Upload folder using huggingface_hub

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 +1,106 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bits": 8,
+    "checkpoint_format": "gptq",
+    "desc_act": false,
+    "dynamic": {
+      "+:.*\\.20\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.21\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.22\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.23\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.24\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.25\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.26\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.27\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.28\\..*": {
+        "bits": 4
+      },
+      "+:.*\\.29\\..*": {
+        "bits": 4
+      }
+    },
+    "format": "gptq",
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "act_group_aware": true,
+      "auto_forward_data_parallel": true,
+      "damp_auto_increment": 0.01,
+      "damp_percent": 0.05,
+      "fallback": {
+        "smooth": null,
+        "strategy": "rtn",
+        "threshold": "0.5%"
+      },
+      "foem": null,
+      "gc_mode": "interval",
+      "gptaq": null,
+      "hessian": {
+        "chunk_bytes": null,
+        "chunk_size": null,
+        "staging_dtype": "float32"
+      },
+      "mock_quantization": false,
+      "mse": 0.0,
+      "offload_to_disk": true,
+      "offload_to_disk_path": "./gptqmodel_offload/slyadpab-cehsqtyh/",
+      "pack_impl": "cpu",
+      "quantizer": [
+        "gptqmodel:6.0.3"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel",
+      "vram_strategy": "exclusive",
+      "wait_for_submodule_finalizers": false
+    },
+    "method": "gptq",
+    "pack_dtype": "int32",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.3",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "5.5.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b3b9f6ca9f7af5f40a5e772993221c04d9e7018bdb402d93a1810d4caac9ec
+size 4275596832

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3682e5a983866109c5a90305c2d5fc42aaff7ad692fd58f1dde68d668edbc915
+size 2310756680

model.safetensors.index.json

@@ -0,0 +1,970 @@
+{
+  "metadata": {
+    "total_size": 6586353512
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

quant_log.csv

@@ -0,0 +1,225 @@
+layer,module,loss,samples,damp,time
+0,self_attn.v_proj,0.0000000004,0.05000,4.879
+0,self_attn.q_proj,0.0000000150,0.05000,4.920
+0,self_attn.k_proj,0.0000000045,0.05000,4.920
+0,self_attn.o_proj,0.0000000000,0.05000,1.541
+0,mlp.up_proj,0.0000000142,0.05000,2.767
+0,mlp.gate_proj,0.0000000164,0.05000,2.788
+0,mlp.down_proj,0.0000000000,0.05000,5.935
+1,self_attn.q_proj,0.0000000452,0.05000,5.686
+1,self_attn.k_proj,0.0000000208,0.05000,5.717
+1,self_attn.v_proj,0.0000000034,0.05000,5.753
+1,self_attn.o_proj,0.0000000000,0.05000,1.558
+1,mlp.gate_proj,0.0000000548,0.05000,2.780
+1,mlp.up_proj,0.0000000480,0.05000,2.812
+1,mlp.down_proj,0.0000000073,0.05000,5.981
+2,self_attn.q_proj,0.0000003553,0.05000,5.404
+2,self_attn.v_proj,0.0000000225,0.05000,5.422
+2,self_attn.k_proj,0.0000001725,0.05000,5.441
+2,self_attn.o_proj,0.0000000000,0.05000,1.573
+2,mlp.gate_proj,0.0000001153,0.05000,2.787
+2,mlp.up_proj,0.0000001006,0.05000,2.788
+2,mlp.down_proj,0.0000000000,0.05000,5.971
+3,self_attn.k_proj,0.0000000937,0.05000,5.724
+3,self_attn.v_proj,0.0000000155,0.05000,5.736
+3,self_attn.q_proj,0.0000001928,0.05000,5.763
+3,self_attn.o_proj,0.0000000000,0.05000,1.568
+3,mlp.up_proj,0.0000001660,0.05000,2.751
+3,mlp.gate_proj,0.0000001922,0.05000,2.756
+3,mlp.down_proj,0.0000000001,0.05000,6.016
+4,self_attn.q_proj,0.0000003002,0.05000,5.606
+4,self_attn.k_proj,0.0000001324,0.05000,5.636
+4,self_attn.v_proj,0.0000000261,0.05000,5.673
+4,self_attn.o_proj,0.0000000000,0.05000,1.554
+4,mlp.gate_proj,0.0000002774,0.05000,2.768
+4,mlp.up_proj,0.0000002246,0.05000,2.775
+4,mlp.down_proj,0.0000000001,0.05000,6.006
+5,self_attn.q_proj,0.0000003899,0.05000,5.595
+5,self_attn.v_proj,0.0000000291,0.05000,5.614
+5,self_attn.k_proj,0.0000001730,0.05000,5.617
+5,self_attn.o_proj,0.0000000001,0.05000,1.574
+5,mlp.gate_proj,0.0000003836,0.05000,2.772
+5,mlp.up_proj,0.0000002912,0.05000,2.784
+5,mlp.down_proj,0.0000000003,0.05000,6.005
+6,self_attn.k_proj,0.0000001706,0.05000,5.528
+6,self_attn.v_proj,0.0000000294,0.05000,5.586
+6,self_attn.q_proj,0.0000003636,0.05000,5.630
+6,self_attn.o_proj,0.0000000001,0.05000,1.573
+6,mlp.gate_proj,0.0000004451,0.05000,2.861
+6,mlp.up_proj,0.0000003460,0.05000,2.881
+6,mlp.down_proj,0.0000000004,0.05000,6.009
+7,self_attn.v_proj,0.0000000391,0.05000,5.708
+7,self_attn.k_proj,0.0000002152,0.05000,5.739
+7,self_attn.q_proj,0.0000004503,0.05000,5.761
+7,self_attn.o_proj,0.0000000001,0.05000,1.558
+7,mlp.up_proj,0.0000004005,0.05000,2.803
+7,mlp.gate_proj,0.0000005274,0.05000,2.822
+7,mlp.down_proj,0.0000000005,0.05000,6.020
+8,self_attn.v_proj,0.0000000364,0.05000,5.675
+8,self_attn.k_proj,0.0000001697,0.05000,5.686
+8,self_attn.q_proj,0.0000003730,0.05000,5.700
+8,self_attn.o_proj,0.0000000002,0.05000,1.551
+8,mlp.gate_proj,0.0000005689,0.05000,2.796
+8,mlp.up_proj,0.0000004404,0.05000,2.803
+8,mlp.down_proj,0.0000000005,0.05000,5.992
+9,self_attn.v_proj,0.0000000435,0.05000,5.665
+9,self_attn.q_proj,0.0000005147,0.05000,5.700
+9,self_attn.k_proj,0.0000002410,0.05000,5.705
+9,self_attn.o_proj,0.0000000002,0.05000,1.557
+9,mlp.gate_proj,0.0000005988,0.05000,2.784
+9,mlp.up_proj,0.0000004793,0.05000,2.792
+9,mlp.down_proj,0.0000000007,0.05000,5.989
+10,self_attn.q_proj,0.0000004548,0.05000,5.268
+10,self_attn.v_proj,0.0000000379,0.05000,5.291
+10,self_attn.k_proj,0.0000002164,0.05000,5.309
+10,self_attn.o_proj,0.0000000003,0.05000,1.565
+10,mlp.up_proj,0.0000005106,0.05000,2.780
+10,mlp.gate_proj,0.0000006227,0.05000,2.789
+10,mlp.down_proj,0.0000000008,0.05000,5.958
+11,self_attn.v_proj,0.0000000559,0.05000,5.584
+11,self_attn.k_proj,0.0000002533,0.05000,5.600
+11,self_attn.q_proj,0.0000005502,0.05000,5.626
+11,self_attn.o_proj,0.0000000004,0.05000,1.522
+11,mlp.up_proj,0.0000005648,0.05000,2.815
+11,mlp.gate_proj,0.0000006790,0.05000,2.825
+11,mlp.down_proj,0.0000000009,0.05000,6.012
+12,self_attn.q_proj,0.0000007278,0.05000,5.495
+12,self_attn.v_proj,0.0000000635,0.05000,5.547
+12,self_attn.k_proj,0.0000003287,0.05000,5.564
+12,self_attn.o_proj,0.0000000004,0.05000,1.548
+12,mlp.up_proj,0.0000006364,0.05000,2.785
+12,mlp.gate_proj,0.0000007479,0.05000,2.796
+12,mlp.down_proj,0.0000000011,0.05000,5.937
+13,self_attn.q_proj,0.0000005740,0.05000,5.754
+13,self_attn.k_proj,0.0000002807,0.05000,5.812
+13,self_attn.v_proj,0.0000000607,0.05000,5.828
+13,self_attn.o_proj,0.0000000006,0.05000,1.556
+13,mlp.gate_proj,0.0000008370,0.05000,2.780
+13,mlp.up_proj,0.0000007320,0.05000,2.790
+13,mlp.down_proj,0.0000000013,0.05000,5.960
+14,self_attn.v_proj,0.0000000978,0.05000,5.400
+14,self_attn.k_proj,0.0000002809,0.05000,5.464
+14,self_attn.q_proj,0.0000006548,0.05000,5.490
+14,self_attn.o_proj,0.0000000007,0.05000,1.586
+14,mlp.gate_proj,0.0000009377,0.05000,2.823
+14,mlp.up_proj,0.0000008157,0.05000,2.830
+14,mlp.down_proj,0.0000000017,0.05000,5.987
+15,self_attn.q_proj,0.0000008244,0.05000,5.573
+15,self_attn.v_proj,0.0000001112,0.05000,5.588
+15,self_attn.k_proj,0.0000003675,0.05000,5.609
+15,self_attn.o_proj,0.0000000008,0.05000,1.566
+15,mlp.gate_proj,0.0000010717,0.05000,2.808
+15,mlp.up_proj,0.0000009010,0.05000,2.818
+15,mlp.down_proj,0.0000000022,0.05000,5.975
+16,self_attn.k_proj,0.0000003414,0.05000,5.454
+16,self_attn.q_proj,0.0000007387,0.05000,5.480
+16,self_attn.v_proj,0.0000001060,0.05000,5.509
+16,self_attn.o_proj,0.0000000009,0.05000,1.547
+16,mlp.gate_proj,0.0000013285,0.05000,2.811
+16,mlp.up_proj,0.0000010571,0.05000,2.817
+16,mlp.down_proj,0.0000000031,0.05000,5.919
+17,self_attn.k_proj,0.0000002850,0.05000,5.686
+17,self_attn.v_proj,0.0000001007,0.05000,5.715
+17,self_attn.q_proj,0.0000006805,0.05000,5.725
+17,self_attn.o_proj,0.0000000011,0.05000,1.541
+17,mlp.up_proj,0.0000012283,0.05000,2.767
+17,mlp.gate_proj,0.0000015413,0.05000,2.776
+17,mlp.down_proj,0.0000000043,0.05000,5.974
+18,self_attn.v_proj,0.0000001238,0.05000,5.556
+18,self_attn.q_proj,0.0000008637,0.05000,5.607
+18,self_attn.k_proj,0.0000003386,0.05000,5.626
+18,self_attn.o_proj,0.0000000011,0.05000,1.556
+18,mlp.gate_proj,0.0000017367,0.05000,2.802
+18,mlp.up_proj,0.0000013842,0.05000,2.808
+18,mlp.down_proj,0.0000000061,0.05000,5.951
+19,self_attn.v_proj,0.0000001450,0.05000,5.642
+19,self_attn.k_proj,0.0000003408,0.05000,5.663
+19,self_attn.q_proj,0.0000007988,0.05000,5.674
+19,self_attn.o_proj,0.0000000013,0.05000,1.604
+19,mlp.gate_proj,0.0000019642,0.05000,2.772
+19,mlp.up_proj,0.0000015377,0.05000,2.790
+19,mlp.down_proj,0.0000000081,0.05000,5.997
+20,self_attn.v_proj,0.0000460283,0.05000,5.376
+20,self_attn.k_proj,0.0001023333,0.05000,5.450
+20,self_attn.q_proj,0.0002501937,0.05000,5.460
+20,self_attn.o_proj,0.0000003618,0.05000,1.531
+20,mlp.up_proj,0.0004975359,0.05000,2.774
+20,mlp.gate_proj,0.0006521194,0.05000,2.779
+20,mlp.down_proj,0.0000025065,0.05000,5.931
+21,self_attn.q_proj,0.0002477611,0.05000,5.504
+21,self_attn.v_proj,0.0000486894,0.05000,5.527
+21,self_attn.k_proj,0.0001006711,0.05000,5.532
+21,self_attn.o_proj,0.0000003476,0.05000,1.553
+21,mlp.gate_proj,0.0007708430,0.05000,2.834
+21,mlp.up_proj,0.0005485023,0.05000,2.842
+21,mlp.down_proj,0.0000025757,0.05000,5.948
+22,self_attn.k_proj,0.0000960108,0.05000,5.470
+22,self_attn.v_proj,0.0000507348,0.05000,5.527
+22,self_attn.q_proj,0.0002405264,0.05000,5.538
+22,self_attn.o_proj,0.0000002108,0.05000,1.560
+22,mlp.gate_proj,0.0008269122,0.05000,2.758
+22,mlp.up_proj,0.0005943207,0.05000,2.774
+22,mlp.down_proj,0.0000027136,0.05000,5.973
+23,self_attn.k_proj,0.0000954055,0.05000,5.533
+23,self_attn.q_proj,0.0002420283,0.05000,5.626
+23,self_attn.v_proj,0.0000532537,0.05000,5.632
+23,self_attn.o_proj,0.0000003501,0.05000,1.542
+23,mlp.gate_proj,0.0009137075,0.05000,2.776
+23,mlp.up_proj,0.0006547531,0.05000,2.791
+23,mlp.down_proj,0.0000030363,0.05000,5.945
+24,self_attn.v_proj,0.0000622052,0.05000,5.253
+24,self_attn.k_proj,0.0001111750,0.05000,5.364
+24,self_attn.q_proj,0.0002778825,0.05000,5.381
+24,self_attn.o_proj,0.0000003277,0.05000,1.549
+24,mlp.gate_proj,0.0010315949,0.05000,2.772
+24,mlp.up_proj,0.0007254657,0.05000,2.776
+24,mlp.down_proj,0.0000033368,0.05000,5.985
+25,self_attn.q_proj,0.0002790395,0.05000,5.293
+25,self_attn.k_proj,0.0001072556,0.05000,5.306
+25,self_attn.v_proj,0.0000711914,0.05000,5.348
+25,self_attn.o_proj,0.0000003792,0.05000,1.548
+25,mlp.gate_proj,0.0011210348,0.05000,2.794
+25,mlp.up_proj,0.0007955477,0.05000,2.800
+25,mlp.down_proj,0.0000038278,0.05000,5.962
+26,self_attn.k_proj,0.0001005206,0.05000,5.340
+26,self_attn.v_proj,0.0000751634,0.05000,5.363
+26,self_attn.q_proj,0.0002639526,0.05000,5.399
+26,self_attn.o_proj,0.0000004955,0.05000,1.543
+26,mlp.gate_proj,0.0011751253,0.05000,2.736
+26,mlp.up_proj,0.0008637970,0.05000,2.749
+26,mlp.down_proj,0.0000043847,0.05000,5.972
+27,self_attn.v_proj,0.0000680719,0.05000,5.472
+27,self_attn.k_proj,0.0001012717,0.05000,5.603
+27,self_attn.q_proj,0.0002717224,0.05000,5.640
+27,self_attn.o_proj,0.0000005582,0.05000,1.565
+27,mlp.up_proj,0.0009500155,0.05000,2.771
+27,mlp.gate_proj,0.0012836707,0.05000,2.789
+27,mlp.down_proj,0.0000051473,0.05000,5.936
+28,self_attn.v_proj,0.0000992078,0.05000,5.279
+28,self_attn.q_proj,0.0002645630,0.05000,5.304
+28,self_attn.k_proj,0.0001015999,0.05000,5.323
+28,self_attn.o_proj,0.0000008682,0.05000,1.565
+28,mlp.up_proj,0.0010524418,0.05000,2.756
+28,mlp.gate_proj,0.0013713280,0.05000,2.756
+28,mlp.down_proj,0.0000069629,0.05000,5.935
+29,self_attn.q_proj,0.0003024004,0.05000,5.304
+29,self_attn.v_proj,0.0001436985,0.05000,5.320
+29,self_attn.k_proj,0.0001024819,0.05000,5.347
+29,self_attn.o_proj,0.0000018162,0.05000,1.534
+29,mlp.gate_proj,0.0013321182,0.05000,2.757
+29,mlp.up_proj,0.0010659065,0.05000,2.770
+29,mlp.down_proj,0.0000087815,0.05000,5.935
+30,self_attn.k_proj,0.0000003260,0.05000,5.367
+30,self_attn.q_proj,0.0000009703,0.05000,5.382
+30,self_attn.v_proj,0.0000005463,0.05000,5.396
+30,self_attn.o_proj,0.0000000055,0.05000,1.542
+30,mlp.up_proj,0.0000037689,0.05000,2.758
+30,mlp.gate_proj,0.0000046290,0.05000,2.762
+30,mlp.down_proj,0.0000000387,0.05000,5.944
+31,self_attn.v_proj,0.0000005541,0.05000,5.782
+31,self_attn.q_proj,0.0000009006,0.05000,5.797
+31,self_attn.k_proj,0.0000003091,0.05000,5.814
+31,self_attn.o_proj,0.0000000074,0.05000,1.541
+31,mlp.gate_proj,0.0000037887,0.05000,2.776
+31,mlp.up_proj,0.0000029935,0.05000,2.782
+31,mlp.down_proj,0.0000000543,0.05000,5.973

quantize_config.json

@@ -0,0 +1,76 @@
+{
+  "bits": 8,
+  "dynamic": {
+    "+:.*\\.20\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.21\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.22\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.23\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.24\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.25\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.26\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.27\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.28\\..*": {
+      "bits": 4
+    },
+    "+:.*\\.29\\..*": {
+      "bits": 4
+    }
+  },
+  "group_size": 128,
+  "desc_act": false,
+  "lm_head": false,
+  "method": "gptq",
+  "quant_method": "gptq",
+  "format": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:6.0.3"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.05,
+    "damp_auto_increment": 0.01,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0,
+    "gptaq": null,
+    "foem": null,
+    "act_group_aware": true,
+    "fallback": {
+      "strategy": "rtn",
+      "threshold": "0.5%",
+      "smooth": null
+    },
+    "offload_to_disk": true,
+    "offload_to_disk_path": "./gptqmodel_offload/slyadpab-cehsqtyh/",
+    "pack_impl": "cpu",
+    "gc_mode": "interval",
+    "wait_for_submodule_finalizers": false,
+    "auto_forward_data_parallel": true,
+    "vram_strategy": "exclusive",
+    "mock_quantization": false,
+    "hessian": {
+      "chunk_size": null,
+      "chunk_bytes": null,
+      "staging_dtype": "float32"
+    }
+  },
+  "sym": true
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}