A continuation of DEEPSEEK_R1_COMPLETE.txt. The complete source identity, every recorded occurrence, and linked equations are on its first page.
Source transcript · continued
Download complete source text ↓4,262 lines · 205.4 KB
# 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 += past_key_value.get_usable_length(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 = past_key_values.get_usable_length(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()
past_length = past_key_values.seen_tokens
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 exclusivelly 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,
)
================================================================================
15.4 generation_config.json
================================================================================
{
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": 1,
"do_sample": true,
"temperature": 0.6,
"top_p": 0.95,
"transformers_version": "4.39.3"
}
================================================================================
15.5 tokenizer_config.json
(the chat template is the long single-line "chat_template" value)
================================================================================
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<｜begin▁of▁sentence｜>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "<｜end▁of▁sentence｜>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"legacy": true,
"model_max_length": 16384,
"pad_token": {
"__type": "AddedToken",
"content": "<｜end▁of▁sentence｜>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sp_model_kwargs": {},
"unk_token": null,
"tokenizer_class": "LlamaTokenizerFast",
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\\n\\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' in message %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{'<｜Assistant｜>' + message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' not in message %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}"
}
================================================================================
15.6 README.md (official model card)
================================================================================
---
license: mit
library_name: transformers
---
# DeepSeek-R1
<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
<!-- markdownlint-disable no-duplicate-header -->
<div align="center">
<img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
</div>
<hr>
<div align="center" style="line-height: 1;">
<a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
<img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
<img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20R1-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
<img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
</a>
</div>
<div align="center" style="line-height: 1;">
<a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
<img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
<img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
<img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
</a>
</div>
<div align="center" style="line-height: 1;">
<a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE" style="margin: 2px;">
<img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
</a>
</div>
<p align="center">
<a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf"><b>Paper Link</b>👁️</a>
</p>
## 1. Introduction
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning.
With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.
However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance,
we introduce DeepSeek-R1, which incorporates cold-start data before RL.
DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks.
To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
**NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](#usage-recommendations) section.**
<p align="center">
<img width="80%" src="figures/benchmark.jpg">
</p>
## 2. Model Summary
---
**Post-Training: Large-Scale Reinforcement Learning on the Base Model**
- We directly apply reinforcement learning (RL) to the base model without relying on supervised fine-tuning (SFT) as a preliminary step. This approach allows the model to explore chain-of-thought (CoT) for solving complex problems, resulting in the development of DeepSeek-R1-Zero. DeepSeek-R1-Zero demonstrates capabilities such as self-verification, reflection, and generating long CoTs, marking a significant milestone for the research community. Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT. This breakthrough paves the way for future advancements in this area.
- We introduce our pipeline to develop DeepSeek-R1. The pipeline incorporates two RL stages aimed at discovering improved reasoning patterns and aligning with human preferences, as well as two SFT stages that serve as the seed for the model's reasoning and non-reasoning capabilities.
We believe the pipeline will benefit the industry by creating better models.
---
**Distillation: Smaller Models Can Be Powerful Too**
- We demonstrate that the reasoning patterns of larger models can be distilled into smaller models, resulting in better performance compared to the reasoning patterns discovered through RL on small models. The open source DeepSeek-R1, as well as its API, will benefit the research community to distill better smaller models in the future.
- Using the reasoning data generated by DeepSeek-R1, we fine-tuned several dense models that are widely used in the research community. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community.
## 3. Model Downloads
### DeepSeek-R1 Models
<div align="center">
| **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
| :------------: | :------------: | :------------: | :------------: | :------------: |
| DeepSeek-R1-Zero | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero) |
| DeepSeek-R1 | 671B | 37B | 128K | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
</div>
DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base.
For more details regarding the model architecture, please refer to [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repository.
### DeepSeek-R1-Distill Models
<div align="center">
| **Model** | **Base Model** | **Download** |
| :------------: | :------------: | :------------: |
| DeepSeek-R1-Distill-Qwen-1.5B | [Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) |
| DeepSeek-R1-Distill-Qwen-7B | [Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) |
| DeepSeek-R1-Distill-Llama-8B | [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) |
| DeepSeek-R1-Distill-Qwen-14B | [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) |
|DeepSeek-R1-Distill-Qwen-32B | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) |
| DeepSeek-R1-Distill-Llama-70B | [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) |
</div>
DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.
We slightly change their configs and tokenizers. Please use our setting to run these models.
## 4. Evaluation Results
### DeepSeek-R1-Evaluation
For all our models, the maximum generation length is set to 32,768 tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 64 responses per query to estimate pass@1.
<div align="center">
| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |
|----------|-------------------|----------------------|------------|--------------|----------------|------------|--------------|
| | Architecture | - | - | MoE | - | - | MoE |
| | # Activated Params | - | - | 37B | - | - | 37B |
| | # Total Params | - | - | 671B | - | - | 671B |
| English | MMLU (Pass@1) | 88.3 | 87.2 | 88.5 | 85.2 | **91.8** | 90.8 |
| | MMLU-Redux (EM) | 88.9 | 88.0 | 89.1 | 86.7 | - | **92.9** |
| | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |
| | DROP (3-shot F1) | 88.3 | 83.7 | 91.6 | 83.9 | 90.2 | **92.2** |
| | IF-Eval (Prompt Strict) | **86.5** | 84.3 | 86.1 | 84.8 | - | 83.3 |
| | GPQA-Diamond (Pass@1) | 65.0 | 49.9 | 59.1 | 60.0 | **75.7** | 71.5 |
| | SimpleQA (Correct) | 28.4 | 38.2 | 24.9 | 7.0 | **47.0** | 30.1 |
| | FRAMES (Acc.) | 72.5 | 80.5 | 73.3 | 76.9 | - | **82.5** |
| | AlpacaEval2.0 (LC-winrate) | 52.0 | 51.1 | 70.0 | 57.8 | - | **87.6** |
| | ArenaHard (GPT-4-1106) | 85.2 | 80.4 | 85.5 | 92.0 | - | **92.3** |
| Code | LiveCodeBench (Pass@1-COT) | 33.8 | 34.2 | - | 53.8 | 63.4 | **65.9** |
| | Codeforces (Percentile) | 20.3 | 23.6 | 58.7 | 93.4 | **96.6** | 96.3 |
| | Codeforces (Rating) | 717 | 759 | 1134 | 1820 | **2061** | 2029 |
| | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |
| | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 |
| Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** |
| | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** |
| | CNMO 2024 (Pass@1) | 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** |
| Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** |
| | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** |
| | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 |
</div>
### Distilled Model Evaluation
<div align="center">
| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |
|------------------------------------------|------------------|-------------------|-----------------|----------------------|----------------------|-------------------|
| GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 |
| Claude-3.5-Sonnet-1022 | 16.0 | 26.7 | 78.3 | 65.0 | 38.9 | 717 |
| o1-mini | 63.6 | 80.0 | 90.0 | 60.0 | 53.8 | **1820** |
| QwQ-32B-Preview | 44.0 | 60.0 | 90.6 | 54.5 | 41.9 | 1316 |
| DeepSeek-R1-Distill-Qwen-1.5B | 28.9 | 52.7 | 83.9 | 33.8 | 16.9 | 954 |
| DeepSeek-R1-Distill-Qwen-7B | 55.5 | 83.3 | 92.8 | 49.1 | 37.6 | 1189 |
| DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 |
| DeepSeek-R1-Distill-Qwen-32B | **72.6** | 83.3 | 94.3 | 62.1 | 57.2 | 1691 |
| DeepSeek-R1-Distill-Llama-8B | 50.4 | 80.0 | 89.1 | 49.0 | 39.6 | 1205 |
| DeepSeek-R1-Distill-Llama-70B | 70.0 | **86.7** | **94.5** | **65.2** | **57.5** | 1633 |
</div>
## 5. Chat Website & API Platform
You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com), and switch on the button "DeepThink"
We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/)
## 6. How to Run Locally
### DeepSeek-R1 Models
Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running DeepSeek-R1 locally.
**NOTE: Hugging Face's Transformers has not been directly supported yet.**
### DeepSeek-R1-Distill Models
DeepSeek-R1-Distill models can be utilized in the same manner as Qwen or Llama models.
For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm):
```shell
vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager
```
You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang)
```bash
python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2
```
### Usage Recommendations
**We recommend adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance:**
1. Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
2. **Avoid adding a system prompt; all instructions should be contained within the user prompt.**
3. For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
4. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
Additionally, we have observed that the DeepSeek-R1 series models tend to bypass thinking pattern (i.e., outputting "\<think\>\n\n\</think\>") when responding to certain queries, which can adversely affect the model's performance.
**To ensure that the model engages in thorough reasoning, we recommend enforcing the model to initiate its response with "\<think\>\n" at the beginning of every output.**
## 7. License
This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that:
- DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B are derived from [Qwen-2.5 series](https://github.com/QwenLM/Qwen2.5), which are originally licensed under [Apache 2.0 License](https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE), and now finetuned with 800k samples curated with DeepSeek-R1.
- DeepSeek-R1-Distill-Llama-8B is derived from Llama3.1-8B-Base and is originally licensed under [llama3.1 license](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE).
- DeepSeek-R1-Distill-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under [llama3.3 license](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE).
## 8. Citation
```
@misc{deepseekai2025deepseekr1incentivizingreasoningcapability,
title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning},
author={DeepSeek-AI},
year={2025},
eprint={2501.12948},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2501.12948},
}
```
## 9. Contact
If you have any questions, please raise an issue or contact us at [[contact email redacted]]([contact email redacted]).
================================================================================
END OF DOCUMENT
================================================================================