gpt-neo-2.7B-cs-finetuning-7-60000

README.md

@@ -0,0 +1,59 @@
+---
+license: mit
+base_model: EleutherAI/gpt-neo-2.7B
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt-neo-2.7B-cs-finetuning-7-60000
+  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. -->
+
+# gpt-neo-2.7B-cs-finetuning-7-60000
+
+This model is a fine-tuned version of [EleutherAI/gpt-neo-2.7B](https://huggingface.co/EleutherAI/gpt-neo-2.7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4477
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.5787        | 1.0   | 765  | 2.4157          |
+| 1.8828        | 2.0   | 1530 | 2.3721          |
+| 1.4804        | 3.0   | 2295 | 2.4477          |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.1
+- Datasets 2.12.0
+- Tokenizers 0.15.1

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926eeed167f815255d3c43a93629e5b8c55232e288e46b9ba896709ef8c92fa7
+size 4993525968

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e523dfea6031e39fc6b387c42fba4c23cc2682e7cfef2a85d67750d0c7329ca0
+size 4982397200

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9414aadc1e08ad32abbd0c25eedadc39bc42a96a2ee359233f7f680741817a8a
+size 629353256

model.safetensors.index.json

@@ -0,0 +1,427 @@
+{
+  "metadata": {
+    "total_size": 10605230080
+  },
+  "weight_map": {
+    "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.14.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.29.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.29.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.30.attn.attention.k_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.attention.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.attention.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.attention.q_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.attention.v_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.30.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.30.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.attention.k_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.attention.out_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.attention.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.attention.q_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.attention.v_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
+    "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00003.safetensors",
+    "transformer.wte.weight": "model-00001-of-00003.safetensors"
+  }
+}