Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "/fast/gsu/downloadmodels/7b/llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "customllama",
+  "auto_map": {
+    "AutoConfig": "configuration_customllama.CustomLlamaConfig",
+    "AutoModelForCausalLM": "modeling_customllama.CustomLlamaForCausalLM"
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 23,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "scales": [
+    1.0,
+    1.0,
+    1.0278732834267,
+    1.0007125033084,
+    1.0372524019845,
+    1.0777305076805,
+    1.1949117035846,
+    0.8763010948154,
+    1.2810249285471,
+    0.8625149492519,
+    0.9961008444105,
+    1.0,
+    1.0,
+    1.0,
+    1.0,
+    1.1784337435162,
+    1.0,
+    1.0,
+    1.0,
+    1.0,
+    1.0,
+    1.0,
+    1.0
+  ],
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

configuration_customllama.py

@@ -0,0 +1,82 @@
+from transformers import PretrainedConfig
+from typing import List
+from transformers.modeling_rope_utils import rope_config_validation
+
+
+class CustomLlamaConfig(PretrainedConfig):
+    model_type = "customllama"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    # Default tensor parallel plan for base model `LlamaModel`
+    base_model_tp_plan = {
+        "layers.*.self_attn.q_proj": "colwise",
+        "layers.*.self_attn.k_proj": "colwise",
+        "layers.*.self_attn.v_proj": "colwise",
+        "layers.*.self_attn.o_proj": "rowwise",
+        "layers.*.mlp.gate_proj": "colwise",
+        "layers.*.mlp.up_proj": "colwise",
+        "layers.*.mlp.down_proj": "rowwise",
+    }
+
+    def __init__(
+        self,
+        vocab_size=32000,
+        hidden_size=4096,
+        intermediate_size=11008,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        hidden_act="silu",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=1,
+        eos_token_id=2,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        mlp_bias=False,
+        head_dim=None,
+        scales=None,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+        self.mlp_bias = mlp_bias
+        self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads
+        self.scales = scales
+       
+        if self.rope_scaling is not None and "type" in self.rope_scaling:
+            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
+        rope_config_validation(self)
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b526832ac4c4d2679491edcc73010c188542ac5fdf720ae97b62df98c5d01e
+size 4962063400

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6413fedb9ef665f082890c84d80d16e78877add6347c13f5bec1405f320c3830
+size 4991441304

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ffe38176b97b0a6b8fb66b73ca57cd3716b732cab6bd8bd75630e3decdff2d
+size 4857206904

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34571c912d77cad5637f1423382f695484625b9bf841b8a325aabdbc03126b5
+size 4857206888

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 19667894272}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "lm_head.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors"}}

modeling_customllama.py

@@ -0,0 +1,49 @@
+from transformers.models.llama.modeling_llama import LlamaModel, LlamaDecoderLayer
+from transformers import LlamaConfig, LlamaForCausalLM
+import torch.nn as nn
+
+from .configuration_customllama import CustomLlamaConfig
+
+
+class CustomLlamaDecoderLayer(LlamaDecoderLayer):
+    def __init__(self, config, layer_idx, scale=1.0):
+        super().__init__(config, layer_idx)
+        self.scale = scale
+
+    def forward(self, hidden_states, attention_mask=None, position_ids=None, past_key_value=None, output_attentions=False, use_cache=True, cache_position=None, position_embeddings=None, **kwargs):
+        outputs = super().forward(
+            hidden_states,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_value=past_key_value,
+            output_attentions=output_attentions,
+            use_cache=use_cache,
+            cache_position=cache_position,
+            position_embeddings=position_embeddings
+        )
+
+        hidden_states = outputs[0]
+        hidden_states = hidden_states * self.scale
+        return (hidden_states, *outputs[1:])
+
+
+class CustomLlama(LlamaModel):
+    config_class = CustomLlamaConfig
+    def __init__(self, config):
+        super().__init__(config)
+        self.scales = config.scales
+        assert len(self.scales) == config.num_hidden_layers
+
+        self.layers = nn.ModuleList([
+            CustomLlamaDecoderLayer(config, layer_idx=i,scale=self.scales[i]) for i in range(config.num_hidden_layers)
+        ])
+
+    def forward(self, *args, **kwargs):
+        return super().forward(*args, **kwargs)
+
+
+class CustomLlamaForCausalLM(LlamaForCausalLM):
+    config_class = CustomLlamaConfig
+    def __init__(self, config):
+        super().__init__(config)
+        self.model = CustomLlama(config)

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}