A continuation of kimi source tree.txt. The complete source identity, every recorded occurrence, and linked equations are on its first page.
Source transcript · continued
Download complete source text ↓6,675 lines · 275.4 KB
config.kv_lora_rank + config.qk_rope_head_dim,
bias=config.attention_bias,
)
self.kv_a_layernorm = DeepseekV3RMSNorm(config.kv_lora_rank)
self.kv_b_proj = nn.Linear(
config.kv_lora_rank,
self.num_heads *
(self.q_head_dim - self.qk_rope_head_dim + self.v_head_dim),
bias=False,
)
self.o_proj = nn.Linear(
self.num_heads * self.v_head_dim,
self.hidden_size,
bias=config.attention_bias,
)
self._init_rope()
self.softmax_scale = self.q_head_dim**(-0.5)
if self.config.rope_scaling is not None:
mscale_all_dim = self.config.rope_scaling.get("mscale_all_dim", 0)
scaling_factor = self.config.rope_scaling["factor"]
if mscale_all_dim:
mscale = yarn_get_mscale(scaling_factor, mscale_all_dim)
self.softmax_scale = self.softmax_scale * mscale * mscale
def _init_rope(self):
if self.config.rope_scaling is None:
self.rotary_emb = DeepseekV3RotaryEmbedding(
self.qk_rope_head_dim,
max_position_embeddings=self.max_position_embeddings,
base=self.rope_theta,
)
else:
scaling_type = self.config.rope_scaling["type"]
scaling_factor = self.config.rope_scaling["factor"]
if scaling_type == "linear":
self.rotary_emb = DeepseekV3LinearScalingRotaryEmbedding(
self.qk_rope_head_dim,
max_position_embeddings=self.max_position_embeddings,
scaling_factor=scaling_factor,
base=self.rope_theta,
)
elif scaling_type == "dynamic":
self.rotary_emb = DeepseekV3DynamicNTKScalingRotaryEmbedding(
self.qk_rope_head_dim,
max_position_embeddings=self.max_position_embeddings,
scaling_factor=scaling_factor,
base=self.rope_theta,
)
elif scaling_type == "yarn":
kwargs = {
key: self.config.rope_scaling[key]
for key in [
"original_max_position_embeddings",
"beta_fast",
"beta_slow",
"mscale",
"mscale_all_dim",
] if key in self.config.rope_scaling
}
self.rotary_emb = DeepseekV3YarnRotaryEmbedding(
self.qk_rope_head_dim,
max_position_embeddings=self.max_position_embeddings,
scaling_factor=scaling_factor,
base=self.rope_theta,
**kwargs,
)
else:
raise ValueError(f"Unknown RoPE scaling type {scaling_type}")
def _shape(self, tensor: torch.Tensor, seq_len: int, bsz: int):
return (tensor.view(bsz, seq_len, self.num_heads,
self.v_head_dim).transpose(1, 2).contiguous())
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_value: Optional[Cache] = None,
output_attentions: bool = False,
use_cache: bool = False,
**kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor],
Optional[Tuple[torch.Tensor]]]:
if "padding_mask" in kwargs:
warnings.warn(
"Passing `padding_mask` is deprecated and will be removed in v4.37. Please make sure use `attention_mask` instead.`"
)
bsz, q_len, _ = hidden_states.size()
if self.q_lora_rank is None:
q = self.q_proj(hidden_states)
else:
q = self.q_b_proj(self.q_a_layernorm(self.q_a_proj(hidden_states)))
q = q.view(bsz, q_len, self.num_heads, self.q_head_dim).transpose(1, 2)
q_nope, q_pe = torch.split(
q, [self.qk_nope_head_dim, self.qk_rope_head_dim], dim=-1)
compressed_kv = self.kv_a_proj_with_mqa(hidden_states)
compressed_kv, k_pe = torch.split(
compressed_kv, [self.kv_lora_rank, self.qk_rope_head_dim], dim=-1)
k_pe = k_pe.view(bsz, q_len, 1, self.qk_rope_head_dim).transpose(1, 2)
kv = (self.kv_b_proj(self.kv_a_layernorm(compressed_kv)).view(
bsz, q_len, self.num_heads,
self.qk_nope_head_dim + self.v_head_dim).transpose(1, 2))
k_nope, value_states = torch.split(
kv, [self.qk_nope_head_dim, self.v_head_dim], dim=-1)
kv_seq_len = value_states.shape[-2]
if past_key_value is not None:
if self.layer_idx is None:
raise ValueError(
f"The cache structure has changed since version v4.36. If you are using {self.__class__.__name__} "
"for auto-regressive decoding with k/v caching, please make sure to initialize the attention class "
"with a layer index.")
kv_seq_len += get_usable_length(past_key_value, kv_seq_len,
self.layer_idx)
cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
q_pe, k_pe = apply_rotary_pos_emb(q_pe, k_pe, cos, sin, position_ids)
query_states = k_pe.new_empty(bsz, self.num_heads, q_len,
self.q_head_dim)
query_states[:, :, :, :self.qk_nope_head_dim] = q_nope
query_states[:, :, :, self.qk_nope_head_dim:] = q_pe
key_states = k_pe.new_empty(bsz, self.num_heads, q_len,
self.q_head_dim)
key_states[:, :, :, :self.qk_nope_head_dim] = k_nope
key_states[:, :, :, self.qk_nope_head_dim:] = k_pe
if past_key_value is not None:
cache_kwargs = {"sin": sin, "cos": cos} # Specific to RoPE models
key_states, value_states = past_key_value.update(
key_states, value_states, self.layer_idx, cache_kwargs)
attn_weights = (
torch.matmul(query_states, key_states.transpose(2, 3)) *
self.softmax_scale)
if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
raise ValueError(
f"Attention weights should be of size {(bsz, self.num_heads, q_len, kv_seq_len)}, but is"
f" {attn_weights.size()}")
assert attention_mask is not None
if attention_mask is not None:
if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
raise ValueError(
f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
)
attn_weights = attn_weights + attention_mask
# upcast attention to fp32
attn_weights = nn.functional.softmax(attn_weights,
dim=-1,
dtype=torch.float32).to(
query_states.dtype)
attn_weights = nn.functional.dropout(attn_weights,
p=self.attention_dropout,
training=self.training)
attn_output = torch.matmul(attn_weights, value_states)
if attn_output.size() != (bsz, self.num_heads, q_len, self.v_head_dim):
raise ValueError(
f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.v_head_dim)}, but is"
f" {attn_output.size()}")
attn_output = attn_output.transpose(1, 2).contiguous()
attn_output = attn_output.reshape(bsz, q_len,
self.num_heads * self.v_head_dim)
attn_output = self.o_proj(attn_output)
if not output_attentions:
attn_weights = None
return attn_output, attn_weights, past_key_value
# Copied from transformers.models.llama.modeling_llama.LlamaFlashAttention2 with Llama->DeepseekV3
class DeepseekV3FlashAttention2(DeepseekV3Attention):
"""
DeepseekV3 flash attention module. This module inherits from `DeepseekV3Attention` as the weights of the module stays
untouched. The only required change would be on the forward pass where it needs to correctly call the public API of
flash attention and deal with padding tokens in case the input contains any of them.
"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# TODO: Should be removed once Flash Attention for RoCm is bumped to 2.1.
# flash_attn<2.1 generates top-left aligned causal mask, while what is needed here is bottom-right alignment, that was made default for flash_attn>=2.1. This attribute is used to handle this difference. Reference: https://github.com/Dao-AILab/flash-attention/releases/tag/v2.1.0.
# Beware that with flash_attn<2.1, using q_seqlen != k_seqlen (except for the case q_seqlen == 1) produces a wrong mask (top-left).
self._flash_attn_uses_top_left_mask = not is_flash_attn_greater_or_equal_2_10(
)
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.LongTensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_value: Optional[Cache] = None,
output_attentions: bool = False,
use_cache: bool = False,
**kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor],
Optional[Tuple[torch.Tensor]]]:
# DeepseekV3FlashAttention2 attention does not support output_attentions
if "padding_mask" in kwargs:
warnings.warn(
"Passing `padding_mask` is deprecated and will be removed in v4.37. Please make sure use `attention_mask` instead.`"
)
# overwrite attention_mask with padding_mask
attention_mask = kwargs.pop("padding_mask")
output_attentions = False
bsz, q_len, _ = hidden_states.size()
if self.q_lora_rank is None:
q = self.q_proj(hidden_states)
else:
q = self.q_b_proj(self.q_a_layernorm(self.q_a_proj(hidden_states)))
q = q.view(bsz, q_len, self.num_heads, self.q_head_dim).transpose(1, 2)
q_nope, q_pe = torch.split(
q, [self.qk_nope_head_dim, self.qk_rope_head_dim], dim=-1)
# Flash attention requires the input to have the shape
# batch_size x seq_length x head_dim x hidden_dim
# therefore we just need to keep the original shape
compressed_kv = self.kv_a_proj_with_mqa(hidden_states)
compressed_kv, k_pe = torch.split(
compressed_kv, [self.kv_lora_rank, self.qk_rope_head_dim], dim=-1)
k_pe = k_pe.view(bsz, q_len, 1, self.qk_rope_head_dim).transpose(1, 2)
kv = (self.kv_b_proj(self.kv_a_layernorm(compressed_kv)).view(
bsz, q_len, self.num_heads,
self.qk_nope_head_dim + self.v_head_dim).transpose(1, 2))
k_nope, value_states = torch.split(
kv, [self.qk_nope_head_dim, self.v_head_dim], dim=-1)
kv_seq_len = value_states.shape[-2]
kv_seq_len = value_states.shape[-2]
if past_key_value is not None:
kv_seq_len += get_usable_length(past_key_value, kv_seq_len,
self.layer_idx)
cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
q_pe, k_pe = apply_rotary_pos_emb(q_pe, k_pe, cos, sin, position_ids)
query_states = k_pe.new_empty(bsz, self.num_heads, q_len,
self.q_head_dim)
query_states[:, :, :, :self.qk_nope_head_dim] = q_nope
query_states[:, :, :, self.qk_nope_head_dim:] = q_pe
key_states = k_pe.new_empty(bsz, self.num_heads, q_len,
self.q_head_dim)
key_states[:, :, :, :self.qk_nope_head_dim] = k_nope
key_states[:, :, :, self.qk_nope_head_dim:] = k_pe
if self.q_head_dim != self.v_head_dim:
value_states = F.pad(value_states,
[0, self.q_head_dim - self.v_head_dim])
if past_key_value is not None:
cache_kwargs = {"sin": sin, "cos": cos} # Specific to RoPE models
key_states, value_states = past_key_value.update(
key_states, value_states, self.layer_idx, cache_kwargs)
# TODO: These transpose are quite inefficient but Flash Attention requires the layout [batch_size, sequence_length, num_heads, head_dim]. We would need to refactor the KV cache
# to be able to avoid many of these transpose/reshape/view.
query_states = query_states.transpose(1, 2)
key_states = key_states.transpose(1, 2)
value_states = value_states.transpose(1, 2)
dropout_rate = self.attention_dropout if self.training else 0.0
# In PEFT, usually we cast the layer norms in float32 for training stability reasons
# therefore the input hidden states gets silently casted in float32. Hence, we need
# cast them back in the correct dtype just to be sure everything works as expected.
# This might slowdown training & inference so it is recommended to not cast the LayerNorms
# in fp32. (DeepseekV3RMSNorm handles it correctly)
input_dtype = query_states.dtype
if input_dtype == torch.float32:
# Handle the case where the model is quantized
if hasattr(self.config, "_pre_quantization_dtype"):
target_dtype = self.config._pre_quantization_dtype
elif torch.is_autocast_enabled():
target_dtype = torch.get_autocast_gpu_dtype()
else:
target_dtype = (self.q_proj.weight.dtype if self.q_lora_rank
is None else self.q_a_proj.weight.dtype)
logger.warning_once(
f"The input hidden states seems to be silently casted in float32, this might be related to"
f" the fact you have upcasted embedding or layer norm layers in float32. We will cast back the input in"
f" {target_dtype}.")
query_states = query_states.to(target_dtype)
key_states = key_states.to(target_dtype)
value_states = value_states.to(target_dtype)
attn_output = self._flash_attention_forward(
query_states,
key_states,
value_states,
attention_mask,
q_len,
dropout=dropout_rate,
softmax_scale=self.softmax_scale,
)
if self.q_head_dim != self.v_head_dim:
attn_output = attn_output[:, :, :, :self.v_head_dim]
attn_output = attn_output.reshape(bsz, q_len, self.num_heads *
self.v_head_dim).contiguous()
attn_output = self.o_proj(attn_output)
if not output_attentions:
attn_weights = None
return attn_output, attn_weights, past_key_value
def _flash_attention_forward(
self,
query_states,
key_states,
value_states,
attention_mask,
query_length,
dropout=0.0,
softmax_scale=None,
):
"""
Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token
first unpad the input, then computes the attention scores and pad the final attention scores.
Args:
query_states (`torch.Tensor`):
Input query states to be passed to Flash Attention API
key_states (`torch.Tensor`):
Input key states to be passed to Flash Attention API
value_states (`torch.Tensor`):
Input value states to be passed to Flash Attention API
attention_mask (`torch.Tensor`):
The padding mask - corresponds to a tensor of size `(batch_size, seq_len)` where 0 stands for the
position of padding tokens and 1 for the position of non-padding tokens.
dropout (`int`, *optional*):
Attention dropout
softmax_scale (`float`, *optional*):
The scaling of QK^T before applying softmax. Default to 1 / sqrt(head_dim)
"""
if not self._flash_attn_uses_top_left_mask:
causal = self.is_causal
else:
# TODO: Remove the `query_length != 1` check once Flash Attention for RoCm is bumped to 2.1. For details, please see the comment in DeepseekV3FlashAttention2 __init__.
causal = self.is_causal and query_length != 1
# Contains at least one padding token in the sequence
if attention_mask is not None:
batch_size = query_states.shape[0]
(
query_states,
key_states,
value_states,
indices_q,
cu_seq_lens,
max_seq_lens,
) = self._upad_input(query_states, key_states, value_states,
attention_mask, query_length)
cu_seqlens_q, cu_seqlens_k = cu_seq_lens
max_seqlen_in_batch_q, max_seqlen_in_batch_k = max_seq_lens
attn_output_unpad = flash_attn_varlen_func(
query_states,
key_states,
value_states,
cu_seqlens_q=cu_seqlens_q,
cu_seqlens_k=cu_seqlens_k,
max_seqlen_q=max_seqlen_in_batch_q,
max_seqlen_k=max_seqlen_in_batch_k,
dropout_p=dropout,
softmax_scale=softmax_scale,
causal=causal,
)
attn_output = pad_input(attn_output_unpad, indices_q, batch_size,
query_length)
else:
attn_output = flash_attn_func(
query_states,
key_states,
value_states,
dropout,
softmax_scale=softmax_scale,
causal=causal,
)
return attn_output
def _upad_input(self, query_layer, key_layer, value_layer, attention_mask,
query_length):
indices_k, cu_seqlens_k, max_seqlen_in_batch_k = _get_unpad_data(
attention_mask)
batch_size, kv_seq_len, num_key_value_heads, head_dim = key_layer.shape
key_layer = index_first_axis(
key_layer.reshape(batch_size * kv_seq_len, num_key_value_heads,
head_dim),
indices_k,
)
value_layer = index_first_axis(
value_layer.reshape(batch_size * kv_seq_len, num_key_value_heads,
head_dim),
indices_k,
)
if query_length == kv_seq_len:
query_layer = index_first_axis(
query_layer.reshape(batch_size * kv_seq_len, self.num_heads,
head_dim),
indices_k,
)
cu_seqlens_q = cu_seqlens_k
max_seqlen_in_batch_q = max_seqlen_in_batch_k
indices_q = indices_k
elif query_length == 1:
max_seqlen_in_batch_q = 1
cu_seqlens_q = torch.arange(
batch_size + 1, dtype=torch.int32, device=query_layer.device
) # There is a memcpy here, that is very bad.
indices_q = cu_seqlens_q[:-1]
query_layer = query_layer.squeeze(1)
else:
# The -q_len: slice assumes left padding.
attention_mask = attention_mask[:, -query_length:]
query_layer, indices_q, cu_seqlens_q, max_seqlen_in_batch_q = unpad_input(
query_layer, attention_mask)
return (
query_layer,
key_layer,
value_layer,
indices_q,
(cu_seqlens_q, cu_seqlens_k),
(max_seqlen_in_batch_q, max_seqlen_in_batch_k),
)
ATTENTION_CLASSES = {
"eager": DeepseekV3Attention,
"flash_attention_2": DeepseekV3FlashAttention2,
}
class DeepseekV3DecoderLayer(nn.Module):
def __init__(self, config: DeepseekV3Config, layer_idx: int):
super().__init__()
self.hidden_size = config.hidden_size
self.self_attn = ATTENTION_CLASSES[config._attn_implementation](
config=config, layer_idx=layer_idx)
self.mlp = (DeepseekV3MoE(config) if
(config.n_routed_experts is not None
and layer_idx >= config.first_k_dense_replace
and layer_idx % config.moe_layer_freq == 0) else
DeepseekV3MLP(config))
self.input_layernorm = DeepseekV3RMSNorm(config.hidden_size,
eps=config.rms_norm_eps)
self.post_attention_layernorm = DeepseekV3RMSNorm(
config.hidden_size, eps=config.rms_norm_eps)
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_value: Optional[Tuple[torch.Tensor]] = None,
output_attentions: Optional[bool] = False,
use_cache: Optional[bool] = False,
**kwargs,
) -> Tuple[torch.FloatTensor, Optional[Tuple[torch.FloatTensor,
torch.FloatTensor]]]:
"""
Args:
hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
attention_mask (`torch.FloatTensor`, *optional*):
attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
query_sequence_length, key_sequence_length)` if default attention is used.
output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under
returned tensors for more detail.
use_cache (`bool`, *optional*):
If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
(see `past_key_values`).
past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states
"""
if "padding_mask" in kwargs:
warnings.warn(
"Passing `padding_mask` is deprecated and will be removed in v4.37. Please make sure use `attention_mask` instead.`"
)
residual = hidden_states
hidden_states = self.input_layernorm(hidden_states)
# Self Attention
hidden_states, self_attn_weights, present_key_value = self.self_attn(
hidden_states=hidden_states,
attention_mask=attention_mask,
position_ids=position_ids,
past_key_value=past_key_value,
output_attentions=output_attentions,
use_cache=use_cache,
**kwargs,
)
hidden_states = residual + hidden_states
# Fully Connected
residual = hidden_states
hidden_states = self.post_attention_layernorm(hidden_states)
hidden_states = self.mlp(hidden_states)
hidden_states = residual + hidden_states
outputs = (hidden_states, )
if output_attentions:
outputs += (self_attn_weights, )
if use_cache:
outputs += (present_key_value, )
return outputs
DeepseekV3_START_DOCSTRING = r"""
This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
etc.)
This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
and behavior.
Parameters:
config ([`DeepseekV3Config`]):
Model configuration class with all the parameters of the model. Initializing with a config file does not
load the weights associated with the model, only the configuration. Check out the
[`~PreTrainedModel.from_pretrained`] method to load the model weights.
"""
@add_start_docstrings(
"The bare DeepseekV3 Model outputting raw hidden-states without any specific head on top.",
DeepseekV3_START_DOCSTRING,
)
class DeepseekV3PreTrainedModel(PreTrainedModel):
config_class = DeepseekV3Config
base_model_prefix = "model"
supports_gradient_checkpointing = True
_no_split_modules = ["DeepseekV3DecoderLayer"]
_skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True
_supports_cache_class = True
def _init_weights(self, module):
std = self.config.initializer_range
if isinstance(module, nn.Linear):
module.weight.data.normal_(mean=0.0, std=std)
if module.bias is not None:
module.bias.data.zero_()
elif isinstance(module, nn.Embedding):
module.weight.data.normal_(mean=0.0, std=std)
if module.padding_idx is not None:
module.weight.data[module.padding_idx].zero_()
DeepseekV3_INPUTS_DOCSTRING = r"""
Args:
input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide
it.
Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
[`PreTrainedTokenizer.__call__`] for details.
[What are input IDs?](../glossary#input-ids)
attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
[What are attention masks?](../glossary#attention-mask)
Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
[`PreTrainedTokenizer.__call__`] for details.
If `past_key_values` is used, optionally only the last `input_ids` have to be input (see
`past_key_values`).
If you want to change padding behavior, you should read [`modeling_opt._prepare_decoder_attention_mask`]
and modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more
information on the default strategy.
- 1 indicates the head is **not masked**,
- 0 indicates the head is **masked**.
position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
config.n_positions - 1]`.
[What are position IDs?](../glossary#position-ids)
past_key_values (`Cache` or `tuple(tuple(torch.FloatTensor))`, *optional*):
Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values`
returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.
Two formats are allowed:
- a [`~cache_utils.Cache`] instance;
- Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of
shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`). This is also known as the legacy
cache format.
The model will output the same cache format that is fed as input. If no `past_key_values` are passed, the
legacy cache format will be returned.
If `past_key_values` are used, the user can optionally input only the last `input_ids` (those that don't
have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `input_ids`
of shape `(batch_size, sequence_length)`.
inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
model's internal embedding lookup matrix.
use_cache (`bool`, *optional*):
If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
`past_key_values`).
output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail.
output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
more detail.
return_dict (`bool`, *optional*):
Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
"""
@add_start_docstrings(
"The bare DeepseekV3 Model outputting raw hidden-states without any specific head on top.",
DeepseekV3_START_DOCSTRING,
)
class DeepseekV3Model(DeepseekV3PreTrainedModel):
"""
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`DeepseekV3DecoderLayer`]
Args:
config: DeepseekV3Config
"""
def __init__(self, config: DeepseekV3Config):
super().__init__(config)
self.padding_idx = config.pad_token_id
self.vocab_size = config.vocab_size
self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size,
self.padding_idx)
self.layers = nn.ModuleList([
DeepseekV3DecoderLayer(config, layer_idx)
for layer_idx in range(config.num_hidden_layers)
])
self._use_flash_attention_2 = config._attn_implementation == "flash_attention_2"
self.norm = DeepseekV3RMSNorm(config.hidden_size,
eps=config.rms_norm_eps)
self.gradient_checkpointing = False
# Initialize weights and apply final processing
self.post_init()
def get_input_embeddings(self):
return self.embed_tokens
def set_input_embeddings(self, value):
self.embed_tokens = value
@add_start_docstrings_to_model_forward(DeepseekV3_INPUTS_DOCSTRING)
def forward(
self,
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_values: Optional[List[torch.FloatTensor]] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
use_cache: Optional[bool] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple, BaseModelOutputWithPast]:
output_attentions = (output_attentions if output_attentions is not None
else self.config.output_attentions)
output_hidden_states = (output_hidden_states
if output_hidden_states is not None else
self.config.output_hidden_states)
use_cache = use_cache if use_cache is not None else self.config.use_cache
return_dict = (return_dict if return_dict is not None else
self.config.use_return_dict)
# retrieve input_ids and inputs_embeds
if input_ids is not None and inputs_embeds is not None:
raise ValueError(
"You cannot specify both input_ids and inputs_embeds at the same time"
)
elif input_ids is not None:
batch_size, seq_length = input_ids.shape[:2]
elif inputs_embeds is not None:
batch_size, seq_length = inputs_embeds.shape[:2]
else:
raise ValueError(
"You have to specify either input_ids or inputs_embeds")
past_key_values_length = 0
if use_cache:
use_legacy_cache = not isinstance(past_key_values, Cache)
if use_legacy_cache:
past_key_values = DynamicCache.from_legacy_cache(
past_key_values)
past_key_values_length = get_usable_length(past_key_values,
seq_length)
if position_ids is None:
device = input_ids.device if input_ids is not None else inputs_embeds.device
position_ids = torch.arange(
past_key_values_length,
seq_length + past_key_values_length,
dtype=torch.long,
device=device,
)
position_ids = position_ids.unsqueeze(0)
if inputs_embeds is None:
inputs_embeds = self.embed_tokens(input_ids)
if self._use_flash_attention_2:
# 2d mask is passed through the layers
attention_mask = (attention_mask if
(attention_mask is not None
and 0 in attention_mask) else None)
else:
# 4d mask is passed through the layers
attention_mask = _prepare_4d_causal_attention_mask(
attention_mask,
(batch_size, seq_length),
inputs_embeds,
past_key_values_length,
)
# embed positions
hidden_states = inputs_embeds
# decoder layers
all_hidden_states = () if output_hidden_states else None
all_self_attns = () if output_attentions else None
next_decoder_cache = None
for decoder_layer in self.layers:
if output_hidden_states:
all_hidden_states += (hidden_states, )
layer_outputs = decoder_layer(
hidden_states,
attention_mask=attention_mask,
position_ids=position_ids,
past_key_value=past_key_values,
output_attentions=output_attentions,
use_cache=use_cache,
)
hidden_states = layer_outputs[0]
if use_cache:
next_decoder_cache = layer_outputs[
2 if output_attentions else 1]
if output_attentions:
all_self_attns += (layer_outputs[1], )
hidden_states = self.norm(hidden_states)
# add hidden states from the last decoder layer
if output_hidden_states:
all_hidden_states += (hidden_states, )
next_cache = None
if use_cache:
next_cache = (next_decoder_cache.to_legacy_cache()
if use_legacy_cache else next_decoder_cache)
if not return_dict:
return tuple(
v for v in
[hidden_states, next_cache, all_hidden_states, all_self_attns]
if v is not None)
return BaseModelOutputWithPast(
last_hidden_state=hidden_states,
past_key_values=next_cache,
hidden_states=all_hidden_states,
attentions=all_self_attns,
)
class DeepseekV3ForCausalLM(DeepseekV3PreTrainedModel):
_tied_weights_keys = ["lm_head.weight"]
def __init__(self, config):
super().__init__(config)
self.model = DeepseekV3Model(config)
self.vocab_size = config.vocab_size
self.lm_head = nn.Linear(config.hidden_size,
config.vocab_size,
bias=False)
# Initialize weights and apply final processing
self.post_init()
def get_input_embeddings(self):
return self.model.embed_tokens
def set_input_embeddings(self, value):
self.model.embed_tokens = value
def get_output_embeddings(self):
return self.lm_head
def set_output_embeddings(self, new_embeddings):
self.lm_head = new_embeddings
def set_decoder(self, decoder):
self.model = decoder
def get_decoder(self):
return self.model
@add_start_docstrings_to_model_forward(DeepseekV3_INPUTS_DOCSTRING)
@replace_return_docstrings(output_type=CausalLMOutputWithPast,
config_class=_CONFIG_FOR_DOC)
def forward(
self,
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_values: Optional[List[torch.FloatTensor]] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
use_cache: Optional[bool] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple, CausalLMOutputWithPast]:
r"""
Args:
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
Labels for computing the masked language modeling loss. Indices should either be in `[0, transformers.,
config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
(masked), the loss is only computed for the tokens with labels in `[0, transformers., config.vocab_size]`.
Returns:
Example:
```python
>>> from transformers import AutoTokenizer, DeepseekV3ForCausalLM
>>> model = DeepseekV3ForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
>>> tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
>>> prompt = "Hey, are you conscious? Can you talk to me?"
>>> inputs = tokenizer(prompt, return_tensors="pt")
>>> # Generate
>>> generate_ids = model.generate(inputs.input_ids, max_length=30)
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
```"""
output_attentions = (output_attentions if output_attentions is not None
else self.config.output_attentions)
output_hidden_states = (output_hidden_states
if output_hidden_states is not None else
self.config.output_hidden_states)
return_dict = (return_dict if return_dict is not None else
self.config.use_return_dict)
# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
outputs = self.model(
input_ids=input_ids,
attention_mask=attention_mask,
position_ids=position_ids,
past_key_values=past_key_values,
inputs_embeds=inputs_embeds,
use_cache=use_cache,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
hidden_states = outputs[0]
logits = self.lm_head(hidden_states)
logits = logits.float()
loss = None
if labels is not None:
# Shift so that tokens < n predict n
shift_logits = logits[..., :-1, :].contiguous()
shift_labels = labels[..., 1:].contiguous()
# Flatten the tokens
loss_fct = CrossEntropyLoss()
shift_logits = shift_logits.view(-1, self.config.vocab_size)
shift_labels = shift_labels.view(-1)
# Enable model parallelism
shift_labels = shift_labels.to(shift_logits.device)
loss = loss_fct(shift_logits, shift_labels)
if not return_dict:
output = (logits, ) + outputs[1:]
return (loss, ) + output if loss is not None else output
return CausalLMOutputWithPast(
loss=loss,
logits=logits,
past_key_values=outputs.past_key_values,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
def prepare_inputs_for_generation(
self,
input_ids,
past_key_values=None,
attention_mask=None,
inputs_embeds=None,
**kwargs,
):
if past_key_values is not None:
if isinstance(past_key_values, Cache):
cache_length = past_key_values.get_seq_length()
# seen_tokens 可能在某些 transformers 版本中不存在，使用 getattr 安全访问
past_length = getattr(past_key_values, 'seen_tokens',
cache_length)
max_cache_length = past_key_values.get_max_length()
else:
cache_length = past_length = past_key_values[0][0].shape[2]
max_cache_length = None
# Keep only the unprocessed tokens:
# 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
# some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
# input)
if (attention_mask is not None
and attention_mask.shape[1] > input_ids.shape[1]):
input_ids = input_ids[:, -(attention_mask.shape[1] -
past_length):]
# 2 - If the past_length is smaller than input_ids', then input_ids holds all input tokens. We can discard
# input_ids based on the past_length.
elif past_length < input_ids.shape[1]:
input_ids = input_ids[:, past_length:]
# 3 - Otherwise (past_length >= input_ids.shape[1]), let's assume input_ids only has unprocessed tokens.
# If we are about to go beyond the maximum cache length, we need to crop the input attention mask.
if (max_cache_length is not None and attention_mask is not None
and cache_length + input_ids.shape[1] > max_cache_length):
attention_mask = attention_mask[:, -max_cache_length:]
position_ids = kwargs.get("position_ids", None)
if attention_mask is not None and position_ids is None:
# create position_ids on the fly for batch generation
position_ids = attention_mask.long().cumsum(-1) - 1
position_ids.masked_fill_(attention_mask == 0, 1)
if past_key_values:
position_ids = position_ids[:, -input_ids.shape[1]:]
# if `inputs_embeds` are passed, we only want to use them in the 1st generation step
if inputs_embeds is not None and past_key_values is None:
model_inputs = {"inputs_embeds": inputs_embeds}
else:
model_inputs = {"input_ids": input_ids}
model_inputs.update({
"position_ids": position_ids,
"past_key_values": past_key_values,
"use_cache": kwargs.get("use_cache"),
"attention_mask": attention_mask,
})
return model_inputs
@staticmethod
def _reorder_cache(past_key_values, beam_idx):
reordered_past = ()
for layer_past in past_key_values:
reordered_past += (tuple(
past_state.index_select(0, beam_idx.to(past_state.device))
for past_state in layer_past), )
return reordered_past
@add_start_docstrings(
"""
The DeepseekV3 Model transformer with a sequence classification head on top (linear layer).
[`DeepseekV3ForSequenceClassification`] uses the last token in order to do the classification, as other causal models
(e.g. GPT-2) do.
Since it does classification on the last token, it requires to know the position of the last token. If a
`pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If
no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the
padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last value in
each row of the batch).
""",
DeepseekV3_START_DOCSTRING,
)
class DeepseekV3ForSequenceClassification(DeepseekV3PreTrainedModel):
def __init__(self, config):
super().__init__(config)
self.num_labels = config.num_labels
self.model = DeepseekV3Model(config)
self.score = nn.Linear(config.hidden_size, self.num_labels, bias=False)
# Initialize weights and apply final processing
self.post_init()
def get_input_embeddings(self):
return self.model.embed_tokens
def set_input_embeddings(self, value):
self.model.embed_tokens = value
@add_start_docstrings_to_model_forward(DeepseekV3_INPUTS_DOCSTRING)
def forward(
self,
input_ids: torch.LongTensor = None,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_values: Optional[List[torch.FloatTensor]] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
use_cache: Optional[bool] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple, SequenceClassifierOutputWithPast]:
r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for computing the sequence classification/regression loss. Indices should be in `[0, transformers.,
config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
"""
return_dict = (return_dict if return_dict is not None else
self.config.use_return_dict)
transformer_outputs = self.model(
input_ids,
attention_mask=attention_mask,
position_ids=position_ids,
past_key_values=past_key_values,
inputs_embeds=inputs_embeds,
use_cache=use_cache,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
hidden_states = transformer_outputs[0]
logits = self.score(hidden_states)
if input_ids is not None:
batch_size = input_ids.shape[0]
else:
batch_size = inputs_embeds.shape[0]
if self.config.pad_token_id is None and batch_size != 1:
raise ValueError(
"Cannot handle batch sizes > 1 if no padding token is defined."
)
if self.config.pad_token_id is None:
sequence_lengths = -1
else:
if input_ids is not None:
sequence_lengths = (torch.eq(
input_ids, self.config.pad_token_id).int().argmax(-1) -
1).to(logits.device)
else:
sequence_lengths = -1
pooled_logits = logits[torch.arange(batch_size, device=logits.device),
sequence_lengths]
loss = None
if labels is not None:
labels = labels.to(logits.device)
if self.config.problem_type is None:
if self.num_labels == 1:
self.config.problem_type = "regression"
elif self.num_labels > 1 and (labels.dtype == torch.long
or labels.dtype == torch.int):
self.config.problem_type = "single_label_classification"
else:
self.config.problem_type = "multi_label_classification"
if self.config.problem_type == "regression":
loss_fct = MSELoss()
if self.num_labels == 1:
loss = loss_fct(pooled_logits.squeeze(), labels.squeeze())
else:
loss = loss_fct(pooled_logits, labels)
elif self.config.problem_type == "single_label_classification":
loss_fct = CrossEntropyLoss()
loss = loss_fct(pooled_logits.view(-1, self.num_labels),
labels.view(-1))
elif self.config.problem_type == "multi_label_classification":
loss_fct = BCEWithLogitsLoss()
loss = loss_fct(pooled_logits, labels)
if not return_dict:
output = (pooled_logits, ) + transformer_outputs[1:]
return ((loss, ) + output) if loss is not None else output
return SequenceClassifierOutputWithPast(
loss=loss,
logits=pooled_logits,
past_key_values=transformer_outputs.past_key_values,
hidden_states=transformer_outputs.hidden_states,
attentions=transformer_outputs.attentions,
)
>>>>> FILE: tokenization_kimi.py (13353 bytes) <<<<<
import os
from collections import OrderedDict
from logging import getLogger
from pathlib import Path
from shutil import copyfile
from typing import Any, Dict, Iterator, List, Optional, Tuple, Union, cast
import tiktoken
from tiktoken.load import load_tiktoken_bpe
from tokenizers import AddedToken
from transformers.convert_slow_tokenizer import bytes_to_unicode
from transformers.tokenization_utils import PreTrainedTokenizer
from .tool_declaration_ts import encode_tools_to_typescript_style
logger = getLogger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "tiktoken.model"}
class TikTokenTokenizer(PreTrainedTokenizer):
"""
Tokenizing and encoding/decoding text using the Tiktoken tokenizer. See megatron/tokenizer/tiktoken_tokenizer.py.
This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.
Args:
vocab_file (`str`):
The path to the Tiktoken model file.
bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|begin_of_text|>",`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|end_of_text|>"`):
The end of sequence token.
unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|reserved_special_token_249|>"`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead. The second to last item in special_tokens.
pad_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|reserved_special_token_250|>"`):
The token used for padding, for example when batching sequences of different lengths.
additional_special_tokens (list of `str`, *optional*):
A tuple or a list of additional tokens, which will be marked as `special`, meaning that they will be
skipped when decoding if `skip_special_tokens` is set to `True`.
"""
vocab_files_names = VOCAB_FILES_NAMES
model_input_names = ["input_ids", "attention_mask"]
special_tokens: Dict[str, int]
num_reserved_special_tokens = 256
pat_str = "|".join([
r"""[\p{Han}]+""",
r"""[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+(?i:'s|'t|'re|'ve|'m|'ll|'d)?""",
r"""[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*(?i:'s|'t|'re|'ve|'m|'ll|'d)?""",
r"""\p{N}{1,3}""",
r""" ?[^\s\p{L}\p{N}]+[\r\n]*""",
r"""\s*[\r\n]+""",
r"""\s+(?!\S)""",
r"""\s+""",
])
def __init__(
self,
vocab_file,
bos_token: Union[str, AddedToken] = "[BOS]",
eos_token: Union[str, AddedToken] = "[EOS]",
unk_token: Union[str, AddedToken, None] = None,
pad_token: Union[str, AddedToken, None] = None,
additional_special_tokens: List[str] = None,
added_tokens_decoder: Optional[dict] = None,
**kwargs,
):
assert os.path.isfile(vocab_file), vocab_file
if additional_special_tokens is None:
additional_special_tokens = [
"<|im_end|>",
"<|im_user|>",
"<|im_assistant|>",
"<|start_header_id|>",
"<|end_header_id|>",
"[EOT]",
"<|im_system|>",
"<|im_middle|>",
]
if added_tokens_decoder:
special_tokens_mapping = {
i: added_tokens_decoder[i].content
for i in added_tokens_decoder
}
else:
special_tokens_mapping = {}
self.vocab_file = vocab_file
mergeable_ranks = load_tiktoken_bpe(vocab_file)
num_base_tokens = len(mergeable_ranks)
self.special_tokens = {
special_tokens_mapping.get(i, f"<|reserved_token_{i}|>"): i
for i in range(num_base_tokens, num_base_tokens +
self.num_reserved_special_tokens)
}
self.model = tiktoken.Encoding(
name=Path(vocab_file).name,
pat_str=self.pat_str,
mergeable_ranks=mergeable_ranks,
special_tokens=self.special_tokens,
)
logger.info(f"Reloaded tiktoken model from {vocab_file}")
self.n_words: int = self.model.n_vocab
# BOS / EOS token IDs
self.bos_id: int = self.special_tokens[str(bos_token)]
self.eos_id: int = self.special_tokens[str(eos_token)]
logger.info(
f"#words: {self.n_words} - BOS ID: {self.bos_id} - EOS ID: {self.eos_id}"
)
self.pad_id: int = self.special_tokens[str(pad_token)]
self.unk_id: int = self.special_tokens[str(unk_token)]
self.byte_encoder = bytes_to_unicode()
self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
self.decoder = {}
for i in range(self.n_words):
# Taken from https://gist.github.com/xenova/a452a6474428de0182b17605a98631ee
decoding = ''.join([
self.byte_encoder[ord(char)] for char in
self.model.decode_single_token_bytes(i).decode('latin-1')
])
self.decoder[i] = decoding
self.encoder = {}
for i in range(self.n_words):
if i in self.decoder:
self.encoder[self.decoder[i]] = i
self._token_config_cache = OrderedDict()
self._cache_max_size = 128
super().__init__(
bos_token=bos_token,
eos_token=eos_token,
unk_token=unk_token,
pad_token=pad_token,
additional_special_tokens=additional_special_tokens,
added_tokens_decoder=added_tokens_decoder,
**kwargs,
)
self.all_special_ids_set = set(self.all_special_ids)
def encode(self,
text: str,
allow_special_tokens: bool = True,
**kwargs) -> List[int]:
"""
Encodes a string into a list of token IDs.
Args:
text (str): The input string to be encoded.
Returns:
list[int]: A list of token IDs.
"""
# If there are other args, we should call super().encode because there are a lot of code
# to handle those args. supper().encode finally will call _tokenize and _convert_token_to_id.
# NOTE: our encode method is not compatible with the super().encode method,
# e.g. split_special_tokens' default is True in our encode method.
if len(kwargs) > 0:
logger.warning(f"Calling super().encode with {kwargs}")
return super().encode(text, **kwargs)
assert type(text) is str
# The tiktoken tokenizer can handle <=400k chars without
# pyo3_runtime.PanicException.
TIKTOKEN_MAX_ENCODE_CHARS = 400_000
# https://github.com/openai/tiktoken/issues/195
# Here we iterate over subsequences and split if we exceed the limit
# of max consecutive non-whitespace or whitespace characters.
MAX_NO_WHITESPACES_CHARS = 25_000
texts = self.pre_tokenizer_process(text)
all_substrs = []
for text in texts:
substrs = (
substr for i in range(0, len(text), TIKTOKEN_MAX_ENCODE_CHARS)
for substr in self._split_whitespaces_or_nonwhitespaces(
text[i:i +
TIKTOKEN_MAX_ENCODE_CHARS], MAX_NO_WHITESPACES_CHARS))
all_substrs.extend(substrs)
t: List[int] = []
for substr in all_substrs:
if allow_special_tokens:
t.extend(
# we should consider special token as a common token
self.model.encode(
substr,
allowed_special="all",
))
else:
t.extend(
# we should consider special token as a common token
self.model.encode(
substr,
disallowed_special=(),
))
return t
def decode(self, token_ids: Union[int, List[int]], **kwargs) -> str:
"""
Decodes a list of token IDs into a string.
Args:
token_ids (List[int]): The list of token IDs to be decoded.
Returns:
str: The decoded string.
"""
# If there are other args, we should call super().decode because there are a lot of code
# to handle those args. supper().encode finally will call convert_tokens_to_string and _convert_id_to_token.
if len(kwargs) > 0:
return super().decode(token_ids, **kwargs)
if type(token_ids) is int:
token_ids = [token_ids]
return self.model.decode(cast(List[int], token_ids))
@staticmethod
def _split_whitespaces_or_nonwhitespaces(
s: str, max_consecutive_slice_len: int) -> Iterator[str]:
"""
Splits the string `s` so that each substring contains no more than `max_consecutive_slice_len`
consecutive whitespaces or consecutive non-whitespaces.
"""
current_slice_len = 0
current_slice_is_space = s[0].isspace() if len(s) > 0 else False
slice_start = 0
for i in range(len(s)):
is_now_space = s[i].isspace()
if current_slice_is_space ^ is_now_space:
current_slice_len = 1
current_slice_is_space = is_now_space
else:
current_slice_len += 1
if current_slice_len > max_consecutive_slice_len:
yield s[slice_start:i]
slice_start = i
current_slice_len = 1
yield s[slice_start:]
def pre_tokenizer_process(self, text: str) -> List[str]:
"""
pre-tokenizes the input text into a list of tokens.
This method is used to split the input text into smaller chunks for internal processing.
"""
return [text]
""" ----- Below are the abstract methods required by PreTrainedTokenizer ----- """
@property
def vocab_size(self) -> int:
return self.n_words
def get_vocab(self) -> Dict[str, int]:
return self.encoder
def _tokenize(self, text: str, **kwargs) -> List[str]:
return [self.decoder[t] for t in self.encode(text)]
def _convert_token_to_id(self, token: str) -> int:
return self.encoder.get(token, self.unk_id)
def _convert_id_to_token(self, index: int) -> str:
return self.decoder.get(index)
@staticmethod
def clean_up_tokenization(out_string: str) -> str:
return out_string
def convert_tokens_to_string(self, tokens: List[str]) -> str:
text = ''.join(tokens)
text = bytearray([self.byte_decoder[c]
for c in text]).decode('utf-8', 'replace')
return text
def save_vocabulary(self,
save_directory: str,
filename_prefix: Optional[str] = None) -> Tuple[str]:
if not os.path.isdir(save_directory):
raise ValueError(
f"vocabulary path ({save_directory}) should be a directory")
out_vocab_file = os.path.join(
save_directory,
(filename_prefix + "-" if filename_prefix else "") +
VOCAB_FILES_NAMES["vocab_file"])
if os.path.abspath(self.vocab_file) != os.path.abspath(
out_vocab_file) and os.path.isfile(self.vocab_file):
copyfile(self.vocab_file, out_vocab_file)
return (out_vocab_file, )
def apply_chat_template(self,
conversation,
tools: Optional[list[dict]] = None,
tokenize: bool = False,
add_generation_prompt: bool = True,
thinking: bool = True,
**kwargs):
tools = deep_sort_dict(tools)
# Convert tools to TypeScript style string if tools are provided
tools_ts_str = None
if tools:
try:
tools_ts_str = encode_tools_to_typescript_style(tools)
except Exception as e:
print(f"Failed to convert tools to TypeScript style: {e}")
tools_ts_str = None
# Store the TypeScript string in kwargs so it can be accessed by the template
if tools_ts_str is not None:
kwargs['tools_ts_str'] = tools_ts_str
return super().apply_chat_template(
conversation,
tools=tools,
tokenize=tokenize,
add_generation_prompt=add_generation_prompt,
thinking=thinking,
**kwargs)
def deep_sort_dict(obj: Any) -> Any:
if isinstance(obj, dict):
return {k: deep_sort_dict(v) for k, v in sorted(obj.items())}
if isinstance(obj, list):
return [deep_sort_dict(item) for item in obj]
return obj
>>>>> FILE: kimi_k25_processor.py (6906 bytes) <<<<<
from transformers.feature_extraction_utils import BatchFeature
from transformers.processing_utils import ProcessorMixin
from transformers.utils import logging
logger = logging.get_logger(__name__)
class KimiK25Processor(ProcessorMixin):