Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "nvidia/Nemotron-H-4B-Instruct",
+  "architectures": [
+    "NemotronHForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_head_dim": 128,
+  "auto_map": {
+    "AutoConfig": "configuration_nemotron_h.NemotronHConfig",
+    "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
+  },
+  "bos_token_id": 1,
+  "chunk_size": 256,
+  "conv_kernel": 4,
+  "eos_token_id": 2,
+  "expand": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 3072,
+  "hybrid_override_pattern": "M-M-M-M*-M-M-M-M-M*-M-M-M-M-M*-M-M-M-M-M*-M-M-M-M-M-",
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_norm_epsilon": 1e-05,
+  "mamba_head_dim": 64,
+  "mamba_hidden_act": "silu",
+  "mamba_num_heads": 112,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_hidden_act": "relu2",
+  "model_type": "nemotron_h",
+  "n_groups": 8,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 52,
+  "num_key_value_heads": 8,
+  "num_logits_to_keep": 1,
+  "pad_token_id": 0,
+  "rescale_prenorm_residual": true,
+  "residual_in_fp32": false,
+  "rms_norm_eps": 1e-05,
+  "sliding_window": null,
+  "ssm_state_size": 128,
+  "tie_word_embeddings": false,
+  "time_step_floor": 0.0001,
+  "time_step_limit": [
+    0.0,
+    Infinity
+  ],
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 192,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "use_mamba_kernels": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [2, 11],
+  "pad_token_id": 0,
+  "transformers_version": "4.48.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ec45e9fe138d04e0e89900ca952d673837984b66f7809c7ed5cb7eb742b611
+size 4994177904

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9377b88ee9b8007cd9b955b5d2d7820b7214799806d96984c1f3126f8b5db13e
+size 3984302576

model.safetensors.index.json

@@ -0,0 +1,318 @@
+{
+  "metadata": {
+    "total_size": 8978446080
+  },
+  "weight_map": {
+    "backbone.embeddings.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.0.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.1.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.1.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.1.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.10.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.10.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.10.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.11.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.12.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.12.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.12.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.13.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.14.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.14.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.14.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.15.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.16.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.16.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.16.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.17.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.18.mixer.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.18.mixer.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.18.mixer.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.18.mixer.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.18.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.19.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.19.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.19.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.2.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.20.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.21.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.21.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.21.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.22.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.23.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.23.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.23.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.24.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.25.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.25.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.25.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.26.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.27.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.27.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.27.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.28.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.29.mixer.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.29.mixer.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.29.mixer.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.29.mixer.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.29.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.3.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.3.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.3.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.30.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.30.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.30.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.31.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.31.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.31.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.31.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.31.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.31.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.31.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.31.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.32.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.32.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.32.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.33.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.34.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.34.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.34.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.35.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.36.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.36.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.36.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.37.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.38.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.38.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.38.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.39.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.4.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.4.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.4.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.4.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.4.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.40.mixer.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.40.mixer.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.40.mixer.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.40.mixer.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.40.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.41.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.41.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.41.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.42.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.43.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.43.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.43.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.44.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.45.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.45.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.45.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.46.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.47.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.47.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.47.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.48.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.49.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.49.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.49.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.5.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.5.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.5.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.50.mixer.A_log": "model-00002-of-00002.safetensors",
+    "backbone.layers.50.mixer.D": "model-00002-of-00002.safetensors",
+    "backbone.layers.50.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.50.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.50.mixer.dt_bias": "model-00002-of-00002.safetensors",
+    "backbone.layers.50.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.50.mixer.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.50.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.50.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.51.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.51.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.51.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.layers.6.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.6.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.6.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.6.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.6.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.7.mixer.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.7.mixer.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.7.mixer.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.7.mixer.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.7.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.8.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.8.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.8.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.mixer.A_log": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.mixer.D": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.mixer.dt_bias": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.mixer.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.layers.9.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.norm_f.weight": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3277c00fe5fb3963b3cb7c07b7f183722d2af4d775a4aea7cfb3684d7cccbc2f
+size 17078330