Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 50257,
+  "<|im_start|>": 50258
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "cerebras/Cerebras-GPT-6.7B",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50257,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 4096,
+  "n_head": 32,
+  "n_inner": 16384,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 50272
+}

config/prox-cerebras-gpt-6.7b-v4.yml

@@ -0,0 +1,97 @@
+base_model: cerebras/Cerebras-GPT-6.7B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+is_llama_derived_model: false
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: /workspace/datasets/dolphin/flan150t-sharegpt.json
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/CapybaraPure_Decontaminated_ShareGPT_cleaned.json
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/open_platypus-sharegpt.json
+    type: sharegpt
+    conversation: chatml
+  - path: teknium/openhermes
+    type: alpaca
+    prompt_style: chatml
+  - path: /workspace/datasets/prox/prox_alpaca.jsonl
+    type: alpaca
+    prompt_style: chatml
+
+dataset_prepared_path: larp
+val_set_size: 0.05
+output_dir: /workspace/prox-1.0-gpt-6b/
+
+sequence_len: 2048
+sample_packing: true  
+pad_to_sequence_len: true
+
+adapter: qlora
+lora_model_dir:
+lora_r: 64
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_modules:
+  - c_fc
+  - c_attn
+  - c_proj
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_modules_to_save:
+  - embed_tokens
+  - lm_head
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 16
+micro_batch_size: 1
+num_epochs: 4
+optimizer: paged_adamw_8bit
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 0.00001
+max_grad_norm: 1000.0
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length:
+bf16: true
+fp16: false
+tf32: true
+
+gradient_checkpointing:
+early_stopping_patience:
+resume_from_checkpoint: 
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 5
+evals_per_epoch: 0
+save_steps: 0.01
+save_safetensors: false
+save_total_limit: 2
+debug:
+deepspeed: deepspeed/zero2.json
+weight_decay: 0.01
+fsdp:
+fsdp_config:
+resize_token_embeddings_to_32x: true
+special_tokens:
+  eos_token: "<|im_end|>"
+  pad_token: "<|endoftext|>"
+tokens:
+  - "<|im_start|>"

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.0.dev0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9432df29181c6b360a56aeda4d74f5caca204868b3d66fa2f54f8055311af9
+size 4993291677

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee3745ccd30fd306b5dffc40babb018bde3b53e21bd021bb0b0774575337ac9
+size 4967414597

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b608335f63b7c3f251af14e6ca5c61632f441991f3e7dd0b76a55a36674cc4
+size 3768180778

pytorch_model.bin.index.json

@@ -0,0 +1,396 @@
+{
+  "metadata": {
+    "total_size": 13728759808
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}