Upload 9 files

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if 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[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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if true %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+        {%- endif %}
+        {%- 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' }}
+        {{- 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' }}
+    {%- if open_thinking is defined and open_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "MiniMindOmni"
+  ],
+  "audio_hidden_size": 512,
+  "audio_ids": [
+    16
+  ],
+  "audio_pad_token": 2049,
+  "audio_special_token": "<|audio_pad|>",
+  "audio_spk_token": 2051,
+  "audio_stop_token": 2050,
+  "audio_vocab_size": 2112,
+  "auto_map": {
+    "AutoConfig": "model_omni.OmniConfig",
+    "AutoModelForCausalLM": "model_omni.MiniMindOmni"
+  },
+  "bos_token_id": 1,
+  "bridge_layer": 3,
+  "dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "flash_attn": true,
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "image_hidden_size": 768,
+  "image_ids": [
+    12
+  ],
+  "image_special_token": "<|image_pad|>",
+  "image_token_len": 64,
+  "inference_rope_scaling": false,
+  "intermediate_size": 2432,
+  "max_position_embeddings": 32768,
+  "model_type": "minimind-o",
+  "moe_intermediate_size": 2432,
+  "norm_topk_prob": true,
+  "num_attention_heads": 8,
+  "num_experts": 4,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 4,
+  "num_talker_hidden_layers": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.0005,
+  "spk_emb_size": 192,
+  "talker_hidden_size": 768,
+  "think_end_ids": [
+    26,
+    234,
+    234
+  ],
+  "transformers_version": "4.57.6",
+  "use_moe": false,
+  "vocab_size": 6400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.6"
+}

model_minimind.py

@@ -0,0 +1,287 @@
+import math, torch, torch.nn.functional as F
+from torch import nn
+from transformers.activations import ACT2FN
+from transformers import PreTrainedModel, GenerationMixin, PretrainedConfig
+from transformers.modeling_outputs import MoeCausalLMOutputWithPast
+
+# 🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏
+#                                     MiniMind Config
+# 🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏
+class MiniMindConfig(PretrainedConfig):
+    model_type = "minimind"
+    def __init__(self, hidden_size=768, num_hidden_layers=8, use_moe=False, **kwargs):
+        super().__init__(**kwargs)
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.use_moe = use_moe
+        self.dropout = kwargs.get("dropout", 0.0)
+        self.vocab_size = kwargs.get("vocab_size", 6400)
+        self.bos_token_id = kwargs.get("bos_token_id", 1)
+        self.eos_token_id = kwargs.get("eos_token_id", 2)
+        self.flash_attn = kwargs.get("flash_attn", True)
+        self.num_attention_heads = kwargs.get("num_attention_heads", 8)
+        self.num_key_value_heads = kwargs.get("num_key_value_heads", 4)
+        self.head_dim = kwargs.get("head_dim", self.hidden_size // self.num_attention_heads)
+        self.hidden_act = kwargs.get("hidden_act", 'silu')
+        self.intermediate_size = kwargs.get("intermediate_size", math.ceil(hidden_size * math.pi / 64) * 64)
+        self.max_position_embeddings = kwargs.get("max_position_embeddings", 32768)
+        self.rms_norm_eps = kwargs.get("rms_norm_eps", 1e-6)
+        self.rope_theta = kwargs.get("rope_theta", 1e6)
+        self.tie_word_embeddings = kwargs.get("tie_word_embeddings", True)
+        self.inference_rope_scaling = kwargs.get("inference_rope_scaling", False)
+        self.rope_scaling = {
+            "beta_fast": 32,
+            "beta_slow": 1,
+            "factor": 16,
+            "original_max_position_embeddings": 2048,
+            "attention_factor": 1.0,
+            "type": "yarn"
+        } if self.inference_rope_scaling else None
+        ### MoE specific configs (ignored if use_moe = False)
+        self.num_experts = kwargs.get("num_experts", 4)
+        self.num_experts_per_tok = kwargs.get("num_experts_per_tok", 1)
+        self.moe_intermediate_size = kwargs.get("moe_intermediate_size", self.intermediate_size)
+        self.norm_topk_prob = kwargs.get("norm_topk_prob", True)
+        self.router_aux_loss_coef = kwargs.get("router_aux_loss_coef", 5e-4)
+
+# 🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏
+#                                     MiniMind Model
+# 🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏🌎🌍🌏
+class RMSNorm(torch.nn.Module):
+    def __init__(self, dim: int, eps: float = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.weight = nn.Parameter(torch.ones(dim))
+
+    def norm(self, x):
+        return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
+
+    def forward(self, x):
+        return (self.weight * self.norm(x.float())).type_as(x)
+
+def precompute_freqs_cis(dim: int, end: int = int(32 * 1024), rope_base: float = 1e6, rope_scaling: dict = None):
+    freqs, attn_factor = 1.0 / (rope_base ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim)), 1.0
+    if rope_scaling is not None: # YaRN: f'(i) = f(i)((1-γ) + γ/s), where γ∈[0,1] is linear ramp
+        orig_max, factor, beta_fast, beta_slow, attn_factor = (
+            rope_scaling.get("original_max_position_embeddings", 2048), rope_scaling.get("factor", 16),
+            rope_scaling.get("beta_fast", 32.0), rope_scaling.get("beta_slow", 1.0), rope_scaling.get("attention_factor", 1.0)
+        )
+        if end / orig_max > 1.0:
+            inv_dim = lambda b: (dim * math.log(orig_max / (b * 2 * math.pi))) / (2 * math.log(rope_base))
+            low, high = max(math.floor(inv_dim(beta_fast)), 0), min(math.ceil(inv_dim(beta_slow)), dim // 2 - 1)
+            ramp = torch.clamp((torch.arange(dim // 2, device=freqs.device).float() - low) / max(high - low, 0.001), 0, 1)
+            freqs = freqs * (1 - ramp + ramp / factor)
+    t = torch.arange(end, device=freqs.device)
+    freqs = torch.outer(t, freqs).float()
+    freqs_cos = torch.cat([torch.cos(freqs), torch.cos(freqs)], dim=-1) * attn_factor
+    freqs_sin = torch.cat([torch.sin(freqs), torch.sin(freqs)], dim=-1) * attn_factor
+    return freqs_cos, freqs_sin
+
+def apply_rotary_pos_emb(q, k, cos, sin, unsqueeze_dim=1):
+    def rotate_half(x): return torch.cat((-x[..., x.shape[-1] // 2:], x[..., : x.shape[-1] // 2]), dim=-1)
+    q_embed = ((q * cos.unsqueeze(unsqueeze_dim)) + (rotate_half(q) * sin.unsqueeze(unsqueeze_dim))).to(q.dtype)
+    k_embed = ((k * cos.unsqueeze(unsqueeze_dim)) + (rotate_half(k) * sin.unsqueeze(unsqueeze_dim))).to(k.dtype)
+    return q_embed, k_embed
+
+def repeat_kv(x: torch.Tensor, n_rep: int) -> torch.Tensor:
+    bs, slen, num_key_value_heads, head_dim = x.shape
+    if n_rep == 1: return x
+    return (x[:, :, :, None, :].expand(bs, slen, num_key_value_heads, n_rep, head_dim).reshape(bs, slen, num_key_value_heads * n_rep, head_dim))
+
+class Attention(nn.Module):
+    def __init__(self, config: MiniMindConfig):
+        super().__init__()
+        self.num_key_value_heads = config.num_attention_heads if config.num_key_value_heads is None else config.num_key_value_heads
+        self.n_local_heads = config.num_attention_heads
+        self.n_local_kv_heads = self.num_key_value_heads
+        self.n_rep = self.n_local_heads // self.n_local_kv_heads
+        self.head_dim = config.head_dim
+        self.is_causal = True
+        self.q_proj = nn.Linear(config.hidden_size, config.num_attention_heads * self.head_dim, bias=False)
+        self.k_proj = nn.Linear(config.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
+        self.v_proj = nn.Linear(config.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
+        self.o_proj = nn.Linear(config.num_attention_heads * self.head_dim, config.hidden_size, bias=False)
+        self.q_norm = RMSNorm(self.head_dim, eps=config.rms_norm_eps)
+        self.k_norm = RMSNorm(self.head_dim, eps=config.rms_norm_eps)
+        self.attn_dropout = nn.Dropout(config.dropout)
+        self.resid_dropout = nn.Dropout(config.dropout)
+        self.dropout = config.dropout
+        self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention') and config.flash_attn
+
+    def forward(self, x, position_embeddings, past_key_value=None, use_cache=False, attention_mask=None):
+        bsz, seq_len, _ = x.shape
+        xq, xk, xv = self.q_proj(x), self.k_proj(x), self.v_proj(x)
+        xq = xq.view(bsz, seq_len, self.n_local_heads, self.head_dim)
+        xk = xk.view(bsz, seq_len, self.n_local_kv_heads, self.head_dim)
+        xv = xv.view(bsz, seq_len, self.n_local_kv_heads, self.head_dim)
+        xq, xk = self.q_norm(xq), self.k_norm(xk)
+        cos, sin = position_embeddings
+        xq, xk = apply_rotary_pos_emb(xq, xk, cos, sin)
+        if past_key_value is not None:
+            xk = torch.cat([past_key_value[0], xk], dim=1)
+            xv = torch.cat([past_key_value[1], xv], dim=1)
+        past_kv = (xk, xv) if use_cache else None
+        xq, xk, xv = (xq.transpose(1, 2), repeat_kv(xk, self.n_rep).transpose(1, 2), repeat_kv(xv, self.n_rep).transpose(1, 2))
+        if self.flash and (seq_len > 1) and (not self.is_causal or past_key_value is None) and (attention_mask is None or torch.all(attention_mask == 1)):
+            output = F.scaled_dot_product_attention(xq, xk, xv, dropout_p=self.dropout if self.training else 0.0, is_causal=self.is_causal)
+        else:
+            scores = (xq @ xk.transpose(-2, -1)) / math.sqrt(self.head_dim)
+            if self.is_causal: scores[:, :, :, -seq_len:] += torch.full((seq_len, seq_len), float("-inf"), device=scores.device).triu(1)
+            if attention_mask is not None: scores += (1.0 - attention_mask.unsqueeze(1).unsqueeze(2)) * -1e9
+            output = self.attn_dropout(F.softmax(scores.float(), dim=-1).type_as(xq)) @ xv
+        output = output.transpose(1, 2).reshape(bsz, seq_len, -1)
+        output = self.resid_dropout(self.o_proj(output))
+        return output, past_kv
+
+class FeedForward(nn.Module):
+    def __init__(self, config: MiniMindConfig, intermediate_size: int = None):
+        super().__init__()
+        intermediate_size = intermediate_size or config.intermediate_size
+        self.gate_proj = nn.Linear(config.hidden_size, intermediate_size, bias=False)
+        self.down_proj = nn.Linear(intermediate_size, config.hidden_size, bias=False)
+        self.up_proj = nn.Linear(config.hidden_size, intermediate_size, bias=False)
+        self.act_fn = ACT2FN[config.hidden_act]
+
+    def forward(self, x):
+        return self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
+
+class MOEFeedForward(nn.Module):
+    def __init__(self, config: MiniMindConfig):
+        super().__init__()
+        self.config = config
+        self.gate = nn.Linear(config.hidden_size, config.num_experts, bias=False)
+        self.experts = nn.ModuleList([FeedForward(config, intermediate_size=config.moe_intermediate_size) for _ in range(config.num_experts)])
+        self.act_fn = ACT2FN[config.hidden_act]
+
+    def forward(self, x):
+        batch_size, seq_len, hidden_dim = x.shape
+        x_flat = x.view(-1, hidden_dim)
+        scores = F.softmax(self.gate(x_flat), dim=-1)
+        topk_weight, topk_idx = torch.topk(scores, k=self.config.num_experts_per_tok, dim=-1, sorted=False)
+        if self.config.norm_topk_prob: topk_weight = topk_weight / (topk_weight.sum(dim=-1, keepdim=True) + 1e-20)
+        y = torch.zeros_like(x_flat)
+        for i, expert in enumerate(self.experts):
+            mask = (topk_idx == i)
+            if mask.any():
+                token_idx = mask.any(dim=-1).nonzero().flatten()
+                weight = topk_weight[mask].view(-1, 1)
+                y.index_add_(0, token_idx, (expert(x_flat[token_idx]) * weight).to(y.dtype))
+            elif self.training:
+                y[0, 0] += 0 * sum(p.sum() for p in expert.parameters())
+        if self.training and self.config.router_aux_loss_coef > 0:
+            load = F.one_hot(topk_idx, self.config.num_experts).float().mean(0)
+            self.aux_loss = (load * scores.mean(0)).sum() * self.config.num_experts * self.config.router_aux_loss_coef
+        else:
+            self.aux_loss = scores.new_zeros(1).squeeze()
+        return y.view(batch_size, seq_len, hidden_dim)
+
+class MiniMindBlock(nn.Module):
+    def __init__(self, layer_id: int, config: MiniMindConfig):
+        super().__init__()
+        self.self_attn = Attention(config)
+        self.input_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.post_attention_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.mlp = FeedForward(config) if not config.use_moe else MOEFeedForward(config)
+
+    def forward(self, hidden_states, position_embeddings, past_key_value=None, use_cache=False, attention_mask=None):
+        residual = hidden_states
+        hidden_states, present_key_value = self.self_attn(
+            self.input_layernorm(hidden_states), position_embeddings,
+            past_key_value, use_cache, attention_mask
+        )
+        hidden_states += residual
+        hidden_states = hidden_states + self.mlp(self.post_attention_layernorm(hidden_states))
+        return hidden_states, present_key_value
+
+class MiniMindModel(nn.Module):
+    def __init__(self, config: MiniMindConfig):
+        super().__init__()
+        self.config = config
+        self.vocab_size, self.num_hidden_layers = config.vocab_size, config.num_hidden_layers
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size)
+        self.dropout = nn.Dropout(config.dropout)
+        self.layers = nn.ModuleList([MiniMindBlock(l, config) for l in range(self.num_hidden_layers)])
+        self.norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        freqs_cos, freqs_sin = precompute_freqs_cis(dim=config.head_dim, end=config.max_position_embeddings, rope_base=config.rope_theta, rope_scaling=config.rope_scaling)
+        self.register_buffer("freqs_cos", freqs_cos, persistent=False)
+        self.register_buffer("freqs_sin", freqs_sin, persistent=False)
+
+    def forward(self, input_ids, attention_mask=None, past_key_values=None, use_cache=False, **kwargs):
+        batch_size, seq_length = input_ids.shape
+        if hasattr(past_key_values, 'layers'): past_key_values = None
+        past_key_values = past_key_values or [None] * len(self.layers)
+        start_pos = past_key_values[0][0].shape[1] if past_key_values[0] is not None else 0
+        hidden_states = self.dropout(self.embed_tokens(input_ids))
+        # Recompute RoPE buffers lost during meta-device init (transformers>=5.x)
+        if self.freqs_cos[0, 0] == 0:
+            freqs_cos, freqs_sin = precompute_freqs_cis(dim=self.config.head_dim, end=self.config.max_position_embeddings, rope_base=self.config.rope_theta, rope_scaling=self.config.rope_scaling)
+            self.freqs_cos, self.freqs_sin = freqs_cos.to(hidden_states.device), freqs_sin.to(hidden_states.device)
+        position_embeddings = (self.freqs_cos[start_pos:start_pos + seq_length], self.freqs_sin[start_pos:start_pos + seq_length])
+        presents = []
+        for layer, past_key_value in zip(self.layers, past_key_values):
+            hidden_states, present = layer(
+                hidden_states,
+                position_embeddings,
+                past_key_value=past_key_value,
+                use_cache=use_cache,
+                attention_mask=attention_mask
+            )
+            presents.append(present)
+        hidden_states = self.norm(hidden_states)
+        aux_loss = sum([l.mlp.aux_loss for l in self.layers if isinstance(l.mlp, MOEFeedForward)], hidden_states.new_zeros(1).squeeze())
+        return hidden_states, presents, aux_loss
+
+class MiniMindForCausalLM(PreTrainedModel, GenerationMixin):
+    config_class = MiniMindConfig
+    _tied_weights_keys = {"lm_head.weight": "model.embed_tokens.weight"}
+    def __init__(self, config: MiniMindConfig = None):
+        self.config = config or MiniMindConfig()
+        super().__init__(self.config)
+        self.model = MiniMindModel(self.config)
+        self.lm_head = nn.Linear(self.config.hidden_size, self.config.vocab_size, bias=False)
+        if self.config.tie_word_embeddings: self.model.embed_tokens.weight = self.lm_head.weight
+        self.post_init()
+
+    def forward(self, input_ids, attention_mask=None, past_key_values=None, use_cache=False, logits_to_keep=0, labels=None, **kwargs):
+        hidden_states, past_key_values, aux_loss = self.model(input_ids, attention_mask, past_key_values, use_cache, **kwargs)
+        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
+        logits = self.lm_head(hidden_states[:, slice_indices, :])
+        loss = None
+        if labels is not None:
+            x, y = logits[..., :-1, :].contiguous(), labels[..., 1:].contiguous()
+            loss = F.cross_entropy(x.view(-1, x.size(-1)), y.view(-1), ignore_index=-100)
+        return MoeCausalLMOutputWithPast(loss=loss, aux_loss=aux_loss, logits=logits, past_key_values=past_key_values, hidden_states=hidden_states)
+    
+    # https://github.com/jingyaogong/minimind/discussions/611
+    @torch.inference_mode()
+    def generate(self, inputs=None, attention_mask=None, max_new_tokens=8192, temperature=0.85, top_p=0.85, top_k=50, eos_token_id=2, streamer=None, use_cache=True, num_return_sequences=1, do_sample=True, repetition_penalty=1.0, **kwargs):
+        input_ids = kwargs.pop("input_ids", inputs).repeat(num_return_sequences, 1)
+        attention_mask = attention_mask.repeat(num_return_sequences, 1) if attention_mask is not None else None
+        past_key_values = kwargs.pop("past_key_values", None)
+        finished = torch.zeros(input_ids.shape[0], dtype=torch.bool, device=input_ids.device)
+        if streamer: streamer.put(input_ids.cpu())
+        for _ in range(max_new_tokens):
+            past_len = past_key_values[0][0].shape[1] if past_key_values else 0
+            outputs = self.forward(input_ids[:, past_len:], attention_mask, past_key_values, use_cache=use_cache, **kwargs)
+            attention_mask = torch.cat([attention_mask, attention_mask.new_ones(attention_mask.shape[0], 1)], -1) if attention_mask is not None else None
+            logits = outputs.logits[:, -1, :] / temperature
+            if repetition_penalty != 1.0:
+                for i in range(input_ids.shape[0]): logits[i, torch.unique(input_ids[i])] /= repetition_penalty
+            if top_k > 0: 
+                logits[logits < torch.topk(logits, top_k)[0][..., -1, None]] = -float('inf')
+            if top_p < 1.0:
+                sorted_logits, sorted_indices = torch.sort(logits, descending=True)
+                mask = torch.cumsum(torch.softmax(sorted_logits, dim=-1), dim=-1) > top_p
+                mask[..., 1:], mask[..., 0] = mask[..., :-1].clone(), 0
+                logits[mask.scatter(1, sorted_indices, mask)] = -float('inf')
+            next_token = torch.multinomial(torch.softmax(logits, dim=-1), num_samples=1) if do_sample else torch.argmax(logits, dim=-1, keepdim=True)
+            if eos_token_id is not None: next_token = torch.where(finished.unsqueeze(-1), next_token.new_full((next_token.shape[0], 1), eos_token_id), next_token)
+            input_ids = torch.cat([input_ids, next_token], dim=-1)
+            past_key_values = outputs.past_key_values if use_cache else None
+            if streamer: streamer.put(next_token.cpu())
+            if eos_token_id is not None:
+                finished |= next_token.squeeze(-1).eq(eos_token_id)
+                if finished.all(): break
+        if streamer: streamer.end()
+        if kwargs.get("return_kv"): return {'generated_ids': input_ids, 'past_kv': past_key_values}
+        return input_ids

model_omni.py

@@ -0,0 +1,461 @@
+import os, math, torch, soundfile as sf, librosa, warnings, numpy as np, onnxruntime as ort, logging, contextlib, io
+from types import SimpleNamespace
+from torch import nn
+from torch.nn import functional as F
+from transformers.modeling_outputs import MoeCausalLMOutputWithPast
+from transformers import SiglipImageProcessor, SiglipVisionModel, logging as hf_logging
+from .model_minimind import *
+
+
+class OmniConfig(MiniMindConfig):
+    model_type = "minimind-o"
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.num_talker_hidden_layers = kwargs.get("num_talker_hidden_layers", 4)
+        self.talker_hidden_size = kwargs.get("talker_hidden_size", 768)
+        self.audio_ids = kwargs.get("audio_ids", [16]) # "<|audio_pad|>" token id
+        self.audio_special_token = kwargs.get("audio_special_token", "<|audio_pad|>")
+        self.audio_hidden_size = kwargs.get("audio_hidden_size", 512)
+        self.audio_vocab_size = kwargs.get("audio_vocab_size", 2112)
+        self.audio_pad_token = kwargs.get("audio_pad_token", 2049)
+        self.audio_stop_token = kwargs.get("audio_stop_token", 2050)
+        self.audio_spk_token = kwargs.get("audio_spk_token", 2051)
+        self.spk_emb_size = kwargs.get("spk_emb_size", 192)
+        self.think_end_ids = kwargs.get("think_end_ids", [26, 234, 234]) # </think>\n\n
+        self.image_ids = kwargs.get("image_ids", [12]) # "<|image_pad|>" token id
+        self.image_special_token = kwargs.get("image_special_token", "<|image_pad|>")
+        self.image_hidden_size = kwargs.get("image_hidden_size", 768)
+        self.image_token_len = kwargs.get("image_token_len", 64)
+        self.bridge_layer = kwargs.get("bridge_layer", self.num_hidden_layers // 2 - 1)
+
+class MMAudioProjector(nn.Module):
+    def __init__(self, in_dim, out_dim):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            nn.LayerNorm(in_dim),
+            nn.Linear(in_dim, out_dim),
+            nn.GELU(),
+            nn.Linear(out_dim, out_dim),
+        )
+    def forward(self, x):
+        return self.mlp(x)
+
+
+class MMVisionProjector(nn.Module):
+    def __init__(self, in_dim, out_dim, source_tokens=64, target_tokens=64):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            nn.LayerNorm(in_dim),
+            nn.Linear(in_dim, out_dim),
+            nn.GELU(),
+            nn.Linear(out_dim, out_dim),
+        )
+    def forward(self, x):
+        return self.mlp(x)
+
+
+class TalkerHead(nn.Module):
+    def __init__(self, in_features, out_features, num_layers=8, rank=256):
+        super().__init__()
+        self.num_layers = num_layers
+        self.base = nn.Linear(in_features, out_features, bias=False)
+        self.adapters = nn.ModuleList([nn.Sequential(nn.Linear(in_features, rank, bias=False), nn.GELU(), nn.Linear(rank, out_features, bias=False)) for _ in range(num_layers)])
+    def forward(self, x):
+        base_out = self.base(x)
+        return [base_out + adapter(x) for adapter in self.adapters]
+
+
+class TalkerEmbedding(nn.Module):
+    def __init__(self, num_embeddings, embedding_dim, num_layers=8, rank=256):
+        super().__init__()
+        self.num_layers = num_layers
+        self.base = nn.Embedding(num_embeddings, embedding_dim)
+        self.adapters = nn.ModuleList([nn.Sequential(nn.Embedding(num_embeddings, rank), nn.GELU(), nn.Linear(rank, embedding_dim, bias=False)) for _ in range(num_layers)])
+    def forward(self, x):
+        base_out = self.base(x)
+        return sum(base_out[:, i, :] + self.adapters[i](x[:, i, :]) for i in range(len(self.adapters))) / self.num_layers
+
+class SenseVoiceAudioProcessor:
+    def __init__(self, frontend): self.frontend = frontend
+    def __call__(self, wav, sampling_rate=16000, return_tensors="pt", return_attention_mask=True, **kwargs):
+        if isinstance(wav, np.ndarray): wav = torch.from_numpy(wav).float()
+        if wav.dim() == 1: wav = wav.unsqueeze(0)
+        with torch.no_grad():
+            fbank, flen = self.frontend(wav, torch.tensor([wav.size(1)]))
+        return SimpleNamespace(input_features=fbank, attention_mask=(torch.arange(fbank.size(1)) < flen[0]).long().unsqueeze(0))
+
+
+class TalkerModule(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.talker_config = MiniMindConfig(hidden_size=config.talker_hidden_size, use_moe=config.use_moe)
+        self.layers = nn.ModuleList([MiniMindBlock(l, self.talker_config) for l in range(config.num_talker_hidden_layers)])
+        self.norm = RMSNorm(config.talker_hidden_size, eps=config.rms_norm_eps)
+        self.lm_head = TalkerHead(config.talker_hidden_size, config.audio_vocab_size)
+        self.embed_tokens = TalkerEmbedding(config.audio_vocab_size, config.talker_hidden_size)
+        self.codec_proj = nn.Sequential(nn.Linear(config.talker_hidden_size, config.talker_hidden_size), nn.GELU(), nn.Linear(config.talker_hidden_size, config.talker_hidden_size), RMSNorm(config.talker_hidden_size, eps=config.rms_norm_eps))
+        self.embed_proj = nn.Sequential(nn.Linear(config.hidden_size, config.hidden_size), nn.GELU(), nn.Linear(config.hidden_size, config.talker_hidden_size), RMSNorm(config.talker_hidden_size, eps=config.rms_norm_eps))
+        self.text_scale, self.audio_scale = nn.Parameter(torch.tensor(3.0)), nn.Parameter(torch.tensor(1.0))
+        self.spk_proj = nn.Linear(config.spk_emb_size, config.talker_hidden_size, bias=False)
+        freqs_cos, freqs_sin = precompute_freqs_cis(dim=self.talker_config.head_dim, end=config.max_position_embeddings, rope_base=config.rope_theta, rope_scaling=config.rope_scaling)
+        self.register_buffer("freqs_cos", freqs_cos, persistent=False)
+        self.register_buffer("freqs_sin", freqs_sin, persistent=False)
+
+
+class MiniMindOmni(MiniMindForCausalLM):
+    config_class = OmniConfig
+    def __init__(self, config: OmniConfig = None, audio_encoder_path=None, vision_model_path=None):
+        config = config or OmniConfig()
+        super().__init__(config)
+        object.__setattr__(self, 'thinker', self.model)  # alias: self.thinker == self.model
+        object.__setattr__(self.model, 'lm_head', self.lm_head)  # alias: self.thinker.lm_head == self.lm_head
+        self.talker = TalkerModule(config)
+        self.audio_proj = MMAudioProjector(config.audio_hidden_size, config.hidden_size)
+        self.vision_proj = MMVisionProjector(config.image_hidden_size, config.hidden_size, target_tokens=config.image_token_len)
+        self.audio_pad_token, self.audio_stop_token, self.audio_spk_token = config.audio_pad_token, config.audio_stop_token, config.audio_spk_token
+        audio_encoder, audio_processor = self.load_sensevoice(audio_encoder_path) if audio_encoder_path else (None, None)
+        object.__setattr__(self, 'audio_encoder', audio_encoder)
+        object.__setattr__(self, 'audio_processor', audio_processor)
+        vision_encoder, vision_processor = self.load_vision(vision_model_path) if vision_model_path else (None, None)
+        object.__setattr__(self, 'vision_encoder', vision_encoder)
+        object.__setattr__(self, 'vision_processor', vision_processor)
+
+    @staticmethod
+    def load_sensevoice(path):
+        if not os.path.exists(path):
+            warnings.warn(f"[MiniMindOmni] SenseVoice path not found: {path}")
+            return None, None
+        logging.getLogger().setLevel(logging.ERROR)
+        hf_logging.set_verbosity_error()
+        with contextlib.redirect_stdout(io.StringIO()):
+            from funasr import AutoModel
+            m = AutoModel(model=path, trust_remote_code=True, disable_update=True, device="cpu")
+        encoder, frontend = m.model.encoder, m.kwargs["frontend"]
+        for p in encoder.parameters(): p.requires_grad = False
+        return encoder.eval().float(), SenseVoiceAudioProcessor(frontend.eval())
+
+    @torch.compiler.disable
+    def encode_audio_inputs(self, audio_inputs, audio_lens=None):
+        if (audio_inputs is None) or (self.audio_encoder is None) or (not audio_inputs.any()): return None
+        batch_mask = audio_inputs.flatten(1).any(1)
+        enc_dtype = next(self.audio_encoder.parameters()).dtype
+        valid_fbank = audio_inputs[batch_mask].to(dtype=enc_dtype)
+        if audio_lens is not None:
+            valid_lens = audio_lens[batch_mask].to(valid_fbank.device)
+        else:
+            valid_lens = torch.tensor([valid_fbank.size(1)] * valid_fbank.size(0), device=valid_fbank.device)
+        with torch.no_grad():
+            emb, _ = self.audio_encoder(valid_fbank, valid_lens)
+        proj_dtype = next(self.audio_proj.parameters()).dtype
+        emb_list = [self.audio_proj(emb[i, :max(1, min(valid_lens[i].item(), emb.size(1)))].unsqueeze(0).to(proj_dtype)).squeeze(0) for i in range(emb.size(0))]
+        if batch_mask.all(): return emb_list
+        out = [None] * audio_inputs.size(0)
+        j = 0
+        for i in range(audio_inputs.size(0)):
+            if batch_mask[i]:
+                out[i] = emb_list[j]
+                j += 1
+        return out
+
+    @torch.compiler.disable
+    def inject_audio_features(self, tokens, h, audio_feats, seqlen):
+        if audio_feats is None or not self.config.audio_ids:
+            return h
+        marker = self.config.audio_ids[0]
+        out = []
+        for b in range(h.size(0)):
+            hb, seq, i = h[b], tokens[b].tolist(), 0
+            af = audio_feats[b] if audio_feats[b] is not None else None
+            while i < len(seq):
+                if seq[i] == marker:
+                    start = i
+                    while i < len(seq) and seq[i] == marker:
+                        i += 1
+                    if af is not None:
+                        inject_len = min(af.size(0), i - start)
+                        hb = torch.cat((hb[:start], af[:inject_len], hb[start + inject_len:]), dim=0)
+                        af = None
+                else:
+                    i += 1
+            out.append(hb)
+        return torch.stack(out)
+    
+    @staticmethod
+    def load_vision(path):
+        if path is None or not os.path.exists(path):
+            warnings.warn(f"[MiniMindOmni] Vision model path not found: {path}. vision_encoder will be None!")
+            return None, None
+        hf_logging.set_verbosity_error()
+        try:
+            model = SiglipVisionModel.from_pretrained(path)
+        except (RuntimeError, ValueError):
+            return None, None
+        processor = SiglipImageProcessor.from_pretrained(path)
+        for p in model.parameters():
+            p.requires_grad = False
+        return model.eval(), processor
+
+    @torch.compiler.disable
+    def get_image_embeddings(self, image_inputs):
+        if hasattr(image_inputs, 'keys'):
+            image_inputs = {k: v.squeeze(1) if v.ndim > 2 and v.shape[1] == 1 else v for k, v in image_inputs.items()}
+            pixel_attention_mask = image_inputs.get('pixel_attention_mask')
+            if pixel_attention_mask is not None and not pixel_attention_mask.any():
+                pv = image_inputs['pixel_values']
+                return pv.new_zeros(pv.size(0), pv.size(1), self.config.image_hidden_size)
+        with torch.no_grad():
+            outputs = self.vision_encoder(**image_inputs)
+        return outputs.last_hidden_state
+
+    @torch.compiler.disable
+    def encode_image_inputs(self, pixel_values):
+        if pixel_values is None or self.vision_encoder is None: return None
+        mask = pixel_values.flatten(1).any(1)
+        if not mask.any(): return pixel_values.new_zeros(pixel_values.size(0), self.config.image_token_len, self.config.hidden_size)
+        with torch.no_grad(): emb = self.vision_encoder(pixel_values=pixel_values[mask]).last_hidden_state
+        if emb.dim() == 2: emb = emb.unsqueeze(0)
+        emb = self.vision_proj(emb)
+        if mask.all(): return emb
+        idx = mask.nonzero().view(-1, 1, 1).expand_as(emb)
+        return emb.new_zeros(pixel_values.size(0), *emb.shape[1:]).scatter(0, idx, emb)
+
+    @torch.compiler.disable
+    def count_vision_proj(self, tokens, h, vision_tensors=None, seqlen=512):
+        if vision_tensors is None or not self.config.image_ids:
+            return h
+        marker, vf = self.config.image_ids[0], vision_tensors
+        if vf.dim() == 3:
+            vf = vf.unsqueeze(1)
+        out = []
+        for b in range(h.size(0)):
+            hb, seq, k, i = h[b], tokens[b].tolist(), 0, 0
+            while i < len(seq):
+                if seq[i] == marker:
+                    start = i
+                    while i < len(seq) and seq[i] == marker:
+                        i += 1
+                    if k < vf.size(1):
+                        hb = torch.cat((hb[:start], vf[b][k][:i - start], hb[i:]), dim=0)[:seqlen]
+                        k += 1
+                else:
+                    i += 1
+            out.append(hb)
+        return torch.stack(out)
+
+    def forward(self, input_ids, attention_mask=None, past_key_values=None, use_cache=False, logits_to_keep=0, audio_inputs=None, audio_lens=None, pixel_values=None, **args):
+        if len(input_ids.shape) == 2:
+            batch_size, seq_length = input_ids.shape
+            text_ids = input_ids
+            audio_ids = torch.full((batch_size, 8, seq_length), self.audio_pad_token, dtype=torch.long, device=input_ids.device)
+        else:
+            batch_size, _, seq_length = input_ids.shape
+            text_ids, audio_ids = input_ids[:, 8, :], input_ids[:, :8, :]
+        if hasattr(past_key_values, 'layers'): past_key_values = None
+        n_thinker, n_talker = len(self.thinker.layers), len(self.talker.layers)
+        past_key_values = past_key_values or ([None] * (n_thinker + n_talker))
+        start_pos = past_key_values[0][0].shape[1] if past_key_values[0] is not None else 0
+        # Recompute RoPE buffers lost during meta-device init (transformers>=5.x)
+        if self.thinker.freqs_cos[0, 0] == 0:
+            freqs_cos, freqs_sin = precompute_freqs_cis(dim=self.config.head_dim, end=self.config.max_position_embeddings, rope_base=self.config.rope_theta, rope_scaling=self.config.rope_scaling)
+            self.thinker.freqs_cos, self.thinker.freqs_sin = freqs_cos.to(input_ids.device), freqs_sin.to(input_ids.device)
+        if self.talker.freqs_cos[0, 0] == 0:
+            freqs_cos, freqs_sin = precompute_freqs_cis(dim=self.talker.talker_config.head_dim, end=self.config.max_position_embeddings, rope_base=self.config.rope_theta, rope_scaling=self.config.rope_scaling)
+            self.talker.freqs_cos, self.talker.freqs_sin = freqs_cos.to(input_ids.device), freqs_sin.to(input_ids.device)
+        presents = []
+
+        # ======= Thinker: text-only input, output text logits =======
+        hidden_states = self.thinker.dropout(self.thinker.embed_tokens(text_ids))
+        position_embeddings = (self.thinker.freqs_cos[start_pos:start_pos + seq_length], self.thinker.freqs_sin[start_pos:start_pos + seq_length])
+        if audio_inputs is not None and start_pos == 0:
+            audio_features = self.encode_audio_inputs(audio_inputs, audio_lens)
+            hidden_states = self.inject_audio_features(text_ids, hidden_states, audio_features, seq_length)
+        if pixel_values is not None and start_pos == 0:
+            if hasattr(pixel_values, 'keys'):
+                img_emb = self.get_image_embeddings(pixel_values).to(hidden_states.dtype)
+                vision_tensors = self.vision_proj(img_emb)
+            else:
+                if len(pixel_values.shape) == 6:
+                    pixel_values = pixel_values.squeeze(2)
+                if len(pixel_values.shape) == 4:
+                    pixel_values = pixel_values.unsqueeze(1)
+                bs, num, c, im_h, im_w = pixel_values.shape
+                stack_dim = 1 if bs > 1 else 0
+                vision_tensors = torch.stack([
+                    self.encode_image_inputs(pixel_values[:, i, :, :, :])
+                    for i in range(num)
+                ], dim=stack_dim)
+            hidden_states = self.count_vision_proj(tokens=text_ids, h=hidden_states, vision_tensors=vision_tensors, seqlen=seq_length)
+        bridge_states = hidden_states
+        for i, (layer, past_key_value) in enumerate(zip(self.thinker.layers, past_key_values[:n_thinker])):
+            hidden_states, present = layer(hidden_states, position_embeddings, past_key_value=past_key_value, use_cache=use_cache, attention_mask=attention_mask)
+            presents.append(present)
+            if i == self.config.bridge_layer: bridge_states = hidden_states
+        h_thinker = self.thinker.norm(hidden_states)
+
+        # ======= Talker: thinker hidden + audio codes, output audio logits =======
+        talker_emb = self.talker.embed_tokens(audio_ids)
+        spk_emb = args.get('spk_emb', None)
+        if spk_emb is not None:
+            spk_mask = (audio_ids[:, 0, :] == self.audio_spk_token).unsqueeze(-1)
+            talker_emb = torch.where(spk_mask, self.talker.spk_proj(spk_emb).unsqueeze(1), talker_emb)
+        hidden_states = self.talker.embed_proj(bridge_states) * self.talker.text_scale + self.talker.codec_proj(talker_emb) * self.talker.audio_scale
+        talker_pos_emb = (self.talker.freqs_cos[start_pos:start_pos + seq_length], self.talker.freqs_sin[start_pos:start_pos + seq_length])
+        for layer, past_key_value in zip(self.talker.layers, past_key_values[n_thinker:]):
+            hidden_states, present = layer(hidden_states, talker_pos_emb, past_key_value=past_key_value, use_cache=use_cache, attention_mask=attention_mask)
+            presents.append(present)
+        h_talker = self.talker.norm(hidden_states)
+
+        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
+        aux_loss = sum(l.mlp.aux_loss for l in list(self.thinker.layers) + list(self.talker.layers) if isinstance(l.mlp, MOEFeedForward))
+        aux_loss += sum(p.sum() for p in self.audio_proj.parameters()) * 0 + sum(p.sum() for p in self.vision_proj.parameters()) * 0 + sum(p.sum() for p in self.talker.lm_head.adapters.parameters()) * 0 + sum(p.sum() for p in self.talker.spk_proj.parameters()) * 0 # dummy gradient
+        text_logits = self.thinker.lm_head(h_thinker[:, slice_indices, :])
+        audio_logits = self.talker.lm_head(h_talker[:, slice_indices, :])
+        
+        out = MoeCausalLMOutputWithPast(aux_loss=aux_loss, logits=text_logits, past_key_values=presents)
+        out.audio_logits = audio_logits
+        return out
+
+    @torch.inference_mode()
+    def generate(self, input_ids, eos_token_id=2, max_new_tokens=1024, temperature=0.75, top_p=0.90,
+                 stream=False, rp=1., use_cache=True, return_audio_codes=False, **args):
+        if stream:
+            return self.stream_generate(input_ids, eos_token_id, max_new_tokens, temperature, top_p, rp, use_cache, return_audio_codes, **args)
+        tokens = list(self.stream_generate(input_ids, eos_token_id, max_new_tokens, temperature, top_p, rp, use_cache, return_audio_codes, **args))
+        return tokens[-1] if tokens else input_ids
+
+    def stream_generate(self, input_ids, eos_token_id, max_new_tokens, temperature, top_p, rp, use_cache, return_audio_codes=False, **args):
+        start_pos, past_kvs, text_finished, first_finished = input_ids.shape[1], None, False, True
+        audio_codes = [[] for _ in range(8)]
+        audio_stop_pos = [None] * 8
+        audio_buffer = torch.full((1, 8, start_pos), self.audio_pad_token, dtype=torch.long, device=input_ids.device)
+        spk_emb = args.get('spk_emb', None)
+        ref_codes = args.get('ref_codes', None)
+        ref_len = ref_codes.shape[2] if ref_codes is not None else 0
+        spk_reserve = 1 if spk_emb is not None else 0
+        fill_end = start_pos
+        fill_start = max(spk_reserve, start_pos - ref_len)
+        if ref_codes is not None and fill_start < fill_end:
+            audio_buffer[:, :, fill_start:fill_end] = ref_codes[:, :, -(fill_end - fill_start):]
+        if spk_emb is not None and fill_start > 0:
+            audio_buffer[:, :, fill_start - 1] = self.audio_spk_token
+        think_end_step, generated_tokens = None, ([] if args.get('open_thinking', False) else None)
+        while input_ids.shape[1] < start_pos + max_new_tokens:
+            if past_kvs is None or not use_cache:
+                out = self.forward(torch.cat((audio_buffer, input_ids.unsqueeze(1)), dim=1), past_key_values=past_kvs, use_cache=use_cache, **args)
+            else:
+                out = self.forward(torch.cat((audio_buffer[:, :, -1:], input_ids[:, -1:].unsqueeze(1)), dim=1), past_key_values=past_kvs, use_cache=use_cache, **args)
+            past_kvs = out.past_key_values
+
+            logits = out.logits[0, -1, :].clone() / (temperature + 1e-9)
+            logits[list(set(input_ids[0].tolist()))] /= rp
+            if top_p and top_p < 1.0:
+                sorted_l, sorted_i = torch.sort(logits, descending=True)
+                mask = torch.cumsum(F.softmax(sorted_l, dim=-1), dim=-1) > top_p
+                mask[1:], mask[0] = mask[:-1].clone(), False
+                logits[sorted_i[mask]] = -float('Inf')
+            text_token = torch.multinomial(F.softmax(logits, dim=-1), 1).item()
+
+            if text_finished:
+                text_token = args.get('enter_token_id', 201) if first_finished else args.get('pad_token_id', 0)
+                first_finished = False
+
+            step = input_ids.shape[1] - start_pos  # 已生成token数（0=首次，此时模型处理prompt末尾token）
+            audio_step = step - 1  # 延迟1步：输出第1个text时无audio，输出第2个text时layer0开始
+            if generated_tokens is not None:
+                generated_tokens.append(text_token)
+                if not think_end_step and generated_tokens[-len(self.config.think_end_ids):] == list(self.config.think_end_ids): think_end_step = step + 2
+                audio_step = (step - think_end_step) if think_end_step else -1
+            for i, al in enumerate(out.audio_logits):
+                if audio_step < i:
+                    audio_codes[i].append(self.audio_pad_token)
+                else:
+                    logits_i = al[0, -1, :].clone() / 0.2
+                    for prev_code in audio_codes[i][-3:]: logits_i[prev_code] /= 1.05
+                    top_val, top_idx = logits_i.topk(50)
+                    code = top_idx[torch.multinomial(F.softmax(top_val, dim=-1), 1)].item()
+                    audio_codes[i].append(code)
+                    if audio_stop_pos[i] is None and code >= 2048: audio_stop_pos[i] = len(audio_codes[i]) - 1
+
+            if text_finished and audio_codes[7][-1] == self.audio_stop_token: break
+
+            input_ids = torch.cat((input_ids, torch.tensor([[text_token]], device=input_ids.device)), dim=1)
+            audio_buffer = torch.cat((audio_buffer, torch.full((1, 8, 1), self.audio_pad_token, dtype=torch.long, device=input_ids.device)), dim=2)
+            for i in range(min(audio_step + 1, 8)): audio_buffer[0, i, -1] = audio_codes[i][-1]
+
+            audio_frame = None
+            if return_audio_codes and audio_step >= 7:
+                frame = [audio_codes[i][step - 7 + i] for i in range(8)]
+                active_layers = sum(1 for i in range(8) if audio_stop_pos[i] is None or step - 7 + i < audio_stop_pos[i])
+                if active_layers >= 8: audio_frame = frame
+            if not text_finished:
+                yield input_ids[:, start_pos:], audio_frame
+                if text_token == eos_token_id: text_finished = True
+            else:
+                yield None, audio_frame
+
+
+# ==== Realtime VAD (与模型本体零耦合，纯工程层) ====
+class SileroVAD:
+    def __init__(self, path):
+        opts = ort.SessionOptions()
+        opts.inter_op_num_threads = opts.intra_op_num_threads = 1
+        opts.log_severity_level = 4
+        self.session = ort.InferenceSession(path, providers=["CPUExecutionProvider"], sess_options=opts)
+        self.h, self.c = np.zeros((2, 1, 64), dtype=np.float32), np.zeros((2, 1, 64), dtype=np.float32)
+
+    def reset(self):
+        self.h[:], self.c[:] = 0, 0
+
+    def __call__(self, chunk, sr=16000):
+        out, self.h, self.c = self.session.run(None, {"input": chunk.reshape(1, -1).astype(np.float32), "h": self.h, "c": self.c, "sr": np.array(sr, dtype="int64")})
+        return float(out[0][0])
+
+
+class RealtimeSession:
+    def __init__(self, vad_path, sr=16000, threshold=0.8, min_speech_ms=128, min_silence_ms=800):
+        self.vad, self.sr, self.threshold = SileroVAD(vad_path), sr, threshold
+        self.min_speech, self.min_silence = int(sr * min_speech_ms / 1000), int(sr * min_silence_ms / 1000)
+        self.reset()
+
+    def reset(self):
+        self.vad.reset()
+        self.buffer, self.ring, self.speaking, self.generating, self.interrupt = [], [], False, False, False
+        self.speech_samples = self.silence_samples = self.tail_silence = 0
+
+    def push_chunk(self, chunk, W=1024):
+        for i in range(0, max(len(chunk), 1), W):
+            w = chunk[i:i + W]
+            if len(w) < W:
+                w = np.pad(w, (0, W - len(w)))
+            prob = self.vad(w, self.sr)
+            if prob > self.threshold:
+                self.silence_samples = self.tail_silence = 0
+                self.speech_samples += len(w)
+                self.buffer.append(w)
+                if self.speech_samples >= self.min_speech and not self.speaking:
+                    self.speaking = True
+                    self.buffer = self.ring + self.buffer
+                    self.ring = []
+                if self.generating and self.speaking:
+                    self.interrupt = True
+                    return 'interrupt'
+            elif self.speaking:
+                self.silence_samples += len(w)
+                self.tail_silence += 1
+                self.buffer.append(w)
+                if self.silence_samples >= self.min_silence:
+                    if self.tail_silence > 1:
+                        del self.buffer[-(self.tail_silence - 1):]
+                    self.speaking, self.speech_samples, self.silence_samples, self.tail_silence = False, 0, 0, 0
+                    return 'speech_end'
+            else:
+                if self.speech_samples > 0:
+                    self.buffer.clear()
+                self.speech_samples = 0
+                self.ring = [w]
+        return 'listening'
+
+    def get_audio(self):
+        audio = np.concatenate(self.buffer) if self.buffer else np.array([], dtype=np.float32)
+        self.buffer.clear()
+        return audio

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21530f9bbc540f461e2c0e29292ad359781d4d984d1e0c994510945f9b0edaab
+size 226324754

special_tokens_map.json

@@ -0,0 +1,52 @@
+{
+  "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|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<|audio_pad|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_eod>",
+    "<tts_text_bos_single>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,335 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<|buffer1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<|buffer2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<|buffer3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<|buffer4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<|buffer5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<|buffer6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<|buffer7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<|buffer8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<|buffer9|>",
+      "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|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<|audio_pad|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_eod>",
+    "<tts_text_bos_single>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "image_token": "<|image_pad|>",
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>",
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}