcc567
+size 5363339440

model-00010-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390eaf7f2c80d1ac017521f4a5113677abfed056753d05c451a7c2a546384998
+size 5361736232

model-00011-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0dcfd2ac425ac53d1f8496738a1d589abf751ed417f8208bc806ec64e2ebc2
+size 5363339592

model-00012-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3162c33985af89993a70da3530ff552c4885e569f8ca06e84b3bead004488a8
+size 5363339104

model-00013-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d1702e2f1958d30eafb81c69f0abf0989c3d8bc82b752793a246c6cc60aa1c
+size 5361736696

model-00014-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81603c43fd54122915e648c6760efb06b2074ddf979220702f0a408776a8749f
+size 5363339120

model-00015-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a9a7e63e77ebefad25c210f3448528febd9233c66764e772fa0d87673f35ba1
+size 5361736688

model-00016-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc5f3e9862db94d54895ed4f147fb71a0508c61b947ba4fc2a6ee664a30e5f4
+size 5363339176

model-00017-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b15acba1b715f59fd5faff35837c873a5c2ba3cbd18f761e230cd0162305a34
+size 5361736552

model-00018-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52507d77cd4eadb12479d79acb5d860fa782de2ddc244d11f9e5a80a63127750
+size 5363339256

model-00019-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cb5e9b3ca010298d6449f011dc04db5c66c70bac463dce08d63a8d60654858
+size 5361736416

model-00020-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b9acd03945bbf30331843a692e68e0ac009355471a5b2c3d887a51d79d5f08
+size 5361791448

model-00021-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d4fcf67f0abda1ac39e21cdf4d004f90109a33ee456ce39e53ea744c2c2fd1
+size 5361736352

model-00022-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7329ef4f994a7ac22901e465f943665708ad88236e630cae0532cf75ee4cc474
+size 5363339456

model-00023-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d546f87e34309770629fdac04b16e16fee4abe435b9613feb1236ec95a0380fc
+size 5361736224

model-00024-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b755e74f642cb8ec7627f50414a6efe617485200f29acb65b340c78a603a79
+size 5363339608

model-00025-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7c7a8ac34e62424109fdc5d58bd5667adae8dcc8bf80254142ca14113f575d
+size 5363339104

model-00026-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d098486d2b0fe98046868dfc5c052f752768df47571eb250c8629e99a90f4b
+size 5361736696

model-00027-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15dfa9511f0446684a5afc4a7afff701a2c03c72ff16750c61e6d11f19e63f22
+size 5363339112

model-00028-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3d1c850ccb27716365a4e7a6078f7a589d2b94b780f0fd7f6ac5222d75402d
+size 5361736664

model-00029-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b061a3c1f07728dedc62e70e1382882c6f28c9d4c3657e68c7edb1f9d8b3c7a9
+size 5363339152

model-00030-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2de093fc6246082803e35e0d9f4a44f674a3182157df6afa1616aa1981ddc8d
+size 5361736528

model-00031-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f45b0fbdcec9210e20e21d83d85c916f4c7a8f82589950960b17b0ea882eb6
+size 5363339280

model-00032-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5107083d264ed50fa120c4a527c80c61c79406918b16200a9db23bb5ff798c6d
+size 5361736392

model-00033-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd86b5c670b8f1cf16a69e25e96ff9f09cc495eb7978ada4ac8eb14729f4586
+size 5363339416

model-00034-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d39453d8ca90f5e38e0d51a95fd585766ad95488fb79d9f5d651bbcfe765bd
+size 5361736264

model-00035-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d557ec5601653b8be2bb8ed3121159b368a53e6c6e27a7a901f2be859a3e32
+size 5363339544

model-00036-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e162b3ad7bb627cd8984e41a62d049f070321b4b30ee7deb335f88a9ab93de9
+size 5363339104

model-00037-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f980f59d1f5bc3dd9a717824b652045da1ea20b32aee9593811453e97d75c64
+size 5361736696

model-00038-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74963234bf95c73eb5d2fcfefb91e266b8174d3bef480f1080dd7548f3e43110
+size 5363338920

model-00039-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e10c68987f919c926469f7adb27d7279989dac736bb7115e9d8f19f9e7d15b
+size 5361735840

model-00040-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea19f319667a7ff62aea9182eb39e676c44a1b2792464ede0dff578ca255030
+size 5363338584

model-00041-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff662658a03396680e04029d8d2fd8963505a3731d8abbaa3112fccaa75c7af7
+size 5361736576

model-00042-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fdeae54c5306335c557fe56a2d4065fe7f8bcbe38f89751b98584490f88900
+size 5363339232

model-00043-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53dba89973165ece2063a47af49ffddbd92393728164eec82e522d99f360dbe9
+size 5361736440

model-00044-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d2aa1c3abc6c15bdc46c0a675729715add84dd7d9218165618a728ad6a3e5dc
+size 5363339368

model-00045-of-00142.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ae817d687bd28da6f341031825cb8f36bb1c84998ce1d86844115f1b7c0ea3
+size 5361736312