Upload folder using huggingface_hub

config.json

@@ -0,0 +1,44 @@
+{
+  "architectures": [
+    "JambaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_layer_offset": 7,
+  "attn_layer_period": 14,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    2,
+    519
+  ],
+  "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 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 519,
+  "pad_token_id": 0,
+  "transformers_version": "4.56.1",
+  "temparature": 0.6
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ac70f54ada6b7387e67507d79fe1c50d2a76bd1d72863ac6e913f6905c3fba
+size 4975539312

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:033c382dc546b7883889c15c772a1c90fe23e490a4515d07d0269ab2b5b8187a
+size 1418731960

model.safetensors.index.json

@@ -0,0 +1,471 @@
+{
+  "metadata": {
+    "total_parameters": 3197109632,
+    "total_size": 6394219264
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00002.safetensors",
+    "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-00002-of-00002.safetensors",
+    "model.layers.0.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mamba.conv1d.bias": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.1.mamba.D": "model-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.11.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.11.mamba.dt_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.13.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mamba.A_log": "model-00002-of-00002.safetensors",
+    "model.layers.13.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.13.mamba.b_layernorm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.13.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.pre_ff_layernorm.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.16.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mamba.c_layernorm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.16.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mamba.x_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.17.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mamba.dt_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.18.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mamba.dt_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.19.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mamba.c_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.19.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.pre_ff_layernorm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.2.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mamba.dt_proj.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.2.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.feed_forward.down_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.20.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.down_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.22.mamba.x_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.23.mamba.conv1d.bias": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.23.mamba.out_proj.weight": "model-00002-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-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-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-00002-of-00002.safetensors",
+    "model.layers.24.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mamba.conv1d.bias": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.24.mamba.dt_proj.weight": "model-00002-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-00001-of-00002.safetensors",
+    "model.layers.25.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.25.mamba.D": "model-00002-of-00002.safetensors",
+    "model.layers.25.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mamba.c_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.25.mamba.dt_proj.bias": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.25.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.feed_forward.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.27.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.27.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mamba.in_proj.weight": "model-00001-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-00002-of-00002.safetensors",
+    "model.layers.3.feed_forward.up_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.3.mamba.conv1d.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.5.feed_forward.gate_proj.weight": "model-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.5.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.pre_ff_layernorm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.6.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mamba.dt_proj.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
+    "model.layers.8.mamba.x_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,258 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "518": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "519": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "520": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "521": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "522": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "523": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "524": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "525": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "526": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "527": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "528": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "529": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "530": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "531": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "532": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "533": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "534": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "535": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "536": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "537": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "538": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "539": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "540": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "541": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "542": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<|unk|>",
+  "use_default_system_prompt": false,
+  "chat_template": "\n{%- set thinking_prefix = thinking_prefix or 'Begin by thinking about the reasoning process in the mind within <think> </think> tags and then proceed to give your response.\\n' -%}\n\n{%- if bos_token is defined and bos_token is not none %}{{- bos_token -}}{%- endif %}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages|length > 0 and messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages|length > 0 and messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {%- set prefix = '' %}\n        {%- if message.role == 'user' and '<think>' not in message.content %}\n            {%- if loop.last %}\n                {%- set prefix = thinking_prefix %}\n            {%- endif %}\n            {%- if not loop.last %}\n                {%- if loop.nextitem.role == 'assistant' and loop.nextitem.content.startswith('<think>') or loop.nextitem.reasoning_content is defined and loop.nextitem.reasoning_content is not none %}\n                    {%- set prefix = thinking_prefix %}\n                {%- endif %}\n            {%- endif %}\n        {%- endif %}\n        {%- if message.role == 'user' and not loop.last and loop.nextitem.role == 'assistant' and loop.nextitem.content.startswith('<think>') and '<think>' not in message.content %}\n            {%- set prefix = thinking_prefix %}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role + '\\n' + prefix + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if reasoning_content %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {{- '<think>\\n' }}\n{%- endif -%}"
+}