Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1,309 @@
+{#- ----------‑‑‑ special token variables ‑‑‑---------- -#}
+{%- set HYTK = ':opensource' %}
+{%- set hy_start_token = '<｜hy_start{}｜>'.format(HYTK) %}
+{%- set hy_middle_token = '<｜hy_middle{}｜>'.format(HYTK) %}
+{%- set hy_end_token = '<｜hy_end{}｜>'.format(HYTK) %}
+{%- set think_begin_token = '<think{}>'.format(HYTK) %}
+{%- set think_end_token = '</think{}>'.format(HYTK) %}
+{%- set toolcalls_begin_token = '<tool_calls{}>'.format(HYTK) %}
+{%- set toolcalls_end_token = '</tool_calls{}>'.format(HYTK) %}
+{%- set toolcall_begin_token = '<tool_call{}>'.format(HYTK) %}
+{%- set toolcall_end_token = '</tool_call{}>'.format(HYTK) %}
+{%- set argkey_begin_token = '<arg_key{}>'.format(HYTK) %}
+{%- set argkey_end_token = '</arg_key{}>'.format(HYTK) %}
+{%- set argvalue_begin_token = '<arg_value{}>'.format(HYTK) %}
+{%- set argvalue_end_token = '</arg_value{}>'.format(HYTK) %}
+{%- set toolresponse_begin_token = '<tool_response{}>'.format(HYTK) %}
+{%- set toolresponse_end_token = '</tool_response{}>'.format(HYTK) %}
+{%- set reasoning_mode_token = '<｜reasoning_mode{}｜>'.format(HYTK) %}
+
+{#- ----------‑‑‑ hyperparameters variables ‑‑‑---------- -#}
+{%- if not add_generation_prompt is defined %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- if not preserved_thinking is defined %}
+    {%- if not tools %}
+        {%- set preserved_thinking = false %}
+    {%- else %}
+        {%- set preserved_thinking = true %}
+    {%- endif %}
+{%- endif %}
+
+{%- if not reasoning_effort is defined %}
+    {%- set reasoning_effort = 'high' %}
+{%- elif reasoning_effort not in ['high', 'no_think'] %}
+    {%- if reasoning_effort is none %}
+        {{- raise_exception('reasoning_effort error : None, should be no_think/high') }}
+    {%- else %}
+        {{- raise_exception('reasoning_effort error : ' + reasoning_effort + ', should be no_think/high') }}
+    {%- endif %}
+{%- endif %}
+
+{%- if fallback_strategy is defined and fallback_strategy == 'reasoning_toolcall_retry' %}
+    {%- set reasoning_effort = 'high' %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- if not raw_last_assistant is defined %}
+    {%- set raw_last_assistant = false %}
+{%- endif %}
+
+{%- 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 render_content(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 -}}
+            {%- else -%}
+                {{- item | string -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- elif content is none -%}
+        {{- '' -}}
+    {%- else -%}
+        {{- content | string -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tools_prompt() -%}
+    {{- '# Tools\n\nYou may call one or more functions to assist with the user query.' -}}
+    {{- '\n\nYou are provided with function signatures within <tools></tools> XML tags:' -}}
+    {{- '\n<tools>\n' -}}
+    {%- set tool_ns = namespace(first=true) -%}
+    {%- for tool in tools -%}
+        {%- set t = tool['function'] if tool is mapping and 'function' in tool else tool -%}
+        {%- if t.defer_loading is not defined or not t.defer_loading -%}
+            {%- if not tool_ns.first -%}{{- '\n' -}}{%- endif -%}
+            {%- set tool_ns.first = false -%}
+            {{- tool_to_json(t) -}}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- '\n</tools>\n\n' -}}
+    {{- 'For function call returns, you should first print ' ~ toolcalls_begin_token -}}
+    {{- '\nFor each function call, you should return object like:\n' -}}
+    {{- toolcall_begin_token ~ '{function-name}' -}}
+    {{- argkey_begin_token ~ '{arg-key-1}' ~ argkey_end_token -}}
+    {{- argvalue_begin_token ~ '{arg-value-1}' ~ argvalue_end_token -}}
+    {{- argkey_begin_token ~ '{arg-key-2}' ~ argkey_end_token -}}
+    {{- argvalue_begin_token ~ '{arg-value-2}' ~ argvalue_end_token -}}
+    {{- '...' -}}
+    {{- toolcall_end_token -}}
+    {{- '\nAt the end of function call returns, you should print ' ~ toolcalls_end_token -}}
+{%- endmacro -%}
+
+{%- macro render_tool_response(message) -%}
+    {%- set content = message['content'] -%}
+    {%- if content is string -%}
+        {{- toolresponse_begin_token ~ content ~ toolresponse_end_token -}}
+    {%- elif content is iterable and content is not mapping and content and content[0] is mapping and content[0].type == 'tool_reference' -%}
+        {{- toolresponse_begin_token -}}
+        {{- '<tools>\n' -}}
+        {%- for tr in content -%}
+            {%- for tool in tools -%}
+                {%- set t = tool['function'] if tool is mapping and 'function' in tool else tool -%}
+                {%- if t.name == tr.name -%}
+                    {{- tool_to_json(t) ~ '\n' -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endfor -%}
+        {{- '</tools>' -}}
+        {{- toolresponse_end_token -}}
+    {%- elif content is iterable and content is not mapping and content and content[0] is mapping and content[0].output is defined -%}
+        {%- for tr in content -%}
+            {{- toolresponse_begin_token ~ tr.output ~ toolresponse_end_token -}}
+        {%- endfor -%}
+    {%- else -%}
+        {{- toolresponse_begin_token ~ render_content(content) ~ toolresponse_end_token -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- consecutive tool messages are clustered into a single tool message whose content is the list of the original tool messages; the result is written to merged_ns.messages (a macro cannot return a list) -#}
+{%- set merged_ns = namespace(messages=[]) %}
+{%- macro merge_tool_responses(messages) -%}
+    {%- set merge_ns = namespace(result=[], cluster=[]) -%}
+    {%- for message in messages -%}
+        {%- if message['role'] == 'tool' -%}
+            {%- set merge_ns.cluster = merge_ns.cluster + [message] -%}
+        {%- else -%}
+            {%- if merge_ns.cluster -%}
+                {%- set merge_ns.result = merge_ns.result + [{'role': 'tool', 'content': merge_ns.cluster}] -%}
+                {%- set merge_ns.cluster = [] -%}
+            {%- endif -%}
+            {%- set merge_ns.result = merge_ns.result + [message] -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- if merge_ns.cluster -%}
+        {%- set merge_ns.result = merge_ns.result + [{'role': 'tool', 'content': merge_ns.cluster}] -%}
+    {%- endif -%}
+    {%- set merged_ns.messages = merge_ns.result -%}
+{%- endmacro -%}
+
+{#- render one tool cluster, reordered to follow the tool_call order of the preceding assistant turn; any missing / ambiguous id falls back to the original tool message order for the whole cluster -#}
+{%- macro render_tool_responses(tool_messages, tool_call_ids) -%}
+    {%- set order_ns = namespace(ordered=[], matched=true) -%}
+    {%- if tool_call_ids and tool_call_ids | length == tool_messages | length -%}
+        {%- for tool_call_id in tool_call_ids -%}
+            {%- set hit_ns = namespace(count=0, message=none) -%}
+            {%- for tool_message in tool_messages -%}
+                {%- set message_id = tool_message['tool_call_id'] if tool_message['tool_call_id'] is defined else tool_message['id'] -%}
+                {%- if message_id is defined and message_id == tool_call_id -%}
+                    {%- set hit_ns.count = hit_ns.count + 1 -%}
+                    {%- set hit_ns.message = tool_message -%}
+                {%- endif -%}
+            {%- endfor -%}
+            {%- if hit_ns.count == 1 -%}
+                {%- set order_ns.ordered = order_ns.ordered + [hit_ns.message] -%}
+            {%- else -%}
+                {%- set order_ns.matched = false -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {%- set order_ns.matched = false -%}
+    {%- endif -%}
+    {%- for tool_message in (order_ns.ordered if order_ns.matched else tool_messages) -%}
+        {{- render_tool_response(tool_message) -}}
+    {%- endfor -%}
+{%- endmacro -%}
+
+{%- set _ = merge_tool_responses(messages) %}
+{%- set normed_messages = merged_ns.messages %}
+
+{%- set ns = namespace(last_user_index=-1, has_leading_system=false) %}
+{%- if normed_messages and normed_messages[0].role == 'system' %}
+    {%- set ns.has_leading_system = true %}
+{%- endif %}
+{%- for message in normed_messages %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.last_user_index = loop.index0 %}
+    {%- endif %}
+{%- endfor %}
+
+{#- no leading system: synthesize one for tools and/or reasoning_mode -#}
+{%- if not ns.has_leading_system %}
+    {{- hy_start_token ~ 'system' ~ hy_middle_token -}}
+    {%- if tools %}
+        {{- render_tools_prompt() -}}
+    {%- endif %}
+    {{- reasoning_mode_token ~ 'reasoning_effort:' ~ reasoning_effort -}}
+    {{- hy_end_token -}}
+{%- endif %}
+
+{%- set last_ns = namespace(last_is_assistant=false) %}
+{%- set prev_ns = namespace(tool_call_ids=[]) %}
+{%- for message in normed_messages %}
+    {%- if message['role'] == 'system' %}
+        {{- hy_start_token ~ 'system' ~ hy_middle_token -}}
+        {#- tools / reasoning_mode only attach to the leading system (messages[0]) -#}
+        {%- if loop.first %}
+            {%- if tools %}
+                {{- render_tools_prompt() -}}
+            {%- endif %}
+            {%- set content = render_content(message['content']) -%}
+            {%- if tools and content -%}
+                {{- '\n\n' -}}
+            {%- endif -%}
+            {{- content -}}
+            {{- reasoning_mode_token ~ 'reasoning_effort:' ~ reasoning_effort -}}
+        {%- else %}
+            {{- render_content(message['content']) -}}
+        {%- endif %}
+        {{- hy_end_token -}}
+    {%- elif message['role'] == 'user' %}
+        {{- hy_start_token ~ 'user' ~ hy_middle_token -}}
+        {{- render_content(message['content']) -}}
+        {{- hy_end_token -}}
+    {%- elif message['role'] == 'assistant' %}
+        {%- set content_body = render_content(message['content']) -%}
+        {#- 'reasoning' takes precedence, fall back to 'reasoning_content' when it is empty -#}
+        {%- set reasoning_text = '' %}
+        {%- if message['reasoning'] is defined and message['reasoning'] is string and message['reasoning'] %}
+            {%- set reasoning_text = message['reasoning'] %}
+        {%- elif message['reasoning_content'] is defined and message['reasoning_content'] is string and message['reasoning_content'] %}
+            {%- set reasoning_text = message['reasoning_content'] %}
+        {%- endif %}
+        {#- no_think overrides preserved_thinking: history is always emitted with empty think tags -#}
+        {%- if reasoning_effort != 'no_think' and (preserved_thinking or loop.index0 > ns.last_user_index) and reasoning_text %}
+            {%- set content = think_begin_token ~ reasoning_text ~ think_end_token ~ content_body %}
+        {%- else %}
+            {%- set content = think_begin_token ~ think_end_token ~ content_body %}
+        {%- endif %}
+        {{- hy_start_token ~ 'assistant' ~ hy_middle_token -}}
+        {%- if message['tool_calls'] is defined and message['tool_calls'] %}
+            {#- remember the tool_call ids of this turn to order the following tool responses; an incomplete id set means "do not reorder" -#}
+            {%- set ids_ns = namespace(ids=[], complete=true) %}
+            {%- for tool in message['tool_calls'] %}
+                {%- set tool_call_id = tool['id'] if tool['id'] is defined and tool['id'] else tool['tool_call_id'] %}
+                {%- if tool_call_id is defined and tool_call_id %}
+                    {%- set ids_ns.ids = ids_ns.ids + [tool_call_id] %}
+                {%- else %}
+                    {%- set ids_ns.complete = false %}
+                {%- endif %}
+            {%- endfor %}
+            {%- set prev_ns.tool_call_ids = ids_ns.ids if ids_ns.complete else [] %}
+            {{- content -}}
+            {{- toolcalls_begin_token -}}
+            {%- for tool in message['tool_calls'] -%}
+                {%- set func = tool['function'] if tool is mapping and 'function' in tool else tool -%}
+                {%- set arguments = func['arguments'] -%}
+                {{- toolcall_begin_token ~ func['name'] -}}
+                {%- for key, value in arguments.items() -%}
+                    {{- argkey_begin_token ~ key ~ argkey_end_token -}}
+                    {%- if value is not string -%}
+                        {%- set value = value | tojson(ensure_ascii=False) -%}
+                    {%- endif -%}
+                    {{- argvalue_begin_token ~ value ~ argvalue_end_token -}}
+                {%- endfor -%}
+                {{- toolcall_end_token -}}
+            {%- endfor -%}
+            {{- toolcalls_end_token -}}
+        {%- else %}
+            {%- if loop.last and raw_last_assistant %}
+                {{- content_body -}}
+            {%- else %}
+                {{- content -}}
+            {%- endif %}
+        {%- endif %}
+        {#- continuation / prefill: last assistant is still open, do not close with hy_end -#}
+        {%- if not (loop.last and raw_last_assistant) and not (loop.last and fallback_strategy is defined and fallback_strategy == 'reasoning_toolcall_retry') %}
+            {{- hy_end_token -}}
+        {%- endif %}
+    {%- elif message['role'] == 'tool' %}
+        {{- hy_start_token ~ 'tool' ~ hy_middle_token -}}
+        {{- render_tool_responses(message['content'], prev_ns.tool_call_ids) -}}
+        {{- hy_end_token -}}
+    {%- else %}
+        {{- hy_start_token ~ message['role'] ~ hy_middle_token -}}
+        {{- render_content(message['content']) -}}
+        {{- hy_end_token -}}
+    {%- endif %}
+    {%- if message['role'] != 'assistant' or not (message['tool_calls'] is defined and message['tool_calls']) %}
+        {%- set prev_ns.tool_call_ids = [] %}
+    {%- endif %}
+    {%- if loop.last and message['role'] == 'assistant' %}
+        {%- set last_ns.last_is_assistant = true %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {%- if not last_ns.last_is_assistant %}
+        {%- if reasoning_effort == 'no_think' %}
+            {{- hy_start_token ~ 'assistant' ~ hy_middle_token ~ think_begin_token ~ think_end_token -}}
+        {%- else %}
+            {{- hy_start_token ~ 'assistant' ~ hy_middle_token ~ think_begin_token -}}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,651 @@
+{
+  "architectures": [
+    "HYV4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bitwise_backward_align": false,
+  "bos_token_id": 120000,
+  "dtype": "bfloat16",
+  "enable_ihc": true,
+  "enable_lm_head_fp32": true,
+  "eos_token_id": 120025,
+  "gated_mla": true,
+  "gating_type": "elementwise",
+  "hc_eps": 1e-06,
+  "hc_magnitude": 2.0,
+  "hc_mult": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "index_head_dim": 128,
+  "index_n_heads": 32,
+  "index_topk": 2048,
+  "indexer_types": [
+    "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",
+    "full"
+  ],
+  "initializer_range": 0.006,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "layer_types": [
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention"
+  ],
+  "learnable_sink": true,
+  "learnable_sink_init": 0.0,
+  "max_position_embeddings": 1048576,
+  "mlp_layer_types": [
+    "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",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "hy_v4",
+  "moe_intermediate_size": 2048,
+  "mtp_loss_factor": 0.1,
+  "n_group": 1,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 78,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 120002,
+  "q_lora_rank": 2048,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.827,
+  "swiglu_limit": 10.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "5.10.2",
+  "use_cache": true,
+  "use_dsa": true,
+  "use_mla": true,
+  "v_head_dim": 256,
+  "vocab_size": 120832,
+  "quantization_config": {
+    "quant_method": "modelopt",
+    "quantization": {
+      "quant_algo": "MXFP8",
+      "kv_cache_quant_algo": null,
+      "exclude_modules": [
+        "lm_head",
+        "model.embed_tokens",
+        "model.hc_head.hc_head_fn",
+        "model.layers.0.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.0.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.0.self_attn.indexer.weights_proj",
+        "model.layers.0.self_attn.linear_gate",
+        "model.layers.1.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.1.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.1.mlp.gate",
+        "model.layers.1.self_attn.indexer.weights_proj",
+        "model.layers.1.self_attn.linear_gate",
+        "model.layers.10.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.10.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.10.mlp.gate",
+        "model.layers.10.self_attn.linear_gate",
+        "model.layers.11.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.11.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.11.mlp.gate",
+        "model.layers.11.self_attn.linear_gate",
+        "model.layers.12.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.12.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.12.mlp.gate",
+        "model.layers.12.self_attn.linear_gate",
+        "model.layers.13.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.13.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.13.mlp.gate",
+        "model.layers.13.self_attn.indexer.weights_proj",
+        "model.layers.13.self_attn.linear_gate",
+        "model.layers.14.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.14.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.14.mlp.gate",
+        "model.layers.14.self_attn.linear_gate",
+        "model.layers.15.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.15.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.15.mlp.gate",
+        "model.layers.15.self_attn.linear_gate",
+        "model.layers.16.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.16.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.16.mlp.gate",
+        "model.layers.16.self_attn.linear_gate",
+        "model.layers.17.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.17.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.17.mlp.gate",
+        "model.layers.17.self_attn.indexer.weights_proj",
+        "model.layers.17.self_attn.linear_gate",
+        "model.layers.18.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.18.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.18.mlp.gate",
+        "model.layers.18.self_attn.linear_gate",
+        "model.layers.19.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.19.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.19.mlp.gate",
+        "model.layers.19.self_attn.linear_gate",
+        "model.layers.2.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.2.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.2.mlp.gate",
+        "model.layers.2.self_attn.linear_gate",
+        "model.layers.20.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.20.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.20.mlp.gate",
+        "model.layers.20.self_attn.linear_gate",
+        "model.layers.21.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.21.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.21.mlp.gate",
+        "model.layers.21.self_attn.indexer.weights_proj",
+        "model.layers.21.self_attn.linear_gate",
+        "model.layers.22.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.22.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.22.mlp.gate",
+        "model.layers.22.self_attn.linear_gate",
+        "model.layers.23.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.23.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.23.mlp.gate",
+        "model.layers.23.self_attn.linear_gate",
+        "model.layers.24.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.24.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.24.mlp.gate",
+        "model.layers.24.self_attn.linear_gate",
+        "model.layers.25.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.25.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.25.mlp.gate",
+        "model.layers.25.self_attn.indexer.weights_proj",
+        "model.layers.25.self_attn.linear_gate",
+        "model.layers.26.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.26.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.26.mlp.gate",
+        "model.layers.26.self_attn.linear_gate",
+        "model.layers.27.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.27.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.27.mlp.gate",
+        "model.layers.27.self_attn.linear_gate",
+        "model.layers.28.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.28.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.28.mlp.gate",
+        "model.layers.28.self_attn.linear_gate",
+        "model.layers.29.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.29.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.29.mlp.gate",
+        "model.layers.29.self_attn.indexer.weights_proj",
+        "model.layers.29.self_attn.linear_gate",
+        "model.layers.3.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.3.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.3.mlp.gate",
+        "model.layers.3.self_attn.linear_gate",
+        "model.layers.30.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.30.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.30.mlp.gate",
+        "model.layers.30.self_attn.linear_gate",
+        "model.layers.31.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.31.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.31.mlp.gate",
+        "model.layers.31.self_attn.linear_gate",
+        "model.layers.32.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.32.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.32.mlp.gate",
+        "model.layers.32.self_attn.linear_gate",
+        "model.layers.33.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.33.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.33.mlp.gate",
+        "model.layers.33.self_attn.indexer.weights_proj",
+        "model.layers.33.self_attn.linear_gate",
+        "model.layers.34.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.34.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.34.mlp.gate",
+        "model.layers.34.self_attn.linear_gate",
+        "model.layers.35.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.35.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.35.mlp.gate",
+        "model.layers.35.self_attn.linear_gate",
+        "model.layers.36.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.36.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.36.mlp.gate",
+        "model.layers.36.self_attn.linear_gate",
+        "model.layers.37.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.37.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.37.mlp.gate",
+        "model.layers.37.self_attn.indexer.weights_proj",
+        "model.layers.37.self_attn.linear_gate",
+        "model.layers.38.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.38.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.38.mlp.gate",
+        "model.layers.38.self_attn.linear_gate",
+        "model.layers.39.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.39.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.39.mlp.gate",
+        "model.layers.39.self_attn.linear_gate",
+        "model.layers.4.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.4.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.4.mlp.gate",
+        "model.layers.4.self_attn.linear_gate",
+        "model.layers.40.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.40.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.40.mlp.gate",
+        "model.layers.40.self_attn.linear_gate",
+        "model.layers.41.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.41.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.41.mlp.gate",
+        "model.layers.41.self_attn.indexer.weights_proj",
+        "model.layers.41.self_attn.linear_gate",
+        "model.layers.42.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.42.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.42.mlp.gate",
+        "model.layers.42.self_attn.linear_gate",
+        "model.layers.43.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.43.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.43.mlp.gate",
+        "model.layers.43.self_attn.linear_gate",
+        "model.layers.44.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.44.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.44.mlp.gate",
+        "model.layers.44.self_attn.linear_gate",
+        "model.layers.45.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.45.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.45.mlp.gate",
+        "model.layers.45.self_attn.indexer.weights_proj",
+        "model.layers.45.self_attn.linear_gate",
+        "model.layers.46.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.46.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.46.mlp.gate",
+        "model.layers.46.self_attn.linear_gate",
+        "model.layers.47.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.47.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.47.mlp.gate",
+        "model.layers.47.self_attn.linear_gate",
+        "model.layers.48.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.48.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.48.mlp.gate",
+        "model.layers.48.self_attn.linear_gate",
+        "model.layers.49.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.49.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.49.mlp.gate",
+        "model.layers.49.self_attn.indexer.weights_proj",
+        "model.layers.49.self_attn.linear_gate",
+        "model.layers.5.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.5.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.5.mlp.gate",
+        "model.layers.5.self_attn.indexer.weights_proj",
+        "model.layers.5.self_attn.linear_gate",
+        "model.layers.50.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.50.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.50.mlp.gate",
+        "model.layers.50.self_attn.linear_gate",
+        "model.layers.51.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.51.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.51.mlp.gate",
+        "model.layers.51.self_attn.linear_gate",
+        "model.layers.52.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.52.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.52.mlp.gate",
+        "model.layers.52.self_attn.linear_gate",
+        "model.layers.53.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.53.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.53.mlp.gate",
+        "model.layers.53.self_attn.indexer.weights_proj",
+        "model.layers.53.self_attn.linear_gate",
+        "model.layers.54.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.54.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.54.mlp.gate",
+        "model.layers.54.self_attn.linear_gate",
+        "model.layers.55.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.55.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.55.mlp.gate",
+        "model.layers.55.self_attn.linear_gate",
+        "model.layers.56.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.56.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.56.mlp.gate",
+        "model.layers.56.self_attn.linear_gate",
+        "model.layers.57.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.57.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.57.mlp.gate",
+        "model.layers.57.self_attn.indexer.weights_proj",
+        "model.layers.57.self_attn.linear_gate",
+        "model.layers.58.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.58.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.58.mlp.gate",
+        "model.layers.58.self_attn.linear_gate",
+        "model.layers.59.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.59.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.59.mlp.gate",
+        "model.layers.59.self_attn.linear_gate",
+        "model.layers.6.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.6.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.6.mlp.gate",
+        "model.layers.6.self_attn.linear_gate",
+        "model.layers.60.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.60.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.60.mlp.gate",
+        "model.layers.60.self_attn.linear_gate",
+        "model.layers.61.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.61.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.61.mlp.gate",
+        "model.layers.61.self_attn.indexer.weights_proj",
+        "model.layers.61.self_attn.linear_gate",
+        "model.layers.62.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.62.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.62.mlp.gate",
+        "model.layers.62.self_attn.linear_gate",
+        "model.layers.63.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.63.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.63.mlp.gate",
+        "model.layers.63.self_attn.linear_gate",
+        "model.layers.64.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.64.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.64.mlp.gate",
+        "model.layers.64.self_attn.linear_gate",
+        "model.layers.65.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.65.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.65.mlp.gate",
+        "model.layers.65.self_attn.indexer.weights_proj",
+        "model.layers.65.self_attn.linear_gate",
+        "model.layers.66.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.66.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.66.mlp.gate",
+        "model.layers.66.self_attn.linear_gate",
+        "model.layers.67.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.67.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.67.mlp.gate",
+        "model.layers.67.self_attn.linear_gate",
+        "model.layers.68.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.68.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.68.mlp.gate",
+        "model.layers.68.self_attn.linear_gate",
+        "model.layers.69.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.69.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.69.mlp.gate",
+        "model.layers.69.self_attn.indexer.weights_proj",
+        "model.layers.69.self_attn.linear_gate",
+        "model.layers.7.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.7.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.7.mlp.gate",
+        "model.layers.7.self_attn.linear_gate",
+        "model.layers.70.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.70.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.70.mlp.gate",
+        "model.layers.70.self_attn.linear_gate",
+        "model.layers.71.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.71.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.71.mlp.gate",
+        "model.layers.71.self_attn.linear_gate",
+        "model.layers.72.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.72.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.72.mlp.gate",
+        "model.layers.72.self_attn.linear_gate",
+        "model.layers.73.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.73.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.73.mlp.gate",
+        "model.layers.73.self_attn.indexer.weights_proj",
+        "model.layers.73.self_attn.linear_gate",
+        "model.layers.74.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.74.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.74.mlp.gate",
+        "model.layers.74.self_attn.linear_gate",
+        "model.layers.75.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.75.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.75.mlp.gate",
+        "model.layers.75.self_attn.linear_gate",
+        "model.layers.76.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.76.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.76.mlp.gate",
+        "model.layers.76.self_attn.linear_gate",
+        "model.layers.77.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.77.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.77.mlp.gate",
+        "model.layers.77.self_attn.indexer.weights_proj",
+        "model.layers.77.self_attn.linear_gate",
+        "model.layers.8.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.8.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.8.mlp.gate",
+        "model.layers.8.self_attn.linear_gate",
+        "model.layers.9.hc_attn_layer.hc_pre.hc_fn",
+        "model.layers.9.hc_mlp_layer.hc_pre.hc_fn",
+        "model.layers.9.mlp.gate",
+        "model.layers.9.self_attn.indexer.weights_proj",
+        "model.layers.9.self_attn.linear_gate",
+        "model.mtp_layers.0.eh_proj",
+        "model.mtp_layers.0.mlp.gate",
+        "model.mtp_layers.0.self_attn.indexer.weights_proj",
+        "model.mtp_layers.0.self_attn.linear_gate"
+      ]
+    }
+  },
+  "torch_dtype": "bfloat16"
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 120000,
+  "do_sample": true,
+  "eos_token_id": 120025,
+  "pad_token_id": 120002,
+  "temperature": 0.9,
+  "top_k": -1,
+  "top_p": 1,
+  "transformers_version": "5.10.2"
+}

model-00001-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414cc8c59bcfd545fe46b63ad31028af39a487df7a1fc837e0e950214b308979
+size 9965666800

model-00002-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c8396df203fc1e77e3e25b8a111b93027d20f83a8455c0e0dec63a0d562c042
+size 9965666808

model-00003-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626fe3712d65c468c6c603d9df0e9aed95f7704caad2f31d03375b3c1dbf6bb9
+size 9965666808

model-00004-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57d8faefe9e3f62b62e2577745fe975478a838726a1968d920eeb5f08d1b659
+size 9965666800

model-00005-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a430997c16e724f83e564a61fa70009a60dbe0c9c2aeb1f2514197382e85675d
+size 9965666808

model-00006-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c5ebbf103e6aa5ff0c67b66c1daed70c36cc5d75f6777e7932683460b1b7fe
+size 9965666808

model-00007-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfae267c634535d61c32abec63f88d6e4ea0d4516f8a8effedb6c18d32fede2c
+size 9965666800

model-00008-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d9521edc9842610d0e6847116af715b834588bae0f685ca6ad7d58d15d6c0d
+size 9965666808

model-00009-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be75396790490279d1d2beb0e04fde101ef75915cf1d04cd483258e923f3cdd
+size 9965666808

model-00010-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43085db3067c7133f9f4131384f21bda57e561bf6af6908d81765ae18e7b980
+size 9965666800

model-00011-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54af493cca42fadbbbe4479c3bd832281da7aa839920073fc84c6c8d25ec8690
+size 9965666808

model-00012-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0c0f158c84b3744acc312dd31b687bdcc4870c40aa70ffcdf8b13048b17c53
+size 9965666808

model-00013-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100a06a52c0aef50c33b24322bf47236c18503b1512d0de428c6ed36a7a3046b
+size 9965666800

model-00014-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2c7f73dff160e0996c0017897d04a7e07f183b7fc85e12091eed76233e6956
+size 9965666808

model-00015-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b978107037f67a85f66819b3d7eadf4ddf84059d6095fc186431dc495a60a5fa
+size 9965666808

model-00016-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a3d99130ba6c50d2dc0af6c27029752757ee9edd357ea84ae50510fb781073
+size 9965666800

model-00017-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d1bc6843dcfa873b9705e020267fedb5b79384a10f6f57a3424c528998d5ed
+size 9965666808

model-00018-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd84de448c8b6cd26e87427fddcee28ca925e1287e5d3a6503c1430d05f6a17
+size 9965666808

model-00019-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451e4caefc5d86b444e64e1eadd3128a5e7c9528ac02ba220603cae19a137d8f
+size 9965666800

model-00020-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278e4c635a9b7c44e48bac5da5fb217a33cd44c8c5268de04cd97a354879b230
+size 9965666808

model-00021-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4185e4eb6b6a88faded960d902b38f8f908e48630f21d27104434c054a06150f
+size 9965666808

model-00022-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef96e10d9c683a5718eb9ff475b25321852254a0e8c7d6398e3a7548ada9821
+size 9965666800

model-00023-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909676a743fd94c95c78112a42a22cd24dd94a218a26681d43d152c7fe93f5ea
+size 9965666808

model-00024-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722eac11890368bec6b258cc09e4a4581879a286cf811c76177af6800d57471d
+size 9965666808

model-00025-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa641469e0d210930d75b0f366afb3a08a00de27282b7b8ba5e55aac64904344
+size 9965666800

model-00026-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a29db98b926f746ffd67fa66de1f1b443628d2e9436ba032905aa0785e094fc
+size 9965666808

model-00027-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a158e22416bff4f3bf4b8769f550dde35c05efc9281c499717060214f5b30b65
+size 9965666808

model-00028-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612ff15c3c9dbd4242e6b5c4be6eeffb874f9a440bd394e344a7935ffe94210e
+size 9965666808

model-00029-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681c9d57cc4d58f389f9f1d15fe9c4a612399e46c78e3a7658415346cc507626
+size 9965666808

model-00030-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620cb4be7f182244cb8d85b4578a72445117cba32c1139917c7d58ac19d82e78
+size 9965666808

model-00031-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc95523478aaac7c431502cf888480792ef7e4162b5ded83c9a5fe5b970f86d
+size 9965666808

model-00032-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a0c1fab7e1eb6446be1b366b425ca055b260158a55f513431f9247aa7da61e
+size 9965666808

model-00033-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451f000728d0bf9caf0302423bdc148e1083be39f6b948b26da850108db07f18
+size 9965666808

model-00034-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9a1604006bbe07f0dc66efbf8a3e0b21ed53ed6f89389e47fc05b39c059c97
+size 9965666808

model-00035-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1746e8a11fdc5fd391ac80b16545ffaa6cb29682850eaf50c024e2244776659e
+size 9965666808

model-00036-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e333786190b0cb378f769fb46ef0dcf41f480201500ee2fbc9e337f0ea695348
+size 9965666808

model-00037-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1276412b7145ca2bf361ab8c1fa98dc62595a976c98e81088efca06e5c343048
+size 9965666808

model-00038-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f75ea0670ee6995e86e60b1da6ed5553126e794358d73bc4f49f8facfb266fb
+size 9965666808

model-00039-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84f35f54f413c99b702f1c7b6428e5ca59dba86f70c72202d662cd2f21d00b0
+size 9965666808

model-00040-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21667ff5533397d947e4b7a6d509f2303862f730a0cb1442bd210f0c76e6a77
+size 9965666808

model-00041-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9283bdabf3634c64344983215b4fd15e52522149fed0400a6cf9d8dc841e23d3
+size 9965666808

model-00042-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257e798baeb95453b2f6aed635e40164509ced129340d38ce6dcb8bfb643f372
+size 9965666808

model-00043-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77aa529f077bb414b1a33e57fc2d98046a87346109477f89a054b633957ccd5c
+size 9965666808

model-00044-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d498e565f1b7e230f09401fdc484a01ab86e0a95a39ff56d40f0dd93ed2bc0
+size 9965666808

model-00045-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e569e3260dda178ef2e180b32c423ebf8d36b173be4600b84c59d05f63f97482
+size 9965666808

model-00046-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f79e1d0aec4238a577d29da2638c43b0c5a94090255fd96bea1ea0ce0ef97b
+size 1484783728

model-00047-of-00130.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5788bd231c8e0ffdd7454568e088be1cd0e723d53b6c657fe55a6334baf0d08
+size 714081224