Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+language:
+  - en
+tags:
+- pretrained
+inference:
+  parameters:
+    temperature: 0.7
+---
+
+# Model Card for Mistral-7B-v0.1
+
+The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. 
+Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.
+
+For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/).
+
+## Model Architecture
+
+Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
+- Grouped-Query Attention
+- Sliding-Window Attention
+- Byte-fallback BPE tokenizer
+
+## Troubleshooting
+
+- If you see the following error:
+```
+KeyError: 'mistral'
+```
+- Or:
+```
+NotImplementedError: Cannot copy out of meta tensor; no data!
+```
+
+Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer.
+
+## Notice
+
+Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms.
+
+## The Mistral AI Team
+ 
+Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralDenseFormerForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "winglian/mistral-denseformer-7b--configuration_mistral.MistralDenseFormerConfig",
+    "AutoModelForCausalLM": "winglian/mistral-denseformer-7b--modeling_mistral.MistralDenseFormerForCausalLM"
+  },
+  "dilation": 4,
+  "dwa_period": 5,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral_denseformer",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

configuration_mistral.py

@@ -0,0 +1,11 @@
+from transformers import MistralConfig
+
+
+class MistralDenseFormerConfig(MistralConfig):
+    model_type = "mistral_denseformer"
+
+    def __init__(self, *args, dilation=4, dwa_period=5, **kwargs):
+        self.dilation = dilation
+        self.dwa_period = dwa_period
+        super().__init__(*args, **kwargs)
+

denseformer.py

@@ -0,0 +1,64 @@
+import torch
+
+
+class InPlaceSetSlice(torch.autograd.Function):
+
+  @staticmethod
+  def forward(ctx, full_tensor, last_slice, x_idx, x_val):
+    full_tensor[x_idx] = x_val
+    ctx.x_idx = x_idx
+    ret = torch.Tensor().to(full_tensor.device)
+    ret.set_(full_tensor[:x_idx + 1])
+    return ret
+
+  @staticmethod
+  def backward(ctx, grad_out):
+    if ctx.x_idx == 0:
+      return None, None, None, grad_out[ctx.x_idx]
+    else:
+      return None, grad_out[:ctx.x_idx], None, grad_out[ctx.x_idx]
+
+
+def apply_inplace_set(x_acc, x_idx, x_val):
+  full_tensor, last_slice = x_acc
+  new_slice = InPlaceSetSlice.apply(full_tensor, last_slice, x_idx, x_val)
+  return full_tensor, new_slice
+
+
+class DWAModules(torch.nn.Module):
+
+  def __init__(self, n_blocks, dilation=1, period=1):
+    super().__init__()
+    self.n_blocks = n_blocks
+    self.dilation = dilation
+    self.period = period
+    self.alphas = torch.nn.ModuleList([torch.nn.Linear((i+1+dilation)//dilation, 1, bias=False) if (i+1)%period == 0 else None for i in range(n_blocks)])
+    self.accumulators = None
+    self._init_weights()
+
+  def _init_weights(self):
+    for module in self.alphas:
+      if module is not None:
+        module.weight.data.zero_()
+        module.weight.data[0, -1] = 1.
+
+  def init_accumulators(self, x):
+    x_accs = []
+    for i in range(self.dilation):
+      current_group_size = (self.n_blocks + 1) // self.dilation
+      if i < (self.n_blocks + 1) % self.dilation:
+        current_group_size += 1
+      x_accs.append((torch.zeros((current_group_size, *x.shape), device=x.device, dtype=x.dtype), None))
+    x_accs[0] = apply_inplace_set(x_accs[0], 0, x)
+    self.accumulators = x_accs
+
+  def forward(self, x, block_idx):
+    assert self.accumulators is not None, "`init_accumulators(x)` needs to be called first"
+    self.accumulators[(block_idx+1) % self.dilation] = apply_inplace_set(
+        self.accumulators[(block_idx+1) % self.dilation], 
+        (block_idx+1)//self.dilation,
+        x  
+    )
+    if (block_idx+1) % self.period == 0:
+      x = torch.tensordot(self.alphas[block_idx].weight.view(-1), self.accumulators[(block_idx+1)%self.dilation][1], dims=1)
+    return x

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9742cb4764964155b7a5f35eefad651f590006091ddeb536863d6c5865cca1b9
+size 9942981696

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcf56354ec0c68b5f8e97b4f3b02d16af899a65b0868d6dba5a51c1b30f01cb
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+    "metadata": {
+        "total_size": 14483464192
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

modeling_mistral.py

@@ -0,0 +1,209 @@
+import logging
+from typing import Optional, List, Tuple, Union
+
+import torch
+from torch import nn
+from transformers import DynamicCache, Cache
+from transformers.modeling_attn_mask_utils import _prepare_4d_causal_attention_mask, \
+    _prepare_4d_causal_attention_mask_for_sdpa
+from transformers.modeling_outputs import BaseModelOutputWithPast
+from transformers.models.mistral.modeling_mistral import MistralPreTrainedModel, MistralDecoderLayer, MistralRMSNorm, \
+    MistralForCausalLM
+from .configuration_mistral import MistralDenseFormerConfig
+from .denseformer import DWAModules
+
+logger = logging.get_logger(__name__)
+
+
+class MistralDenseFormerModel(MistralPreTrainedModel):
+    """
+    Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`MistralDecoderLayer`]
+
+    Args:
+        config: MistralConfig
+    """
+
+    def __init__(self, config: MistralDenseFormerConfig):
+        super().__init__(config)
+        self.padding_idx = config.pad_token_id
+        self.vocab_size = config.vocab_size
+
+        self.dwa_modules = DWAModules(config.num_hidden_layers, config.dilation, config.dwa_period)
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
+        self.layers = nn.ModuleList(
+            [MistralDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
+        )
+        self._attn_implementation = config._attn_implementation
+        self.norm = MistralRMSNorm(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
+
+    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 decoder_input_ids and decoder_inputs_embeds at the same time")
+        elif input_ids is not None:
+            batch_size, seq_length = input_ids.shape
+        elif inputs_embeds is not None:
+            batch_size, seq_length, _ = inputs_embeds.shape
+        else:
+            raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds")
+
+        if self.gradient_checkpointing and self.training:
+            if use_cache:
+                logger.warning_once(
+                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
+                )
+                use_cache = False
+
+        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).view(-1, seq_length)
+        else:
+            position_ids = position_ids.view(-1, seq_length).long()
+
+        if inputs_embeds is None:
+            inputs_embeds = self.embed_tokens(input_ids)
+
+        if attention_mask is not None and self._attn_implementation == "flash_attention_2" and use_cache:
+            is_padding_right = attention_mask[:, -1].sum().item() != batch_size
+            if is_padding_right:
+                raise ValueError(
+                    "You are attempting to perform batched generation with padding_side='right'"
+                    " this may lead to unexpected behaviour for Flash Attention version of Mistral. Make sure to "
+                    " call `tokenizer.padding_side  = 'left'` before tokenizing the input. "
+                )
+
+        if self._attn_implementation == "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
+        elif self._attn_implementation == "sdpa" and not output_attentions:
+            # output_attentions=True can not be supported when using SDPA, and we fall back on
+            # the manual implementation that requires a 4D causal mask in all cases.
+            attention_mask = _prepare_4d_causal_attention_mask_for_sdpa(
+                attention_mask,
+                (batch_size, seq_length),
+                inputs_embeds,
+                past_key_values_length,
+            )
+        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,
+                sliding_window=self.config.sliding_window,
+            )
+
+        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
+
+        self.dwa_modules.init_accumulators(hidden_states)
+
+        for layer_idx, decoder_layer in enumerate(self.layers):
+            if output_hidden_states:
+                all_hidden_states += (hidden_states,)
+
+            if self.gradient_checkpointing and self.training:
+                layer_outputs = self._gradient_checkpointing_func(
+                    decoder_layer.__call__,
+                    hidden_states,
+                    attention_mask,
+                    position_ids,
+                    past_key_values,
+                    output_attentions,
+                    use_cache,
+                )
+            else:
+                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.dwa_modules(hidden_states, block_idx=layer_idx)
+
+        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 MistralDenseFormerForCausalLM(MistralForCausalLM):
+    def __init__(self, config: MistralDenseFormerConfig):
+        super().__init__(config)
+        self.model = MistralDenseFormerModel(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()
+

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}