jais-13b-arabic-text-summarizer

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: core42/jais-13b
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: tmp_trainer
+  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. -->
+
+# tmp_trainer
+
+This model is a fine-tuned version of [core42/jais-13b](https://huggingface.co/core42/jais-13b) on the None dataset.
+
+## 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: 5e-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
+
+
+
+### Framework versions
+
+- Transformers 4.39.0
+- Pytorch 2.2.0
+- Datasets 2.20.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "core42/jais-13b",
+  "activation_function": "swiglu",
+  "architectures": [
+    "JAISLMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "core42/jais-13b--configuration_jais.JAISConfig",
+    "AutoModel": "core42/jais-13b--modeling_jais.JAISModel",
+    "AutoModelForCausalLM": "core42/jais-13b--modeling_jais.JAISLMHeadModel",
+    "AutoModelForQuestionAnswering": "core42/jais-13b--modeling_jais.JAISForQuestionAnswering",
+    "AutoModelForSequenceClassification": "core42/jais-13b--modeling_jais.JAISForSequenceClassification",
+    "AutoModelForTokenClassification": "core42/jais-13b--modeling_jais.JAISForTokenClassification"
+  },
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "embeddings_scale": 14.6,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "jais",
+  "n_embd": 5120,
+  "n_head": 40,
+  "n_inner": 13653,
+  "n_layer": 40,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "position_embedding_type": "alibi",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "scale_qk_dot_by_d": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0",
+  "use_cache": true,
+  "vocab_size": 84992,
+  "width_scale": 0.11100000000000002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40b7152a07b7b3e730831dd6765f4035c47077455ab4f1e02fffd2b37cae6ee
+size 4995652090

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09655931e1d8f6736c3a83661dcca93448189a774db56747b3d6c3c6c67423f4
+size 4894434774

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd14ea1b41fe9257d992751495683a9b041c48da9b5609ca03f580f6b749cf6a
+size 4981809136

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d6582f07bfbce727e804c03f10769d8db4f2f3f156d4bcae83d8373e2e5853
+size 4876951720

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:259714bea5089ecaf67995910ad259bd03e4ace473bbb0ea570842bffdc14ba5
+size 4894431208

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321f701005d944c8b6be1f411f6fa88ee2df74056ed125ec4794e5359d73dd78
+size 1398405288

model.safetensors.index.json

@@ -0,0 +1,571 @@
+{
+  "metadata": {
+    "total_size": 26041623920
+  },
+  "weight_map": {
+    "transformer.h.0.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_fc2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_fc2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_fc2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_fc2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.10.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_fc2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_fc2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.11.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.11.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.mlp.c_fc2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.11.mlp.c_fc2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.12.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.12.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.12.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.12.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.12.mlp.c_fc2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.12.mlp.c_fc2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.13.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.13.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.13.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.13.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.13.mlp.c_fc2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.13.mlp.c_fc2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.14.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.14.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.14.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.14.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_fc2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_fc2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_fc2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_fc2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_fc2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_fc2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.17.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.17.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.mlp.c_fc2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.17.mlp.c_fc2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.18.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.18.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.18.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.18.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.18.mlp.c_fc2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.18.mlp.c_fc2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.19.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.19.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.19.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.19.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.19.mlp.c_fc2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.19.mlp.c_fc2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.2.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_fc2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_fc2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.20.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.20.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.20.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.20.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.20.mlp.c_fc2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.20.mlp.c_fc2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.21.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.21.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.21.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.21.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.21.mlp.c_fc2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.21.mlp.c_fc2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.22.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.22.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.22.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_fc2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_fc2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.23.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.23.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.mlp.c_fc2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.23.mlp.c_fc2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.24.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.24.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.24.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.24.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.24.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.24.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.24.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.24.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.24.mlp.c_fc2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.24.mlp.c_fc2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.24.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.24.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.25.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.25.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.25.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.25.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.25.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.25.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.25.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.25.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.25.mlp.c_fc2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.25.mlp.c_fc2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.25.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.25.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.26.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.26.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.26.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.26.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.26.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.26.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.26.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.26.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.26.mlp.c_fc2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.26.mlp.c_fc2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.26.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.26.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.27.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.27.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.27.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.27.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.27.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.27.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.27.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.27.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.27.mlp.c_fc2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.27.mlp.c_fc2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.27.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.27.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.28.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.28.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.28.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.28.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.28.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.28.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.28.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.28.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.28.mlp.c_fc2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.28.mlp.c_fc2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.28.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.28.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.29.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.29.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.29.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.29.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.29.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.29.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.29.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.29.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.29.mlp.c_fc2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.29.mlp.c_fc2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.29.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.29.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.3.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_fc2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_fc2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.30.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.30.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.30.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.30.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.30.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.30.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.30.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.30.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.30.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.30.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.30.mlp.c_fc2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.30.mlp.c_fc2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.30.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.30.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.31.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.31.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.31.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.31.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.31.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.31.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.31.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.31.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.31.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.31.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.31.mlp.c_fc2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.31.mlp.c_fc2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.31.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.31.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.32.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.32.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.32.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.32.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.32.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.32.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.32.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.32.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.32.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.32.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.32.mlp.c_fc2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.32.mlp.c_fc2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.32.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.32.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.33.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.33.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.33.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.33.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.33.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.33.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.33.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.33.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.33.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.33.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.33.mlp.c_fc2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.33.mlp.c_fc2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.33.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.33.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.34.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.34.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.34.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.34.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.34.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.34.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.34.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.34.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.34.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.34.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.34.mlp.c_fc2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.34.mlp.c_fc2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.34.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.34.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.35.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.35.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.35.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.35.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.35.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.35.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.35.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.35.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.35.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.35.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.35.mlp.c_fc2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.35.mlp.c_fc2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.35.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.35.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.36.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.36.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.36.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.36.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.36.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.36.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.36.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.36.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.36.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.36.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.36.mlp.c_fc2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.36.mlp.c_fc2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.36.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.36.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.37.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.37.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.37.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.37.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.37.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.37.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.37.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.37.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.37.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.37.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.37.mlp.c_fc2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.37.mlp.c_fc2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.37.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.37.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.38.attn.c_attn.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.38.attn.c_attn.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.38.attn.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.38.attn.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.38.ln_1.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.38.ln_1.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.38.ln_2.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.38.ln_2.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.38.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.38.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.38.mlp.c_fc2.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.38.mlp.c_fc2.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.38.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.38.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.39.attn.c_attn.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.39.attn.c_attn.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.39.attn.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.39.attn.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.39.ln_1.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.39.ln_1.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.39.ln_2.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.39.ln_2.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.39.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.39.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.39.mlp.c_fc2.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.39.mlp.c_fc2.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.39.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.39.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.4.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_fc2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_fc2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.5.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.5.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.mlp.c_fc2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.5.mlp.c_fc2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.6.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.6.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.6.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.6.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.6.mlp.c_fc2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.c_fc2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_fc2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_fc2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_fc2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_fc2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_fc2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_fc2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.ln_f.bias": "model-00006-of-00006.safetensors",
+    "transformer.ln_f.weight": "model-00006-of-00006.safetensors",
+    "transformer.relative_pe.slopes": "model-00006-of-00006.safetensors",
+    "transformer.wte.weight": "model-00001-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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 +1,18 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe57307bfab73f687004dcb7d81157d3c8b1fc061ffc6898a77c6d4f2a407c70
+size 5112