Upload folder using huggingface_hub

.gitattributes

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

chat_template.jinja

@@ -0,0 +1,255 @@
+[gMASK]<sop>
+{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}
+{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
+{%- set clear_thinking = clear_thinking if clear_thinking is defined else false -%}
+{%- if tools -%}
+{%- macro tool_to_json(tool) -%}
+    {%- set ns_tool = namespace(first=true) -%}
+    {{ '{' -}}
+    {%- for k, v in tool.items() -%}
+        {%- if k != 'defer_loading' and k != 'strict' -%}
+            {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
+            {%- set ns_tool.first = false -%}
+            "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- endmacro -%}
+{%- macro tool_references_to_response(refs) -%}
+    {{- '<tool_response><tools>\n' -}}
+    {%- for tr in refs -%}
+        {%- for tool in tools -%}
+            {%- if 'function' in tool -%}
+                {%- set tool = tool['function'] -%}
+            {%- endif -%}
+            {%- if tool.name == tr.name -%}
+                {{- tool_to_json(tool) + '\n' -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endfor -%}
+    {{- '</tools></tool_response>' -}}
+{%- endmacro -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{%- if 'function' in tool -%}
+    {%- set tool = tool['function'] -%}
+{%- endif -%}
+{% if tool.defer_loading is not defined or not tool.defer_loading %}
+{{ tool_to_json(tool) }}
+{% endif %}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
+{%- macro 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 -%}
+    {%- elif content is not none -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro tool_response(text) -%}
+{{- '<tool_response>' + text + '</tool_response>' -}}
+{%- endmacro -%}
+{%- macro render_tool_response(m) -%}
+{%- if m.content is string -%}
+    {{- tool_response(m.content) -}}
+{%- elif m.content and m.content is not mapping and m.content.0.type == "tool_reference" -%}
+    {{- tool_references_to_response(m.content) -}}
+{%- elif is_list_of_outputs(m) -%}
+    {%- for tr in m.content -%}
+        {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == "tool_reference" -%}
+            {{- tool_references_to_response(tr.output) -}}
+        {%- else -%}
+            {{- tool_response(visible_text(tr.output)) -}}
+        {%- endif -%}
+    {%- endfor -%}
+{%- else -%}
+    {{- tool_response(visible_text(m.content)) -}}
+{%- endif -%}
+{%- endmacro -%}
+{%- macro id_of(obj) -%}
+    {%- if obj.tool_call_id -%}
+        {{- obj.tool_call_id -}}
+    {%- elif obj.id -%}
+        {{- obj.id -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro is_list_of_outputs(m) -%}
+    {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}
+{%- endmacro -%}
+{%- macro has_dup_tool_result_id(lo, hi, target) -%}
+    {%- set ns_cnt = namespace(n=0) -%}
+    {%- for k in range(lo, hi + 1) -%}
+        {%- set m = messages[k] -%}
+        {%- if is_list_of_outputs(m) -%}
+            {%- for entry in m.content -%}
+                {%- if id_of(entry) == target -%}
+                    {%- set ns_cnt.n = ns_cnt.n + 1 -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- elif id_of(m) == target -%}
+            {%- set ns_cnt.n = ns_cnt.n + 1 -%}
+        {%- endif -%}
+        {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}
+    {%- endfor -%}
+    {%- if ns_cnt.n > 1 -%}1{%- endif -%}
+{%- endmacro -%}
+{%- macro tc_id_exists(tcs, target) -%}
+    {%- set ns_f = namespace(found=false) -%}
+    {%- for tc in tcs -%}
+        {%- if id_of(tc) == target -%}
+            {%- set ns_f.found = true -%}
+            {%- break -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- if ns_f.found -%}1{%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) -%}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{%- for m in messages -%}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- elif '</think>' in content %}
+    {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
+    {%- set content = content.split('</think>')[-1] %}
+{%- endif %}
+{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
+{{ '<think>' + reasoning_content +  '</think>'}}
+{%- else -%}
+{{ '<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' -}}
+    {%- set block_start = loop.index0 -%}
+    {%- set ns_blk = namespace(end=block_start) -%}
+    {%- for j in range(block_start, messages|length) -%}
+        {%- if messages[j].role == 'tool' -%}
+            {%- set ns_blk.end = j -%}
+        {%- else -%}
+            {%- break -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns_a = namespace(tool_calls=none) -%}
+    {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}
+        {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}
+    {%- endif -%}
+    {%- set ns_chk = namespace(can_sort=true) -%}
+    {%- if not ns_a.tool_calls -%}
+        {%- set ns_chk.can_sort = false -%}
+    {%- else -%}
+        {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {%- if not ns_chk.can_sort -%}{%- break -%}{%- endif -%}
+            {%- set m = messages[k] -%}
+            {%- if is_list_of_outputs(m) -%}
+                {%- for entry in m.content -%}
+                    {%- if not ns_chk.can_sort -%}{%- break -%}{%- endif -%}
+                    {%- set eid = id_of(entry) -%}
+                    {%- if not eid -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {%- set tk_id = id_of(m) -%}
+                {%- if not tk_id -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- for i in range(ns_a.tool_calls | length) -%}
+            {%- if not ns_chk.can_sort -%}{%- break -%}{%- endif -%}
+            {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}
+            {%- if not tc_id -%}
+                {%- set ns_chk.can_sort = false -%}
+            {%- endif -%}
+            {%- for j in range(i + 1, ns_a.tool_calls | length) -%}
+                {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}
+                    {%- set ns_chk.can_sort = false -%}
+                    {%- break -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- if ns_chk.can_sort -%}
+        {%- for tc in ns_a.tool_calls -%}
+            {%- set tc_id = id_of(tc) -%}
+            {%- for k in range(block_start, ns_blk.end + 1) -%}
+                {%- set m = messages[k] -%}
+                {%- if is_list_of_outputs(m) -%}
+                    {%- for entry in m.content -%}
+                        {%- set eid = id_of(entry) -%}
+                        {%- if eid == tc_id -%}
+                            {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == "tool_reference" -%}
+                                {{- tool_references_to_response(entry.output) -}}
+                            {%- else -%}
+                                {{- tool_response(visible_text(entry.output)) -}}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                {%- else -%}
+                    {%- set tk_id = id_of(m) -%}
+                    {%- if tk_id == tc_id -%}
+                        {{- render_tool_response(m) -}}
+                    {%- endif -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endfor -%}
+    {%- else -%}
+        {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {{- render_tool_response(messages[k]) -}}
+        {%- endfor -%}
+    {%- endif -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,776 @@
+{
+ "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,
+ "moe_router_dtype": "float32",
+ "n_group": 1,
+ "n_routed_experts": 168,
+ "n_shared_experts": 1,
+ "norm_topk_prob": true,
+ "num_attention_heads": 64,
+ "num_experts_per_tok": 8,
+ "num_hidden_layers": 78,
+ "num_key_value_heads": 64,
+ "num_nextn_predict_layers": 1,
+ "pad_token_id": 154820,
+ "pretraining_tp": 1,
+ "q_lora_rank": 2048,
+ "qk_head_dim": 256,
+ "qk_nope_head_dim": 192,
+ "qk_rope_head_dim": 64,
+ "rms_norm_eps": 1e-05,
+ "rope_interleave": true,
+ "rope_parameters": {
+  "rope_theta": 8000000,
+  "rope_type": "default"
+ },
+ "routed_scaling_factor": 2.5,
+ "scoring_func": "sigmoid",
+ "tie_word_embeddings": false,
+ "topk_group": 1,
+ "topk_method": "noaux_tc",
+ "transformers_version": "5.15.0",
+ "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": [
+   "model.layers.59.post_attention_layernorm",
+   "model.layers.47.mlp.gate.e_score_correction_bias",
+   "model.layers.71.self_attn.kv_a_layernorm",
+   "model.layers.46.mlp.gate.e_score_correction_bias",
+   "model.layers.30.self_attn.kv_a_layernorm",
+   "model.layers.23.self_attn.kv_a_layernorm",
+   "model.layers.73.mlp.gate.e_score_correction_bias",
+   "model.layers.36.mlp.gate",
+   "model.layers.12.self_attn.q_a_layernorm",
+   "model.layers.51.mlp.gate",
+   "model.layers.47.self_attn.kv_a_layernorm",
+   "model.layers.45.self_attn.q_a_layernorm",
+   "model.layers.15.self_attn.q_a_layernorm",
+   "model.layers.39.input_layernorm",
+   "model.layers.50.self_attn.kv_a_layernorm",
+   "model.layers.19.post_attention_layernorm",
+   "model.layers.71.input_layernorm",
+   "model.layers.72.self_attn.kv_a_layernorm",
+   "model.layers.70.mlp.gate",
+   "model.layers.52.input_layernorm",
+   "model.layers.78.self_attn.kv_a_layernorm",
+   "model.layers.48.post_attention_layernorm",
+   "model.layers.4.self_attn.q_a_layernorm",
+   "model.layers.62.self_attn.q_a_layernorm",
+   "model.layers.4.post_attention_layernorm",
+   "model.layers.38.self_attn.indexers_proj",
+   "model.layers.61.mlp.gate.e_score_correction_bias",
+   "model.layers.14.mlp.gate.e_score_correction_bias",
+   "model.layers.36.self_attn.kv_a_layernorm",
+   "model.layers.65.mlp.gate",
+   "model.layers.13.self_attn.kv_a_layernorm",
+   "model.layers.57.mlp.gate",
+   "model.layers.65.self_attn.kv_a_layernorm",
+   "model.layers.68.input_layernorm",
+   "model.layers.70.self_attn.kv_a_layernorm",
+   "model.layers.24.mlp.gate.e_score_correction_bias",
+   "model.layers.4.input_layernorm",
+   "model.layers.20.input_layernorm",
+   "model.layers.65.self_attn.q_a_layernorm",
+   "model.layers.38.mlp.gate",
+   "model.layers.76.mlp.gate.e_score_correction_bias",
+   "model.layers.62.input_layernorm",
+   "model.layers.45.input_layernorm",
+   "model.layers.68.post_attention_layernorm",
+   "model.layers.72.input_layernorm",
+   "model.layers.32.mlp.gate.e_score_correction_bias",
+   "model.layers.27.input_layernorm",
+   "model.layers.16.post_attention_layernorm",
+   "model.layers.35.self_attn.q_a_layernorm",
+   "model.layers.58.self_attn.indexers_proj",
+   "model.layers.3.mlp.gate.e_score_correction_bias",
+   "model.layers.49.self_attn.q_a_layernorm",
+   "model.layers.66.mlp.gate.e_score_correction_bias",
+   "model.layers.10.self_attn.q_a_layernorm",
+   "model.layers.51.mlp.gate.e_score_correction_bias",
+   "model.layers.64.self_attn.q_a_layernorm",
+   "model.layers.70.input_layernorm",
+   "model.layers.71.post_attention_layernorm",
+   "model.layers.67.post_attention_layernorm",
+   "model.layers.6.self_attn.indexer.k_norm",
+   "model.layers.3.mlp.gate",
+   "model.layers.11.mlp.gate",
+   "model.layers.17.input_layernorm",
+   "model.layers.13.mlp.gate",
+   "model.layers.15.mlp.gate",
+   "model.layers.71.self_attn.q_a_layernorm",
+   "model.layers.33.mlp.gate.e_score_correction_bias",
+   "model.layers.72.mlp.gate.e_score_correction_bias",
+   "model.layers.65.post_attention_layernorm",
+   "model.layers.78.hnorm",
+   "model.layers.40.post_attention_layernorm",
+   "model.layers.12.mlp.gate.e_score_correction_bias",
+   "model.layers.8.input_layernorm",
+   "model.layers.73.mlp.gate",
+   "model.layers.11.post_attention_layernorm",
+   "model.layers.61.input_layernorm",
+   "model.layers.14.self_attn.kv_a_layernorm",
+   "model.layers.39.self_attn.kv_a_layernorm",
+   "model.layers.70.self_attn.indexer.k_norm",
+   "model.layers.45.mlp.gate",
+   "model.layers.51.self_attn.q_a_layernorm",
+   "model.layers.64.post_attention_layernorm",
+   "model.layers.20.post_attention_layernorm",
+   "model.layers.66.self_attn.kv_a_layernorm",
+   "model.layers.10.self_attn.indexer.k_norm.bias",
+   "model.layers.23.input_layernorm",
+   "model.layers.38.self_attn.indexer.k_norm",
+   "model.layers.19.self_attn.kv_a_layernorm",
+   "model.layers.40.self_attn.q_a_layernorm",
+   "model.layers.10.self_attn.indexer.k_norm",
+   "model.layers.44.post_attention_layernorm",
+   "model.layers.70.post_attention_layernorm",
+   "model.layers.41.mlp.gate.e_score_correction_bias",
+   "model.layers.36.post_attention_layernorm",
+   "model.layers.30.self_attn.indexer.k_norm.bias",
+   "model.layers.54.self_attn.q_a_layernorm",
+   "model.layers.59.mlp.gate",
+   "model.layers.69.post_attention_layernorm",
+   "lm_head",
+   "model.layers.77.self_attn.kv_a_layernorm",
+   "model.layers.75.self_attn.q_a_layernorm",
+   "model.layers.56.self_attn.q_a_layernorm",
+   "model.layers.50.self_attn.indexer.k_norm.bias",
+   "model.layers.54.mlp.gate",
+   "model.layers.6.self_attn.indexer.k_norm.bias",
+   "model.layers.15.input_layernorm",
+   "model.layers.29.self_attn.q_a_layernorm",
+   "model.layers.54.self_attn.indexers_proj",
+   "model.layers.73.self_attn.kv_a_layernorm",
+   "model.layers.0.self_attn.indexer.k_norm",
+   "model.layers.58.self_attn.indexer.k_norm",
+   "model.layers.36.input_layernorm",
+   "model.layers.47.self_attn.q_a_layernorm",
+   "model.layers.26.mlp.gate.e_score_correction_bias",
+   "model.layers.50.input_layernorm",
+   "model.layers.16.self_attn.q_a_layernorm",
+   "model.layers.19.mlp.gate.e_score_correction_bias",
+   "model.layers.78.input_layernorm",
+   "model.layers.27.mlp.gate",
+   "model.layers.19.self_attn.q_a_layernorm",
+   "model.layers.25.input_layernorm",
+   "model.layers.33.self_attn.kv_a_layernorm",
+   "model.layers.32.mlp.gate",
+   "model.layers.61.self_attn.kv_a_layernorm",
+   "model.layers.50.self_attn.indexers_proj",
+   "model.layers.34.self_attn.indexers_proj",
+   "model.layers.4.mlp.gate.e_score_correction_bias",
+   "model.layers.76.post_attention_layernorm",
+   "model.layers.57.post_attention_layernorm",
+   "model.layers.73.post_attention_layernorm",
+   "model.layers.68.mlp.gate.e_score_correction_bias",
+   "model.layers.34.self_attn.kv_a_layernorm",
+   "model.layers.78.enorm",
+   "model.layers.30.mlp.gate",
+   "model.layers.10.self_attn.indexers_proj",
+   "model.layers.34.input_layernorm",
+   "model.layers.34.post_attention_layernorm",
+   "model.layers.20.mlp.gate.e_score_correction_bias",
+   "model.layers.54.self_attn.indexer.k_norm.bias",
+   "model.layers.44.mlp.gate",
+   "model.layers.25.mlp.gate.e_score_correction_bias",
+   "model.layers.26.self_attn.indexers_proj",
+   "model.layers.66.self_attn.indexer.k_norm.bias",
+   "model.layers.41.post_attention_layernorm",
+   "model.layers.51.post_attention_layernorm",
+   "model.layers.22.self_attn.indexer.k_norm.bias",
+   "model.layers.21.mlp.gate.e_score_correction_bias",
+   "model.layers.15.self_attn.kv_a_layernorm",
+   "model.layers.25.self_attn.kv_a_layernorm",
+   "model.layers.55.mlp.gate",
+   "model.layers.11.self_attn.q_a_layernorm",
+   "model.layers.72.mlp.gate",
+   "model.layers.21.self_attn.kv_a_layernorm",
+   "model.layers.59.mlp.gate.e_score_correction_bias",
+   "model.layers.2.input_layernorm",
+   "model.layers.5.mlp.gate",
+   "model.layers.54.self_attn.kv_a_layernorm",
+   "model.layers.0.self_attn.indexers_proj",
+   "model.layers.71.mlp.gate.e_score_correction_bias",
+   "model.layers.6.self_attn.q_a_layernorm",
+   "model.layers.14.mlp.gate",
+   "model.layers.44.self_attn.kv_a_layernorm",
+   "model.layers.61.post_attention_layernorm",
+   "model.layers.64.self_attn.kv_a_layernorm",
+   "model.layers.1.post_attention_layernorm",
+   "model.layers.4.mlp.gate",
+   "model.layers.22.post_attention_layernorm",
+   "model.layers.21.self_attn.q_a_layernorm",
+   "model.layers.74.self_attn.q_a_layernorm",
+   "model.layers.18.self_attn.indexers_proj",
+   "model.layers.75.input_layernorm",
+   "model.layers.70.self_attn.q_a_layernorm",
+   "model.layers.22.self_attn.indexer.k_norm",
+   "model.layers.42.mlp.gate.e_score_correction_bias",
+   "model.layers.5.self_attn.kv_a_layernorm",
+   "model.layers.31.mlp.gate.e_score_correction_bias",
+   "model.layers.62.self_attn.indexer.k_norm.bias",
+   "model.layers.29.post_attention_layernorm",
+   "model.layers.6.self_attn.kv_a_layernorm",
+   "model.layers.48.input_layernorm",
+   "model.layers.74.self_attn.indexer.k_norm.bias",
+   "model.layers.7.input_layernorm",
+   "model.layers.39.self_attn.q_a_layernorm",
+   "model.layers.41.input_layernorm",
+   "model.layers.54.self_attn.indexer.k_norm",
+   "model.layers.32.self_attn.q_a_layernorm",
+   "model.layers.39.mlp.gate.e_score_correction_bias",
+   "model.layers.42.input_layernorm",
+   "model.layers.43.mlp.gate",
+   "model.layers.72.self_attn.q_a_layernorm",
+   "model.layers.37.mlp.gate.e_score_correction_bias",
+   "model.layers.5.post_attention_layernorm",
+   "model.layers.28.mlp.gate",
+   "model.layers.2.post_attention_layernorm",
+   "model.layers.49.post_attention_layernorm",
+   "model.layers.43.self_attn.kv_a_layernorm",
+   "model.layers.12.input_layernorm",
+   "model.layers.56.mlp.gate",
+   "model.layers.5.input_layernorm",
+   "model.layers.29.mlp.gate.e_score_correction_bias",
+   "model.layers.4.self_attn.kv_a_layernorm",
+   "model.layers.20.self_attn.q_a_layernorm",
+   "model.layers.59.self_attn.q_a_layernorm",
+   "model.layers.68.mlp.gate",
+   "model.layers.21.post_attention_layernorm",
+   "model.layers.26.self_attn.q_a_layernorm",
+   "model.layers.52.self_attn.q_a_layernorm",
+   "model.layers.29.self_attn.kv_a_layernorm",
+   "model.layers.24.input_layernorm",
+   "model.layers.34.self_attn.indexer.k_norm.bias",
+   "model.layers.43.input_layernorm",
+   "model.layers.27.self_attn.kv_a_layernorm",
+   "model.layers.31.input_layernorm",
+   "model.layers.69.mlp.gate",
+   "model.layers.26.post_attention_layernorm",
+   "model.layers.3.self_attn.q_a_layernorm",
+   "model.layers.37.post_attention_layernorm",
+   "model.layers.52.mlp.gate",
+   "model.layers.73.input_layernorm",
+   "model.layers.19.input_layernorm",
+   "model.layers.13.self_attn.q_a_layernorm",
+   "model.layers.76.input_layernorm",
+   "model.layers.8.mlp.gate",
+   "model.layers.63.post_attention_layernorm",
+   "model.layers.58.mlp.gate",
+   "model.layers.31.post_attention_layernorm",
+   "model.layers.23.mlp.gate.e_score_correction_bias",
+   "model.layers.34.self_attn.q_a_layernorm",
+   "model.layers.78.self_attn.indexer.k_norm.bias",
+   "model.layers.13.mlp.gate.e_score_correction_bias",
+   "model.layers.71.mlp.gate",
+   "model.layers.14.input_layernorm",
+   "model.layers.17.mlp.gate.e_score_correction_bias",
+   "model.layers.8.post_attention_layernorm",
+   "model.layers.45.self_attn.kv_a_layernorm",
+   "model.layers.46.self_attn.indexer.k_norm",
+   "model.layers.20.self_attn.kv_a_layernorm",
+   "model.layers.78.self_attn.indexer.k_norm",
+   "model.layers.37.mlp.gate",
+   "model.layers.7.mlp.gate",
+   "model.layers.30.mlp.gate.e_score_correction_bias",
+   "model.layers.67.mlp.gate",
+   "model.layers.73.self_attn.q_a_layernorm",
+   "model.layers.10.self_attn.kv_a_layernorm",
+   "model.layers.61.mlp.gate",
+   "model.layers.22.mlp.gate.e_score_correction_bias",
+   "model.layers.58.input_layernorm",
+   "model.layers.8.self_attn.kv_a_layernorm",
+   "model.layers.33.self_attn.q_a_layernorm",
+   "model.layers.55.self_attn.q_a_layernorm",
+   "model.layers.32.input_layernorm",
+   "model.layers.17.self_attn.kv_a_layernorm",
+   "model.layers.46.self_attn.indexer.k_norm.bias",
+   "model.layers.11.mlp.gate.e_score_correction_bias",
+   "model.layers.9.input_layernorm",
+   "model.layers.77.input_layernorm",
+   "model.layers.16.self_attn.kv_a_layernorm",
+   "model.layers.45.post_attention_layernorm",
+   "model.layers.74.mlp.gate",
+   "model.layers.68.self_attn.q_a_layernorm",
+   "model.layers.55.self_attn.kv_a_layernorm",
+   "model.layers.44.input_layernorm",
+   "model.layers.60.self_attn.kv_a_layernorm",
+   "model.layers.14.post_attention_layernorm",
+   "model.layers.62.self_attn.indexers_proj",
+   "model.layers.0.self_attn.q_a_layernorm",
+   "model.layers.72.post_attention_layernorm",
+   "model.layers.78.post_attention_layernorm",
+   "model.layers.60.mlp.gate.e_score_correction_bias",
+   "model.layers.26.self_attn.indexer.k_norm.bias",
+   "model.layers.38.post_attention_layernorm",
+   "model.layers.50.post_attention_layernorm",
+   "model.layers.28.input_layernorm",
+   "model.layers.30.self_attn.indexer.k_norm",
+   "model.layers.37.self_attn.q_a_layernorm",
+   "model.layers.56.input_layernorm",
+   "model.layers.27.post_attention_layernorm",
+   "model.layers.74.input_layernorm",
+   "model.layers.78.self_attn.q_a_layernorm",
+   "model.layers.42.self_attn.q_a_layernorm",
+   "model.layers.26.self_attn.indexer.k_norm",
+   "model.layers.42.self_attn.kv_a_layernorm",
+   "model.layers.1.self_attn.indexer.k_norm",
+   "model.layers.39.post_attention_layernorm",
+   "model.layers.48.mlp.gate.e_score_correction_bias",
+   "model.layers.74.post_attention_layernorm",
+   "model.layers.69.self_attn.q_a_layernorm",
+   "model.layers.13.input_layernorm",
+   "model.layers.74.self_attn.indexer.k_norm",
+   "model.layers.29.mlp.gate",
+   "model.layers.7.mlp.gate.e_score_correction_bias",
+   "model.layers.3.self_attn.kv_a_layernorm",
+   "model.layers.35.self_attn.kv_a_layernorm",
+   "model.layers.46.self_attn.indexers_proj",
+   "model.layers.0.self_attn.kv_a_layernorm",
+   "model.layers.43.self_attn.q_a_layernorm",
+   "model.norm",
+   "model.layers.1.self_attn.kv_a_layernorm",
+   "model.layers.38.self_attn.indexer.k_norm.bias",
+   "model.layers.30.self_attn.q_a_layernorm",
+   "model.layers.0.input_layernorm",
+   "model.layers.47.input_layernorm",
+   "model.layers.8.self_attn.q_a_layernorm",
+   "model.layers.61.self_attn.q_a_layernorm",
+   "model.layers.1.self_attn.indexer.k_norm.bias",
+   "model.layers.62.mlp.gate.e_score_correction_bias",
+   "model.layers.66.self_attn.q_a_layernorm",
+   "model.layers.46.self_attn.kv_a_layernorm",
+   "model.layers.66.mlp.gate",
+   "model.layers.69.input_layernorm",
+   "model.layers.69.self_attn.kv_a_layernorm",
+   "model.layers.22.input_layernorm",
+   "model.layers.30.post_attention_layernorm",
+   "model.layers.24.self_attn.q_a_layernorm",
+   "model.layers.48.mlp.gate",
+   "model.layers.7.self_attn.kv_a_layernorm",
+   "model.layers.67.input_layernorm",
+   "model.layers.27.self_attn.q_a_layernorm",
+   "model.layers.23.mlp.gate",
+   "model.layers.45.mlp.gate.e_score_correction_bias",
+   "model.layers.76.self_attn.kv_a_layernorm",
+   "model.layers.22.self_attn.q_a_layernorm",
+   "model.layers.78.mlp.gate",
+   "model.layers.9.mlp.gate",
+   "model.layers.57.self_attn.q_a_layernorm",
+   "model.layers.78.mlp.gate.e_score_correction_bias",
+   "model.layers.23.post_attention_layernorm",
+   "model.layers.38.self_attn.q_a_layernorm",
+   "model.layers.53.mlp.gate",
+   "model.layers.77.self_attn.q_a_layernorm",
+   "model.layers.62.self_attn.kv_a_layernorm",
+   "model.layers.12.mlp.gate",
+   "model.layers.34.self_attn.indexer.k_norm",
+   "model.layers.46.self_attn.q_a_layernorm",
+   "model.layers.36.self_attn.q_a_layernorm",
+   "model.layers.58.self_attn.indexer.k_norm.bias",
+   "model.layers.60.post_attention_layernorm",
+   "model.layers.28.post_attention_layernorm",
+   "model.layers.2.self_attn.kv_a_layernorm",
+   "model.layers.70.self_attn.indexers_proj",
+   "model.layers.16.mlp.gate.e_score_correction_bias",
+   "model.layers.2.self_attn.indexer.k_norm",
+   "model.layers.31.self_attn.kv_a_layernorm",
+   "model.layers.64.input_layernorm",
+   "model.layers.6.mlp.gate.e_score_correction_bias",
+   "model.layers.50.self_attn.indexer.k_norm",
+   "model.layers.58.self_attn.q_a_layernorm",
+   "model.layers.57.mlp.gate.e_score_correction_bias",
+   "model.layers.13.post_attention_layernorm",
+   "model.layers.28.self_attn.kv_a_layernorm",
+   "model.layers.31.self_attn.q_a_layernorm",
+   "model.layers.1.self_attn.q_a_layernorm",
+   "model.layers.17.mlp.gate",
+   "model.layers.15.post_attention_layernorm",
+   "model.layers.18.self_attn.indexer.k_norm.bias",
+   "model.layers.18.self_attn.indexer.k_norm",
+   "model.layers.43.mlp.gate.e_score_correction_bias",
+   "model.layers.11.input_layernorm",
+   "model.layers.9.post_attention_layernorm",
+   "model.layers.33.input_layernorm",
+   "model.layers.66.input_layernorm",
+   "model.layers.78.self_attn.indexers_proj",
+   "model.layers.54.post_attention_layernorm",
+   "model.layers.53.mlp.gate.e_score_correction_bias",
+   "model.layers.5.mlp.gate.e_score_correction_bias",
+   "model.layers.19.mlp.gate",
+   "model.layers.49.mlp.gate",
+   "model.layers.66.self_attn.indexers_proj",
+   "model.layers.14.self_attn.indexer.k_norm.bias",
+   "model.layers.41.mlp.gate",
+   "model.layers.42.self_attn.indexer.k_norm.bias",
+   "model.layers.65.input_layernorm",
+   "model.layers.75.mlp.gate",
+   "model.layers.12.self_attn.kv_a_layernorm",
+   "model.layers.53.input_layernorm",
+   "model.layers.58.self_attn.kv_a_layernorm",
+   "model.layers.60.self_attn.q_a_layernorm",
+   "model.layers.6.mlp.gate",
+   "model.layers.49.self_attn.kv_a_layernorm",
+   "model.layers.16.mlp.gate",
+   "model.layers.22.mlp.gate",
+   "model.layers.58.post_attention_layernorm",
+   "model.layers.15.mlp.gate.e_score_correction_bias",
+   "model.layers.26.input_layernorm",
+   "model.layers.3.post_attention_layernorm",
+   "model.layers.6.input_layernorm",
+   "model.layers.22.self_attn.kv_a_layernorm",
+   "model.layers.16.input_layernorm",
+   "model.layers.33.post_attention_layernorm",
+   "model.layers.17.post_attention_layernorm",
+   "model.layers.35.mlp.gate",
+   "model.layers.56.post_attention_layernorm",
+   "model.layers.7.self_attn.q_a_layernorm",
+   "model.layers.24.mlp.gate",
+   "model.layers.24.post_attention_layernorm",
+   "model.layers.36.mlp.gate.e_score_correction_bias",
+   "model.layers.56.mlp.gate.e_score_correction_bias",
+   "model.layers.32.post_attention_layernorm",
+   "model.layers.47.post_attention_layernorm",
+   "model.layers.40.mlp.gate",
+   "model.layers.41.self_attn.kv_a_layernorm",
+   "model.layers.52.self_attn.kv_a_layernorm",
+   "model.layers.9.self_attn.kv_a_layernorm",
+   "model.layers.77.mlp.gate.e_score_correction_bias",
+   "model.layers.78.shared_head.norm",
+   "model.layers.53.post_attention_layernorm",
+   "model.layers.63.self_attn.kv_a_layernorm",
+   "model.layers.48.self_attn.kv_a_layernorm",
+   "model.layers.28.mlp.gate.e_score_correction_bias",
+   "model.layers.8.mlp.gate.e_score_correction_bias",
+   "model.layers.52.mlp.gate.e_score_correction_bias",
+   "model.layers.52.post_attention_layernorm",
+   "model.layers.18.self_attn.q_a_layernorm",
+   "model.layers.50.mlp.gate.e_score_correction_bias",
+   "model.layers.64.mlp.gate.e_score_correction_bias",
+   "model.layers.38.mlp.gate.e_score_correction_bias",
+   "model.layers.59.input_layernorm",
+   "model.layers.21.input_layernorm",
+   "model.layers.39.mlp.gate",
+   "model.layers.77.post_attention_layernorm",
+   "model.layers.76.self_attn.q_a_layernorm",
+   "model.layers.12.post_attention_layernorm",
+   "model.layers.43.post_attention_layernorm",
+   "model.layers.35.input_layernorm",
+   "model.layers.62.mlp.gate",
+   "model.layers.38.self_attn.kv_a_layernorm",
+   "model.layers.63.mlp.gate",
+   "model.layers.27.mlp.gate.e_score_correction_bias",
+   "model.layers.18.mlp.gate",
+   "model.layers.25.post_attention_layernorm",
+   "model.layers.55.mlp.gate.e_score_correction_bias",
+   "model.layers.66.self_attn.indexer.k_norm",
+   "model.layers.48.self_attn.q_a_layernorm",
+   "model.layers.78.eh_proj",
+   "model.layers.77.mlp.gate",
+   "model.layers.6.self_attn.indexers_proj",
+   "model.layers.14.self_attn.q_a_layernorm",
+   "model.layers.2.self_attn.q_a_layernorm",
+   "model.layers.42.mlp.gate",
+   "model.layers.54.mlp.gate.e_score_correction_bias",
+   "model.layers.60.input_layernorm",
+   "model.layers.40.self_attn.kv_a_layernorm",
+   "model.layers.51.self_attn.kv_a_layernorm",
+   "model.layers.18.input_layernorm",
+   "model.layers.30.self_attn.indexers_proj",
+   "model.layers.53.self_attn.kv_a_layernorm",
+   "model.layers.6.post_attention_layernorm",
+   "model.layers.70.self_attn.indexer.k_norm.bias",
+   "model.layers.54.input_layernorm",
+   "model.layers.41.self_attn.q_a_layernorm",
+   "model.layers.18.mlp.gate.e_score_correction_bias",
+   "model.layers.34.mlp.gate.e_score_correction_bias",
+   "model.layers.47.mlp.gate",
+   "model.layers.46.mlp.gate",
+   "model.layers.25.self_attn.q_a_layernorm",
+   "model.layers.63.mlp.gate.e_score_correction_bias",
+   "model.layers.66.post_attention_layernorm",
+   "model.layers.76.mlp.gate",
+   "model.embed_tokens",
+   "model.layers.67.self_attn.kv_a_layernorm",
+   "model.layers.67.mlp.gate.e_score_correction_bias",
+   "model.layers.26.self_attn.kv_a_layernorm",
+   "model.layers.31.mlp.gate",
+   "model.layers.18.self_attn.kv_a_layernorm",
+   "model.layers.34.mlp.gate",
+   "model.layers.55.post_attention_layernorm",
+   "model.layers.30.input_layernorm",
+   "model.layers.50.mlp.gate",
+   "model.layers.63.input_layernorm",
+   "model.layers.11.self_attn.kv_a_layernorm",
+   "model.layers.24.self_attn.kv_a_layernorm",
+   "model.layers.75.mlp.gate.e_score_correction_bias",
+   "model.layers.10.post_attention_layernorm",
+   "model.layers.1.self_attn.indexers_proj",
+   "model.layers.42.self_attn.indexers_proj",
+   "model.layers.46.input_layernorm",
+   "model.layers.23.self_attn.q_a_layernorm",
+   "model.layers.63.self_attn.q_a_layernorm",
+   "model.layers.14.self_attn.indexer.k_norm",
+   "model.layers.14.self_attn.indexers_proj",
+   "model.layers.60.mlp.gate",
+   "model.layers.70.mlp.gate.e_score_correction_bias",
+   "model.layers.53.self_attn.q_a_layernorm",
+   "model.layers.0.post_attention_layernorm",
+   "model.layers.35.mlp.gate.e_score_correction_bias",
+   "model.layers.75.self_attn.kv_a_layernorm",
+   "model.layers.1.input_layernorm",
+   "model.layers.42.post_attention_layernorm",
+   "model.layers.37.input_layernorm",
+   "model.layers.9.mlp.gate.e_score_correction_bias",
+   "model.layers.46.post_attention_layernorm",
+   "model.layers.26.mlp.gate",
+   "model.layers.65.mlp.gate.e_score_correction_bias",
+   "model.layers.67.self_attn.q_a_layernorm",
+   "model.layers.44.mlp.gate.e_score_correction_bias",
+   "model.layers.33.mlp.gate",
+   "model.layers.29.input_layernorm",
+   "model.layers.18.post_attention_layernorm",
+   "model.layers.75.post_attention_layernorm",
+   "model.layers.44.self_attn.q_a_layernorm",
+   "model.layers.10.mlp.gate",
+   "model.layers.21.mlp.gate",
+   "model.layers.58.mlp.gate.e_score_correction_bias",
+   "model.layers.7.post_attention_layernorm",
+   "model.layers.50.self_attn.q_a_layernorm",
+   "model.layers.9.self_attn.q_a_layernorm",
+   "model.layers.2.self_attn.indexers_proj",
+   "model.layers.0.self_attn.indexer.k_norm.bias",
+   "model.layers.74.self_attn.kv_a_layernorm",
+   "model.layers.74.mlp.gate.e_score_correction_bias",
+   "model.layers.49.mlp.gate.e_score_correction_bias",
+   "model.layers.62.post_attention_layernorm",
+   "model.layers.57.self_attn.kv_a_layernorm",
+   "model.layers.40.input_layernorm",
+   "model.layers.69.mlp.gate.e_score_correction_bias",
+   "model.layers.35.post_attention_layernorm",
+   "model.layers.74.self_attn.indexers_proj",
+   "model.layers.55.input_layernorm",
+   "model.layers.49.input_layernorm",
+   "model.layers.40.mlp.gate.e_score_correction_bias",
+   "model.layers.25.mlp.gate",
+   "model.layers.2.self_attn.indexer.k_norm.bias",
+   "model.layers.68.self_attn.kv_a_layernorm",
+   "model.layers.51.input_layernorm",
+   "model.layers.22.self_attn.indexers_proj",
+   "model.layers.10.input_layernorm",
+   "model.layers.42.self_attn.indexer.k_norm",
+   "model.layers.56.self_attn.kv_a_layernorm",
+   "model.layers.17.self_attn.q_a_layernorm",
+   "model.layers.59.self_attn.kv_a_layernorm",
+   "model.layers.3.input_layernorm",
+   "model.layers.57.input_layernorm",
+   "model.layers.38.input_layernorm",
+   "model.layers.62.self_attn.indexer.k_norm",
+   "model.layers.20.mlp.gate",
+   "model.layers.64.mlp.gate",
+   "model.layers.28.self_attn.q_a_layernorm",
+   "model.layers.32.self_attn.kv_a_layernorm",
+   "model.layers.10.mlp.gate.e_score_correction_bias",
+   "model.layers.5.self_attn.q_a_layernorm",
+   "model.layers.37.self_attn.kv_a_layernorm"
+  ]
+ }
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.12.0"
+}

model-00001-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d314eee140ac4c0364c1198554ee972068087d38c111e7ec8dcda8c9ab74f63
+size 8611217496

model-00002-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aebd5d4053b00c1b26f9d79c8b83f3f1d7f1d53c872fd5dfa3bd3a4c6bf072e4
+size 8612118432

model-00003-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d37a9e5884dbc234837205d2531934c48a3257a0f9d1be2cc85355038a355a
+size 8601010360

model-00004-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7548825beb6715b582c6f2c510134e3aaf3abe674732ff12e8675006f02b4b
+size 8600494216

model-00005-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78aa114afa7fc1831d4a380578aded0fef8594abf7d98ae9ae02b9dee13900c
+size 8611252496

model-00006-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2448f158dea13bfd634ccdb4edb1ea9b2cea4eb83451079f16d0d282ad7e3126
+size 8601906464

model-00007-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be359749e656d5fca0f5a239c505d39cdb8eb2bdc9cf41a6c8182d29b83dad7
+size 8612156016

model-00008-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e35cadf7587d92ab3bef5713eeafc2122a0cf72c32b5b8ad7744331a0777abc
+size 8609202624

model-00009-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142519e6c3a76b94bac8553ff51469852fa45328d930aa4b0c6d3436504de4e6
+size 8602432984

model-00010-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ecd102f30ab8e043b43842b44183c2b523de1e736094716aa9e2730c3933ef
+size 8612178440

model-00011-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff215b8cfc92db6865d4565a0ece162aac303391ed58a1b6b2880f7f9a1e51ef
+size 8612206408

model-00012-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf99e315698f160dc0bb8408867e417cc1a1d2cc79283203f3d13f2de422cde
+size 8600936440

model-00013-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6c2e77096f4a3564683d2f5106d5bb89222f2ee46476f353fe5944235bcb2d
+size 8612175240

model-00014-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88bec0ed949dcec73df3792a206cfdcd26f31b678319e940a121d2b0f01ca536
+size 8610027648

model-00015-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462261d8c13c2d02aff6a474a8447b084d79765180245203fe50252dc15bb648
+size 8601645168

model-00016-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd035e8f9871a6f24654cc1c50c310b8f262c9a12d0752adef3e6e37a1d33dc
+size 8601732120

model-00017-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531668ba55a61e08da52ff3b7665240007409a1cbffd2a67a83df0df34d63d41
+size 8612402576

model-00018-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53bc2606facba59f288ed5f0fe878e70ae228c2526d625cc22da7ba6c51078e
+size 8612119616

model-00019-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9687cb5924702ea0ea3c7ed8d06ae90a6a0a17fba6947e1e93a18f1dd4c9c10
+size 8601048896

model-00020-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c749f7fee5a23ec4197c7f2ddbcedd07244ca71a56480b3f3e03a35dff7e2ce0
+size 8612133544

model-00021-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875311fb524c9d99a6ef204e82ea758565a505c9f16e348be34450c47b83eb75
+size 8612151160

model-00022-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3501e1c51f730a8fa022e1cd4d18945c61ba49dca2136f5482294a4cbb6147ec
+size 8601045664

model-00023-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bf23814c351b0d6806a1ea6dbc68337cdce2d42de3d7a24108be19d38838f4
+size 8600408008

model-00024-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c09578c8b91c9fa7759b1db273d6a67cb642860fd2017c54ae91461dde6641
+size 8611247880

model-00025-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d73a8b81c397294b523828d0878075a434f341e772db0f66322483a9a4860a
+size 8601906848

model-00026-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216206eab7fb6dc55f4206d87ee0f0518a73b05802a47696bd8b391a6bbf8b33
+size 8612172032

model-00027-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06347bff80d0e06571898ba1865111270c89207bd06f221a39d68eb863ae334b
+size 8612194536

model-00028-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b5a9d6d62a8e1fc09eedc8f400e6f6841b7a87cfe0d5a6649755cdef89ff76
+size 8600976648

model-00029-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c752c8d0f2ad90d50cbb4c5c12925d263b82172f905db212998ca7d7832442e
+size 8612168808

model-00030-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f884d465d31af9933ad480b4ae496dfaeb75129e2ce8c5d1aa1aef5b5c0bcd
+size 8602979720

model-00031-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223f329ac6d7ac8384b9d4a09a5d7aff6e9bc6fc1027d4adfe783986ad6b603a
+size 8608680688

model-00032-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3ac3b5e62d28221075512da68ddb5acacf76e1c73137c6caf78348a6d829a5
+size 8601087448

model-00033-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f37c307a485b5f2c8dd86689836625f822408476d62cd7f6762b0659658c35
+size 8600445256

model-00034-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1ddc234d5ba536e7e634a0974effe4bccfe1cea5c93c40867ff02d7d38a9e0
+size 8602048032

model-00035-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d01fa261e513d9bce7fac0d487918ed159f63c46dfe0998d2f43997a43a703
+size 8611158296

model-00036-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080e8a16502e0ea48fe355101c53a052446449eb048b4285cecb4dd6ace8fdc5
+size 8612098208

model-00037-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e47b5cd089ab44620ed5d63aaa47f1866c25b7c10f3bfbef38eda4828109168
+size 8602989272

model-00038-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f09c0cad3d1e41ad6471c5123c389c0ac8865528343646f29bb4f436eb3db55
+size 8610166376

model-00039-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120faf3f144d5c4fe3f3ff33771745af43235aab05341881eb8942ce81a0dcb1
+size 8612181712

model-00040-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd74daf8f391b7c72407ebcc15685362cbe9b6d45384f29a7b7c39bb33e81d59
+size 8602963016

model-00041-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eecf3cc5f43621029971d7cbc36fec3d2912b3d5644a4be6f0047b91c50f795
+size 8610127624

model-00042-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4539eb8ed8fa1997bb83e992ed976879db218b7a319249fb0540fc7a89e0791
+size 8610090952

model-00043-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81f399e642a3d9275f1bdc0f432012f8b3ff1dd6b6b8bafb4d0db840dd1f052
+size 8601644664

model-00044-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd77a14cd8ac4308a9ddd8f425c1b719c878099922695af2c19efac481557bb
+size 8610608536

model-00045-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7d0a58942947519650835501e706672d0a4e60f55f8e8f08c0ba1039394b77
+size 8600503224

model-00046-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63510d76c5e65864bd0ee655e09177badbef2d81564a83855bed1a1815da7379
+size 8612152808