Add files using upload-large-folder tool

README.md

@@ -0,0 +1,8 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: mlx
+base_model: ai21labs/AI21-Jamba2-3B
+tags:
+- mlx
+---

chat_template.jinja

@@ -0,0 +1,66 @@
+{%- if bos_token is defined and bos_token is not none %}{{- bos_token -}}{%- endif %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages|length > 0 and messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages|length > 0 and messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif -%}

config.json

@@ -0,0 +1,41 @@
+{
+    "architectures": [
+        "JambaForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "attn_layer_offset": 7,
+    "attn_layer_period": 14,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 2,
+    "expert_layer_offset": 1,
+    "expert_layer_period": 2,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "mamba_conv_bias": true,
+    "mamba_d_conv": 4,
+    "mamba_d_state": 16,
+    "mamba_dt_rank": 160,
+    "mamba_expand": 2,
+    "mamba_proj_bias": false,
+    "max_position_embeddings": 262144,
+    "model_type": "jamba",
+    "num_attention_heads": 20,
+    "num_experts": 1,
+    "num_experts_per_tok": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 1,
+    "num_logits_to_keep": 1,
+    "output_router_logits": false,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "router_aux_loss_coef": 0.001,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "transformers_version": "4.56.1",
+    "use_cache": true,
+    "use_mamba_kernels": true,
+    "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.56.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fda780efaeb2f8250805b1239bf18316ee09a9b8c842e4a48c897377bbb0648
+size 5349850299

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0dd2e948be8e63780f65a1eb77e3c0429fd97a8bb64a1292b4d4d35f34bee7
+size 708876485

model.safetensors.index.json

@@ -0,0 +1,470 @@
+{
+    "metadata": {
+        "total_size": 6058674944,
+        "total_parameters": 3027074432
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.A_log": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.D": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.A_log": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.D": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.A_log": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.D": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.3.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.A_log": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.D": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors"
+    }
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "json_tools",
+  "unk_token": "<|unk|>",
+  "use_default_system_prompt": false
+}