Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,134 @@
+{
+  "_name_or_path": "nvidia/Hymba-1.5B-Instruct",
+  "architectures": [
+    "HymbaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_hidden_size": -1,
+  "attn_implementation": "flex",
+  "attn_implementation_new": "flex",
+  "auto_map": {
+    "AutoConfig": "nvidia/Hymba-1.5B-Instruct--configuration_hymba.HymbaConfig",
+    "AutoModelForCausalLM": "nvidia/Hymba-1.5B-Instruct--modeling_hymba.HymbaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "calc_logits_for_entire_prompt": false,
+  "conv_dim": {
+    "0": 32,
+    "1": 32,
+    "2": 32
+  },
+  "eos_token_id": 2,
+  "global_attn_idx": [
+    0,
+    15,
+    31
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "kq_head_dim": -1,
+  "kq_norm": "none",
+  "kv_reuse_every_i_layer": -1,
+  "kv_reuse_group": [
+    [
+      1,
+      2
+    ],
+    [
+      3,
+      4
+    ],
+    [
+      5,
+      6
+    ],
+    [
+      7,
+      8
+    ],
+    [
+      9,
+      10
+    ],
+    [
+      11,
+      12
+    ],
+    [
+      13,
+      14
+    ],
+    [
+      16,
+      17,
+      18
+    ],
+    [
+      19,
+      20
+    ],
+    [
+      21,
+      22
+    ],
+    [
+      23,
+      24
+    ],
+    [
+      25,
+      26
+    ],
+    [
+      27,
+      28
+    ],
+    [
+      29,
+      30
+    ]
+  ],
+  "kv_weight_reuse": false,
+  "layer_type": [
+    "h",
+    "h",
+    "h"
+  ],
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 100,
+  "mamba_expand": 2,
+  "mamba_inner_layernorms": true,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 8192,
+  "memory_tokens_interspersed_every": 0,
+  "mlp_hidden_act": "silu",
+  "model_type": "hymba",
+  "num_attention_heads": 2,
+  "num_experts": 1,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 3,
+  "num_key_value_heads": 1,
+  "num_mamba": 1,
+  "num_memory_tokens": 128,
+  "orig_max_position_embeddings": 2048,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope": true,
+  "rope_theta": 10000.0,
+  "rope_type": "ntk",
+  "router_aux_loss_coef": 0.001,
+  "seq_length": 8192,
+  "sliding_window": 1024,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "use_mamba_kernels": true,
+  "v_head_dim": 16,
+  "vocab_size": 32001
+}

configuration_hymba.py

@@ -0,0 +1,116 @@
+import math
+from transformers.configuration_utils import PretrainedConfig
+
+
+class HymbaConfig(PretrainedConfig):
+
+    model_type = "hymba"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+            self,
+            vocab_size=65536,
+            tie_word_embeddings=False,
+            hidden_size=4096,
+            intermediate_size=14336,
+            num_hidden_layers=32,
+            num_attention_heads=32,
+            num_key_value_heads=8,
+            hidden_act="silu",
+            initializer_range=0.02,
+            rms_norm_eps=1e-6,
+            use_cache=True,
+            calc_logits_for_entire_prompt=False,
+            output_router_logits=False,
+            router_aux_loss_coef=0.001,
+            pad_token_id=0,
+            bos_token_id=1,
+            eos_token_id=2,
+            sliding_window=None,
+            max_position_embeddings=262144,
+            orig_max_position_embeddings=None,
+            attention_dropout=0.0,
+            num_experts_per_tok=2,
+            num_experts=16,
+            use_mamba_kernels=True,
+            mamba_d_state=16,
+            mamba_d_conv=4,
+            mamba_expand=2,
+            mamba_dt_rank="auto",
+            mamba_conv_bias=True,
+            mamba_proj_bias=False,
+            mamba_inner_layernorms=True,
+            kv_reuse_every_i_layer=-1,
+            kv_reuse_group=None,
+            kv_weight_reuse=False,
+            global_attn_idx=None,
+            num_mamba=1,
+            attn_implementation_new='sdpa',
+            rope_type=None,
+            **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.tie_word_embeddings = tie_word_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.sliding_window = sliding_window
+        self.max_position_embeddings = max_position_embeddings
+        self.orig_max_position_embeddings = orig_max_position_embeddings
+        self.attention_dropout = attention_dropout
+
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+
+        self.use_cache = use_cache
+        self.calc_logits_for_entire_prompt = calc_logits_for_entire_prompt
+        self.output_router_logits = output_router_logits
+        self.router_aux_loss_coef = router_aux_loss_coef
+
+        self.num_experts_per_tok = num_experts_per_tok
+        self.num_experts = num_experts
+
+        self.use_mamba_kernels = use_mamba_kernels
+        self.mamba_d_state = mamba_d_state
+        self.mamba_d_conv = mamba_d_conv
+        self.mamba_expand = mamba_expand
+        self.mamba_dt_rank = math.ceil(self.hidden_size / 16) if mamba_dt_rank == "auto" else mamba_dt_rank
+        self.mamba_conv_bias = mamba_conv_bias
+        self.mamba_proj_bias = mamba_proj_bias
+        self.mamba_inner_layernorms = mamba_inner_layernorms
+
+        self.attn_hidden_size = kwargs.pop("attn_hidden_size", -1)
+        self.kq_head_dim = kwargs.pop("kq_head_dim", -1)
+        self.v_head_dim = kwargs.pop("v_head_dim", -1)
+        self.kq_norm = kwargs.pop("kq_norm", None)
+        self.rope = kwargs.pop("rope", False)
+        self.rope_theta = kwargs.pop("rope_theta", 10000.0)
+        self.num_memory_tokens = kwargs.pop("num_memory_tokens", 0)
+        self.memory_tokens_interspersed_every = kwargs.pop("memory_tokens_interspersed_every", 0)
+
+        self.kv_reuse_every_i_layer = kv_reuse_every_i_layer
+        self.kv_reuse_group = kv_reuse_group
+        self.kv_weight_reuse = kv_weight_reuse
+
+        self.global_attn_idx = global_attn_idx
+
+        self.num_mamba = num_mamba
+
+        self.attn_implementation_new = attn_implementation_new
+
+        self.rope_type = rope_type
+        
+        
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.3",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0790172bf25b656f6f7638ef68d946d7da103930c637604908da09830de8e112
+size 1109368

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{'<extra_id_0>System'}}{% for message in messages %}{% if message['role'] == 'system' %}{{'\n' + message['content'].strip()}}{% if tools or contexts %}{{'\n'}}{% endif %}{% endif %}{% endfor %}{% if tools %}{% for tool in tools %}{{ '\n<tool> ' + tool|tojson + ' </tool>' }}{% endfor %}{% endif %}{% if contexts %}{% if tools %}{{'\n'}}{% endif %}{% for context in contexts %}{{ '\n<context> ' + context.strip() + ' </context>' }}{% endfor %}{% endif %}{{'\n\n'}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<extra_id_1>User\n' + message['content'].strip() + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<extra_id_1>Assistant\n' + message['content'].strip() + '\n' }}{% elif message['role'] == 'tool' %}{{ '<extra_id_1>Tool\n' + message['content'].strip() + '\n' }}{% endif %}{% endfor %}{%- if add_generation_prompt %}{{'<extra_id_1>Assistant\n'}}{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}