fix sequence length in santacoder and introduce new model type

README.md

@@ -1,19 +1,20 @@
 ---
-license: bigcode-openrail-m
+license: openrail
 datasets:
 - bigcode/the-stack
 language:
 - code
-programming_language:
+programming_language: 
 - Java
 - JavaScript
 - Python
 pipeline_tag: text-generation
-inference: true
+inference: false
 widget:
 - text: 'def print_hello_world():'
   example_title: Hello world
   group: Python
+
 model-index:
 - name: SantaCoder
   results:
@@ -87,7 +88,7 @@ model-index:
       verified: false
     - name: pass@100
       type: pass@100
-      value: 0.7
+      value: 0.70
       verified: false
   - task:
       type: text-generation
@@ -153,7 +154,7 @@ model-index:
     metrics:
     - name: single_line
       type: exact_match
-      value: 0.6
+      value: 0.60
       verified: false
   - task:
       type: text-generation
@@ -185,11 +186,11 @@ Play with the model on the [SantaCoder Space Demo](https://huggingface.co/spaces
 # Model Summary
 
 The SantaCoder models are a series of 1.1B parameter models trained on the Python, Java, and JavaScript subset of [The Stack (v1.1)](https://huggingface.co/datasets/bigcode/the-stack) (which excluded opt-out requests). 
-The main model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), a context window of 2048 tokens, and was trained using near-deduplication and comment-to-code ratio as filtering criteria and using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255).
+The main model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), was trained using near-deduplication and comment-to-code ratio as filtering criteria and using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255).
 In addition there are several models that were trained on datasets with different filter parameters and with architecture and objective variations. 
 
 - **Repository:** [bigcode/Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
-- **Project Website:** [bigcode-project.org](https://www.bigcode-project.org)
+- **Project Website:** [bigcode-project.org](www.bigcode-project.org)
 - **Paper:** [🎅SantaCoder: Don't reach for the stars!🌟](https://arxiv.org/abs/2301.03988)
 - **Point of Contact:** [contact@bigcode-project.org](mailto:contact@bigcode-project.org)
 - **Languages:** Python, Java, and JavaScript
@@ -243,7 +244,6 @@ inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
 outputs = model.generate(inputs)
 print(tokenizer.decode(outputs[0]))
 ```
-Make sure to use `<fim-prefix>, <fim-suffix>, <fim-middle>` and not  `<fim_prefix>, <fim_suffix>, <fim_middle>` as in StarCoder models.
 
 ### Load other checkpoints
 We upload the checkpoint of each experiment to a separate branch as well as the intermediate checkpoints as commits on the branches. You can load them with the `revision` flag:
@@ -286,7 +286,7 @@ The model has been trained on source code in Python, Java, and JavaScript. The p
 - **FP16 if applicable:** [apex](https://github.com/NVIDIA/apex)
 
 # License
-The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement [here](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement).
+The model is licenses under the CodeML Open RAIL-M v0.1 license. You can find the full license [here](https://huggingface.co/spaces/bigcode/license).
 
 # Citation
 ```

config.json

@@ -9,12 +9,12 @@
     "AutoConfig": "configuration_gpt2_mq.GPT2CustomConfig",
     "AutoModelForCausalLM": "modeling_gpt2_mq.GPT2LMHeadCustomModel"
   },
-  "bos_token_id": 49152,
+  "bos_token_id": 50256,
   "embd_pdrop": 0.1,
-  "eos_token_id": 49152,
+  "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
+  "model_type": "santacoder",
   "n_embd": 2048,
   "n_head": 16,
   "n_inner": 8192,

modeling_gpt2_mq.py

@@ -1,39 +1,21 @@
 """PyTorch OpenAI GPT-2 model modified with MultiQuery attention"""
 
 
-import math
-import os
-from dataclasses import dataclass
 from typing import Optional, Tuple, Union
 
 import torch
 import torch.utils.checkpoint
 from torch import nn
 from torch.cuda.amp import autocast
-from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
-
-from transformers.activations import ACT2FN
-from transformers.modeling_outputs import (
-    BaseModelOutputWithPastAndCrossAttentions,
-    CausalLMOutputWithCrossAttentions,
-    SequenceClassifierOutputWithPast,
-    TokenClassifierOutput,
-)
-from transformers.modeling_utils import PreTrainedModel, SequenceSummary
+
+from transformers.modeling_outputs import BaseModelOutputWithPastAndCrossAttentions
 from transformers.pytorch_utils import Conv1D, find_pruneable_heads_and_indices, prune_conv1d_layer
 
-from transformers.utils import (
-    ModelOutput,
-    add_code_sample_docstrings,
-    add_start_docstrings,
-    add_start_docstrings_to_model_forward,
-    logging,
-    replace_return_docstrings,
-)
-from transformers.utils.model_parallel_utils import assert_device_map, get_device_map
+from transformers.utils import logging
 from transformers.models.gpt2.modeling_gpt2 import GPT2Model, GPT2Block, GPT2PreTrainedModel, GPT2LMHeadModel
-from .configuration_gpt2_mq import GPT2CustomConfig, MULTI_QUERY, MULTI_HEAD
+from .configuration_gpt2_mq import GPT2CustomConfig, MULTI_QUERY
 
+logger = logging.get_logger(__name__)
 
 
 class GPT2MQAttention(nn.Module):
@@ -329,6 +311,201 @@ class GPT2CustomModel(GPT2Model):
         # Initialize weights and apply final processing
         self.post_init()
 
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Tuple[Tuple[torch.Tensor]]] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        token_type_ids: Optional[torch.LongTensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        head_mask: Optional[torch.FloatTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: 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, BaseModelOutputWithPastAndCrossAttentions]:
+        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
+
+        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:
+            input_shape = input_ids.size()
+            input_ids = input_ids.view(-1, input_shape[-1])
+            batch_size = input_ids.shape[0]
+        elif inputs_embeds is not None:
+            input_shape = inputs_embeds.size()[:-1]
+            batch_size = inputs_embeds.shape[0]
+        else:
+            raise ValueError("You have to specify either input_ids or inputs_embeds")
+
+        device = input_ids.device if input_ids is not None else inputs_embeds.device
+
+        if token_type_ids is not None:
+            token_type_ids = token_type_ids.view(-1, input_shape[-1])
+        if position_ids is not None:
+            position_ids = position_ids.view(-1, input_shape[-1])
+
+        if past_key_values is None:
+            past_length = 0
+            past_key_values = tuple([None] * len(self.h))
+        else:
+            # this is different from GPT2
+            past_length = past_key_values[0][0].size(-1)
+        if position_ids is None:
+            position_ids = torch.arange(past_length, input_shape[-1] + past_length, dtype=torch.long, device=device)
+            position_ids = position_ids.unsqueeze(0).view(-1, input_shape[-1])
+
+        # GPT2Attention mask.
+        if attention_mask is not None:
+            if batch_size <= 0:
+                raise ValueError("batch_size has to be defined and > 0")
+            attention_mask = attention_mask.view(batch_size, -1)
+            # We create a 3D attention mask from a 2D tensor mask.
+            # Sizes are [batch_size, 1, 1, to_seq_length]
+            # So we can broadcast to [batch_size, num_heads, from_seq_length, to_seq_length]
+            # this attention mask is more simple than the triangular masking of causal attention
+            # used in OpenAI GPT, we just need to prepare the broadcast dimension here.
+            attention_mask = attention_mask[:, None, None, :]
+
+            # Since attention_mask is 1.0 for positions we want to attend and 0.0 for
+            # masked positions, this operation will create a tensor which is 0.0 for
+            # positions we want to attend and the dtype's smallest value for masked positions.
+            # Since we are adding it to the raw scores before the softmax, this is
+            # effectively the same as removing these entirely.
+            attention_mask = attention_mask.to(dtype=self.dtype)  # fp16 compatibility
+            attention_mask = (1.0 - attention_mask) * torch.finfo(self.dtype).min
+
+        # If a 2D or 3D attention mask is provided for the cross-attention
+        # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
+        if self.config.add_cross_attention and encoder_hidden_states is not None:
+            encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size()
+            encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
+            if encoder_attention_mask is None:
+                encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device)
+            encoder_attention_mask = self.invert_attention_mask(encoder_attention_mask)
+        else:
+            encoder_attention_mask = None
+
+        # Prepare head mask if needed
+        # 1.0 in head_mask indicate we keep the head
+        # attention_probs has shape bsz x n_heads x N x N
+        # head_mask has shape n_layer x batch x n_heads x N x N
+        head_mask = self.get_head_mask(head_mask, self.config.n_layer)
+
+        if inputs_embeds is None:
+            inputs_embeds = self.wte(input_ids)
+        position_embeds = self.wpe(position_ids)
+        hidden_states = inputs_embeds + position_embeds
+
+        if token_type_ids is not None:
+            token_type_embeds = self.wte(token_type_ids)
+            hidden_states = hidden_states + token_type_embeds
+
+        hidden_states = self.drop(hidden_states)
+
+        output_shape = input_shape + (hidden_states.size(-1),)
+
+        presents = () if use_cache else None
+        all_self_attentions = () if output_attentions else None
+        all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
+        all_hidden_states = () if output_hidden_states else None
+        for i, (block, layer_past) in enumerate(zip(self.h, past_key_values)):
+
+            # Model parallel
+            if self.model_parallel:
+                torch.cuda.set_device(hidden_states.device)
+                # Ensure layer_past is on same device as hidden_states (might not be correct)
+                if layer_past is not None:
+                    layer_past = tuple(past_state.to(hidden_states.device) for past_state in layer_past)
+                # Ensure that attention_mask is always on the same device as hidden_states
+                if attention_mask is not None:
+                    attention_mask = attention_mask.to(hidden_states.device)
+                if isinstance(head_mask, torch.Tensor):
+                    head_mask = head_mask.to(hidden_states.device)
+            if output_hidden_states:
+                all_hidden_states = all_hidden_states + (hidden_states,)
+
+            if self.gradient_checkpointing and self.training:
+
+                if use_cache:
+                    logger.warning(
+                        "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
+                    )
+                    use_cache = False
+
+                def create_custom_forward(module):
+                    def custom_forward(*inputs):
+                        # None for past_key_value
+                        return module(*inputs, use_cache, output_attentions)
+
+                    return custom_forward
+
+                outputs = torch.utils.checkpoint.checkpoint(
+                    create_custom_forward(block),
+                    hidden_states,
+                    None,
+                    attention_mask,
+                    head_mask[i],
+                    encoder_hidden_states,
+                    encoder_attention_mask,
+                )
+            else:
+                outputs = block(
+                    hidden_states,
+                    layer_past=layer_past,
+                    attention_mask=attention_mask,
+                    head_mask=head_mask[i],
+                    encoder_hidden_states=encoder_hidden_states,
+                    encoder_attention_mask=encoder_attention_mask,
+                    use_cache=use_cache,
+                    output_attentions=output_attentions,
+                )
+
+            hidden_states = outputs[0]
+            if use_cache is True:
+                presents = presents + (outputs[1],)
+
+            if output_attentions:
+                all_self_attentions = all_self_attentions + (outputs[2 if use_cache else 1],)
+                if self.config.add_cross_attention:
+                    all_cross_attentions = all_cross_attentions + (outputs[3 if use_cache else 2],)
+
+            # Model Parallel: If it's the last layer for that device, put things on the next device
+            if self.model_parallel:
+                for k, v in self.device_map.items():
+                    if i == v[-1] and "cuda:" + str(k) != self.last_device:
+                        hidden_states = hidden_states.to("cuda:" + str(k + 1))
+
+        hidden_states = self.ln_f(hidden_states)
+
+        hidden_states = hidden_states.view(output_shape)
+        # Add last hidden state
+        if output_hidden_states:
+            all_hidden_states = all_hidden_states + (hidden_states,)
+
+        if not return_dict:
+            return tuple(
+                v
+                for v in [hidden_states, presents, all_hidden_states, all_self_attentions, all_cross_attentions]
+                if v is not None
+            )
+
+        return BaseModelOutputWithPastAndCrossAttentions(
+            last_hidden_state=hidden_states,
+            past_key_values=presents,
+            hidden_states=all_hidden_states,
+            attentions=all_self_attentions,
+            cross_attentions=all_cross_attentions,
+        )
+
 
 class GPT2LMHeadCustomModel(GPT2LMHeadModel):
     config_class = GPT2CustomConfig