Upload folder using huggingface_hub

README.md

@@ -0,0 +1,94 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: phi-2-sft-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# phi-2-sft-out
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2813
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| No log        | 0.0   | 1     | 1.7973          |
+| 1.9767        | 0.25  | 5290  | 1.4832          |
+| 1.8474        | 0.5   | 10580 | 1.4356          |
+| 1.8121        | 0.75  | 15870 | 1.4022          |
+| 1.8333        | 1.0   | 21160 | 1.3678          |
+| 1.6601        | 1.25  | 26450 | 1.3508          |
+| 1.5452        | 1.5   | 31740 | 1.3357          |
+| 1.7381        | 1.75  | 37030 | 1.3191          |
+| 1.6256        | 2.0   | 42320 | 1.3090          |
+| 1.5521        | 2.25  | 47610 | 1.2961          |
+| 1.8318        | 2.5   | 52900 | 1.2910          |
+| 1.6761        | 2.75  | 58190 | 1.2901          |
+| 1.6312        | 3.0   | 63480 | 1.2879          |
+| 1.7003        | 3.25  | 68770 | 1.2820          |
+| 1.6915        | 3.5   | 74060 | 1.2814          |
+| 1.5757        | 3.75  | 79350 | 1.2813          |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

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 +1,32 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "flash_attn": false,
+  "flash_rotary": false,
+  "fused_dense": false,
+  "img_processor": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "phi-msft",
+  "n_embd": 2560,
+  "n_head": 32,
+  "n_head_kv": null,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "resid_pdrop": 0.1,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.0.dev0",
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8991707e9880bc2a9594f717283bb8763bbbcd94e571129dc4dd276420b04b1
+size 4982467864

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79e43aac44fa64b04b2450e859478207486287bf83e6165eee1ed94c1138565
+size 576934128

model.safetensors.index.json

@@ -0,0 +1,332 @@
+{
+  "metadata": {
+    "total_size": 5559367680
+  },
+  "weight_map": {
+    "lm_head.linear.bias": "model-00002-of-00002.safetensors",
+    "lm_head.linear.weight": "model-00002-of-00002.safetensors",
+    "lm_head.ln.bias": "model-00002-of-00002.safetensors",
+    "lm_head.ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.30.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.30.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.30.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,323 @@
+{
+  "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|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}