Upload folder using huggingface_hub

README.md

@@ -0,0 +1,93 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+base_model:
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+- abacaj/phi-2-super
+---
+
+# phi-2-DLEC
+
+phi-2-DLEC is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+
+## 🧩 Configuration
+
+```yaml
+dtype: bfloat16
+merge_method: passthrough
+slices:
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [0, 3] # Introduces 0, 3
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [3, 8] # Duplicates 3, introduces 4, 7, 8
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [7, 12] # Duplicates 7, 8, introduces 11, 12
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [11, 16] # Duplicates 11, 12, introduces 15, 16
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [15, 20] # Duplicates 15, 16, introduces 19, 20
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [19, 24] # Duplicates 19, 20, introduces 23, 24
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [23, 28] # Duplicates 23, 24, introduces 27, 28
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [27, 32] # Duplicates 27, 28, introduces 31, 32
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "TheSkullery/phi-2-DLEC"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "abacaj/phi-2-super",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 38,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

mergekit_config.yml

@@ -0,0 +1,29 @@
+
+dtype: bfloat16
+merge_method: passthrough
+slices:
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [0, 3] # Introduces 0, 3
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [3, 8] # Duplicates 3, introduces 4, 7, 8
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [7, 12] # Duplicates 7, 8, introduces 11, 12
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [11, 16] # Duplicates 11, 12, introduces 15, 16
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [15, 20] # Duplicates 15, 16, introduces 19, 20
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [19, 24] # Duplicates 19, 20, introduces 23, 24
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [23, 28] # Duplicates 23, 24, introduces 27, 28
+  - sources:
+      - model: abacaj/phi-2-super
+        layer_range: [27, 32] # Duplicates 27, 28, introduces 31, 32
+

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a451418aadf855b0b5b4025148425e858cf5a4963675d434cccb69a812dd6ba
+size 1953672680

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455f9a56c8af2210c2c765db90d0c6ce50a599f774bf3bf18a4206b3a96a2a3c
+size 1993046568

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467cf479fc018cf11d61defc212be931b88706cdedf0ba45381c1100efbf0283
+size 1992941400

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e572e36272f4332358e5792b29f18206694b6f7aed95072349510ed598204d73
+size 563822568

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.36.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.35.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.35.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.35.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.35.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.35.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.34.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.34.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.34.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.34.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.34.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.33.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.32.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.33.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.32.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.33.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.32.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.33.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.32.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.33.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.32.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.31.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.31.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.31.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.31.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.31.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.30.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.30.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.30.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.30.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.30.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.29.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.29.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.29.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.29.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.29.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.28.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.27.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.28.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.27.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors", "model.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.dense.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.dense.bias": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.bias": "model-00001-of-00004.safetensors", "model.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.22.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.23.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.22.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.22.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.21.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.21.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.20.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.20.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.19.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.19.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.18.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.17.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.18.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.17.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.16.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.16.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.15.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.15.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.14.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.14.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.13.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.12.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.13.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.12.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.11.mlp.fc2.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.fc2.bias": "model-00002-of-00004.safetensors", "model.layers.11.mlp.fc1.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.fc1.bias": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.dense.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.dense.bias": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors", "model.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors", "model.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.dense.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.dense.bias": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.bias": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00003-of-00004.safetensors", "model.final_layernorm.weight": "model-00003-of-00004.safetensors", "model.final_layernorm.bias": "model-00003-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors", "lm_head.bias": "model-00004-of-00004.safetensors", "model.layers.37.mlp.fc2.weight": "model-00004-of-00004.safetensors", "model.layers.37.mlp.fc2.bias": "model-00004-of-00004.safetensors", "model.layers.37.mlp.fc1.weight": "model-00004-of-00004.safetensors", "model.layers.37.mlp.fc1.bias": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.dense.weight": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.dense.bias": "model-00004-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.37.input_layernorm.bias": "model-00004-of-00004.safetensors", "model.layers.36.mlp.fc2.weight": "model-00004-of-00004.safetensors", "model.layers.36.mlp.fc2.bias": "model-00004-of-00004.safetensors", "model.layers.36.mlp.fc1.weight": "model-00004-of-00004.safetensors", "model.layers.36.mlp.fc1.bias": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.dense.weight": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.dense.bias": "model-00004-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.36.input_layernorm.bias": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}