Initial push

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.53.3"
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86df32404f7a014fafa68b5a6f7c4c179ea8e887574bf32e5a0d0dcdd1b4107b
+size 1947537195

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8609e2de7172163e6d9eba6b4f9b7264ec6c7e88d91b15b90f8845d926af04b4
+size 1964848666

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ced56a6f711a037e90edceef3ceb9c91cd1145b22bc11c5c756776c0bdbf152
+size 1964848794

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ab9eed0c01cab30857e47cef26829bbc81c972a6b2c626096aee693d72589f
+size 1645782299

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30e1fa5d40c9c2cbf414ea1a8eb76010738a7501c7aac2a38d6e5f632f9bf12
+size 536872764

pytorch_model.bin.index.json

@@ -0,0 +1,747 @@
+{
+  "metadata": {
+    "total_parameters": 7248023552,
+    "total_size": 8059633888
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00005-of-00005.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.down_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.down_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.gate_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.gate_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.up_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.up_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.k_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.k_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.o_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.o_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.q_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.q_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.v_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.v_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.down_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.down_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.gate_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.gate_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.up_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.up_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.k_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.k_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.o_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.o_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.q_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.q_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.v_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.v_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.down_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.down_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.gate_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.gate_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.up_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.up_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.k_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.k_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.o_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.o_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.q_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.q_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.v_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.v_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.down_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.down_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.up_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.up_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.down_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.down_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.gate_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.gate_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.up_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.up_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.self_attn.k_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.k_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.o_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.o_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.q_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.q_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.v_proj.SCB": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.v_proj.weight_format": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.down_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.down_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.gate_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.gate_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.up_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.up_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.k_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.k_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.o_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.o_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.q_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.q_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.v_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.v_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.down_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.down_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.gate_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.gate_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.up_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.up_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.k_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.k_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.o_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.o_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.q_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.q_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.v_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.v_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.down_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.down_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.gate_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.gate_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.up_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.up_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.k_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.k_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.o_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.o_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.q_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.q_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.v_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.v_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.down_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.down_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.gate_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.gate_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.up_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.mlp.up_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.k_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.k_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.o_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.o_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.q_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.q_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.v_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.v_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.down_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.down_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.gate_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.gate_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.up_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.mlp.up_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.k_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.k_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.o_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.o_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.q_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.q_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.v_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.v_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.down_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.down_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.gate_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.gate_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.up_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.up_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.k_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.k_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.o_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.o_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.q_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.q_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.v_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.v_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.down_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.down_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.gate_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.gate_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.up_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.mlp.up_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.k_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.k_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.o_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.o_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.q_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.q_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.v_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.v_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.down_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.down_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.gate_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.gate_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.up_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.up_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.k_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.k_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.o_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.o_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.q_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.q_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.v_proj.SCB": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.v_proj.weight_format": "pytorch_model-00004-of-00005.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.down_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.down_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.gate_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.gate_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.up_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.up_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.k_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.k_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.o_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.o_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.q_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.q_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.v_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.v_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.down_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.down_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.gate_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.gate_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.up_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.up_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.k_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.k_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.o_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.o_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.q_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.q_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.v_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.v_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.mlp.gate_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.gate_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.self_attn.k_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.k_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.o_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.o_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.q_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.q_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.v_proj.SCB": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.v_proj.weight_format": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.down_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.down_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.gate_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.gate_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.up_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.up_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.k_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.k_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.o_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.o_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.q_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.q_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.v_proj.SCB": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.v_proj.weight_format": "pytorch_model-00002-of-00005.bin",
+    "model.norm.weight": "pytorch_model-00004-of-00005.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404