Upload model

README.md

@@ -0,0 +1,135 @@
+---
+license: apache-2.0
+base_model: PygmalionAI/metharme-1.3b
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: PygmalionAI/metharme-1.3b
+model_type: StableLmForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: hieunguyenminh/roleplay
+    type: "completion"
+dataset_prepared_path: 
+val_set_size: 0.00
+output_dir: ./outputs/out
+
+sequence_len: 250
+sample_packing: true
+pad_to_sequence_len: true
+save_safetensors: true
+gpu_memory_limit: 80GiB
+
+adapter:
+lora_model_dir:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_linear:
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00005
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+flash_attn_cross_entropy: false
+flash_attn_rms_norm: true
+flash_attn_fuse_qkv: false
+flash_attn_fuse_mlp: true
+
+warmup_steps: 20
+evals_per_epoch: 4
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed: #deepspeed_configs/zero2.json # multi-gpu only
+weight_decay: 0.00
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# outputs/out
+
+This model is a fine-tuned version of [PygmalionAI/metharme-1.3b](https://huggingface.co/PygmalionAI/metharme-1.3b) 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "PygmalionAI/metharme-1.3b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 0,
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca95389073513581cb759b115ec097dc23df6232f0f5f1767a68b799a1670bf2
+size 2829330208

model.safetensors.index.json

@@ -0,0 +1 @@
+{"weight_map": {"pytorch_model-00001-of-340.safetensors": ["model.embed_tokens.weight", "model.layers.0.self_attn.q_proj.weight", "model.layers.0.self_attn.q_proj.bias", "model.layers.0.self_attn.k_proj.weight", "model.layers.0.self_attn.k_proj.bias", "model.layers.0.self_attn.v_proj.weight", "model.layers.0.self_attn.v_proj.bias", "model.layers.0.self_attn.o_proj.weight", "model.layers.0.mlp.gate_proj.weight", "model.layers.0.mlp.up_proj.weight", "model.layers.0.mlp.down_proj.weight", "model.layers.0.input_layernorm.weight", "model.layers.0.input_layernorm.bias", "model.layers.0.post_attention_layernorm.weight", "model.layers.0.post_attention_layernorm.bias", "model.layers.1.self_attn.q_proj.weight", "model.layers.1.self_attn.q_proj.bias", "model.layers.1.self_attn.k_proj.weight", "model.layers.1.self_attn.k_proj.bias", "model.layers.1.self_attn.v_proj.weight", "model.layers.1.self_attn.v_proj.bias", "model.layers.1.self_attn.o_proj.weight", "model.layers.1.mlp.gate_proj.weight", "model.layers.1.mlp.up_proj.weight", "model.layers.1.mlp.down_proj.weight", "model.layers.1.input_layernorm.weight", "model.layers.1.input_layernorm.bias", "model.layers.1.post_attention_layernorm.weight", "model.layers.1.post_attention_layernorm.bias", "model.layers.2.self_attn.q_proj.weight", "model.layers.2.self_attn.q_proj.bias", "model.layers.2.self_attn.k_proj.weight", "model.layers.2.self_attn.k_proj.bias", "model.layers.2.self_attn.v_proj.weight", "model.layers.2.self_attn.v_proj.bias", "model.layers.2.self_attn.o_proj.weight", "model.layers.2.mlp.gate_proj.weight", "model.layers.2.mlp.up_proj.weight", "model.layers.2.mlp.down_proj.weight", "model.layers.2.input_layernorm.weight", "model.layers.2.input_layernorm.bias", "model.layers.2.post_attention_layernorm.weight", "model.layers.2.post_attention_layernorm.bias", "model.layers.3.self_attn.q_proj.weight", "model.layers.3.self_attn.q_proj.bias", "model.layers.3.self_attn.k_proj.weight", "model.layers.3.self_attn.k_proj.bias", "model.layers.3.self_attn.v_proj.weight", "model.layers.3.self_attn.v_proj.bias", "model.layers.3.self_attn.o_proj.weight", "model.layers.3.mlp.gate_proj.weight", "model.layers.3.mlp.up_proj.weight", "model.layers.3.mlp.down_proj.weight", "model.layers.3.input_layernorm.weight", "model.layers.3.input_layernorm.bias", "model.layers.3.post_attention_layernorm.weight", "model.layers.3.post_attention_layernorm.bias", "model.layers.4.self_attn.q_proj.weight", "model.layers.4.self_attn.q_proj.bias", "model.layers.4.self_attn.k_proj.weight", "model.layers.4.self_attn.k_proj.bias", "model.layers.4.self_attn.v_proj.weight", "model.layers.4.self_attn.v_proj.bias", "model.layers.4.self_attn.o_proj.weight", "model.layers.4.mlp.gate_proj.weight", "model.layers.4.mlp.up_proj.weight", "model.layers.4.mlp.down_proj.weight", "model.layers.4.input_layernorm.weight", "model.layers.4.input_layernorm.bias", "model.layers.4.post_attention_layernorm.weight", "model.layers.4.post_attention_layernorm.bias", "model.layers.5.self_attn.q_proj.weight", "model.layers.5.self_attn.q_proj.bias", "model.layers.5.self_attn.k_proj.weight", "model.layers.5.self_attn.k_proj.bias", "model.layers.5.self_attn.v_proj.weight", "model.layers.5.self_attn.v_proj.bias", "model.layers.5.self_attn.o_proj.weight", "model.layers.5.mlp.gate_proj.weight", "model.layers.5.mlp.up_proj.weight", "model.layers.5.mlp.down_proj.weight", "model.layers.5.input_layernorm.weight", "model.layers.5.input_layernorm.bias", "model.layers.5.post_attention_layernorm.weight", "model.layers.5.post_attention_layernorm.bias", "model.layers.6.self_attn.q_proj.weight", "model.layers.6.self_attn.q_proj.bias", "model.layers.6.self_attn.k_proj.weight", "model.layers.6.self_attn.k_proj.bias", "model.layers.6.self_attn.v_proj.weight", "model.layers.6.self_attn.v_proj.bias", "model.layers.6.self_attn.o_proj.weight", "model.layers.6.mlp.gate_proj.weight", "model.layers.6.mlp.up_proj.weight", "model.layers.6.mlp.down_proj.weight", "model.layers.6.input_layernorm.weight", "model.layers.6.input_layernorm.bias", "model.layers.6.post_attention_layernorm.weight", "model.layers.6.post_attention_layernorm.bias", "model.layers.7.self_attn.q_proj.weight", "model.layers.7.self_attn.q_proj.bias", "model.layers.7.self_attn.k_proj.weight", "model.layers.7.self_attn.k_proj.bias", "model.layers.7.self_attn.v_proj.weight", "model.layers.7.self_attn.v_proj.bias", "model.layers.7.self_attn.o_proj.weight", "model.layers.7.mlp.gate_proj.weight", "model.layers.7.mlp.up_proj.weight", "model.layers.7.mlp.down_proj.weight", "model.layers.7.input_layernorm.weight", "model.layers.7.input_layernorm.bias", "model.layers.7.post_attention_layernorm.weight", "model.layers.7.post_attention_layernorm.bias", "model.layers.8.self_attn.q_proj.weight", "model.layers.8.self_attn.q_proj.bias", "model.layers.8.self_attn.k_proj.weight", "model.layers.8.self_attn.k_proj.bias", "model.layers.8.self_attn.v_proj.weight", "model.layers.8.self_attn.v_proj.bias", "model.layers.8.self_attn.o_proj.weight", "model.layers.8.mlp.gate_proj.weight", "model.layers.8.mlp.up_proj.weight", "model.layers.8.mlp.down_proj.weight", "model.layers.8.input_layernorm.weight", "model.layers.8.input_layernorm.bias", "model.layers.8.post_attention_layernorm.weight", "model.layers.8.post_attention_layernorm.bias", "model.layers.9.self_attn.q_proj.weight", "model.layers.9.self_attn.q_proj.bias", "model.layers.9.self_attn.k_proj.weight", "model.layers.9.self_attn.k_proj.bias", "model.layers.9.self_attn.v_proj.weight", "model.layers.9.self_attn.v_proj.bias", "model.layers.9.self_attn.o_proj.weight", "model.layers.9.mlp.gate_proj.weight", "model.layers.9.mlp.up_proj.weight", "model.layers.9.mlp.down_proj.weight", "model.layers.9.input_layernorm.weight", "model.layers.9.input_layernorm.bias", "model.layers.9.post_attention_layernorm.weight", "model.layers.9.post_attention_layernorm.bias", "model.layers.10.self_attn.q_proj.weight", "model.layers.10.self_attn.q_proj.bias", "model.layers.10.self_attn.k_proj.weight", "model.layers.10.self_attn.k_proj.bias", "model.layers.10.self_attn.v_proj.weight", "model.layers.10.self_attn.v_proj.bias", "model.layers.10.self_attn.o_proj.weight", "model.layers.10.mlp.gate_proj.weight", "model.layers.10.mlp.up_proj.weight", "model.layers.10.mlp.down_proj.weight", "model.layers.10.input_layernorm.weight", "model.layers.10.input_layernorm.bias", "model.layers.10.post_attention_layernorm.weight", "model.layers.10.post_attention_layernorm.bias", "model.layers.11.self_attn.q_proj.weight", "model.layers.11.self_attn.q_proj.bias", "model.layers.11.self_attn.k_proj.weight", "model.layers.11.self_attn.k_proj.bias", "model.layers.11.self_attn.v_proj.weight", "model.layers.11.self_attn.v_proj.bias", "model.layers.11.self_attn.o_proj.weight", "model.layers.11.mlp.gate_proj.weight", "model.layers.11.mlp.up_proj.weight", "model.layers.11.mlp.down_proj.weight", "model.layers.11.input_layernorm.weight", "model.layers.11.input_layernorm.bias", "model.layers.11.post_attention_layernorm.weight", "model.layers.11.post_attention_layernorm.bias", "model.layers.12.self_attn.q_proj.weight", "model.layers.12.self_attn.q_proj.bias", "model.layers.12.self_attn.k_proj.weight", "model.layers.12.self_attn.k_proj.bias", "model.layers.12.self_attn.v_proj.weight", "model.layers.12.self_attn.v_proj.bias", "model.layers.12.self_attn.o_proj.weight", "model.layers.12.mlp.gate_proj.weight", "model.layers.12.mlp.up_proj.weight", "model.layers.12.mlp.down_proj.weight", "model.layers.12.input_layernorm.weight", "model.layers.12.input_layernorm.bias", "model.layers.12.post_attention_layernorm.weight", "model.layers.12.post_attention_layernorm.bias", "model.layers.13.self_attn.q_proj.weight", "model.layers.13.self_attn.q_proj.bias", "model.layers.13.self_attn.k_proj.weight", "model.layers.13.self_attn.k_proj.bias", "model.layers.13.self_attn.v_proj.weight", "model.layers.13.self_attn.v_proj.bias", "model.layers.13.self_attn.o_proj.weight", "model.layers.13.mlp.gate_proj.weight", "model.layers.13.mlp.up_proj.weight", "model.layers.13.mlp.down_proj.weight", "model.layers.13.input_layernorm.weight", "model.layers.13.input_layernorm.bias", "model.layers.13.post_attention_layernorm.weight", "model.layers.13.post_attention_layernorm.bias", "model.layers.14.self_attn.q_proj.weight", "model.layers.14.self_attn.q_proj.bias", "model.layers.14.self_attn.k_proj.weight", "model.layers.14.self_attn.k_proj.bias", "model.layers.14.self_attn.v_proj.weight", "model.layers.14.self_attn.v_proj.bias", "model.layers.14.self_attn.o_proj.weight", "model.layers.14.mlp.gate_proj.weight", "model.layers.14.mlp.up_proj.weight", "model.layers.14.mlp.down_proj.weight", "model.layers.14.input_layernorm.weight", "model.layers.14.input_layernorm.bias", "model.layers.14.post_attention_layernorm.weight", "model.layers.14.post_attention_layernorm.bias", "model.layers.15.self_attn.q_proj.weight", "model.layers.15.self_attn.q_proj.bias", "model.layers.15.self_attn.k_proj.weight", "model.layers.15.self_attn.k_proj.bias", "model.layers.15.self_attn.v_proj.weight", "model.layers.15.self_attn.v_proj.bias", "model.layers.15.self_attn.o_proj.weight", "model.layers.15.mlp.gate_proj.weight", "model.layers.15.mlp.up_proj.weight", "model.layers.15.mlp.down_proj.weight", "model.layers.15.input_layernorm.weight", "model.layers.15.input_layernorm.bias", "model.layers.15.post_attention_layernorm.weight", "model.layers.15.post_attention_layernorm.bias", "model.layers.16.self_attn.q_proj.weight", "model.layers.16.self_attn.q_proj.bias", "model.layers.16.self_attn.k_proj.weight", "model.layers.16.self_attn.k_proj.bias", "model.layers.16.self_attn.v_proj.weight", "model.layers.16.self_attn.v_proj.bias", "model.layers.16.self_attn.o_proj.weight", "model.layers.16.mlp.gate_proj.weight", "model.layers.16.mlp.up_proj.weight", "model.layers.16.mlp.down_proj.weight", "model.layers.16.input_layernorm.weight", "model.layers.16.input_layernorm.bias", "model.layers.16.post_attention_layernorm.weight", "model.layers.16.post_attention_layernorm.bias", "model.layers.17.self_attn.q_proj.weight", "model.layers.17.self_attn.q_proj.bias", "model.layers.17.self_attn.k_proj.weight", "model.layers.17.self_attn.k_proj.bias", "model.layers.17.self_attn.v_proj.weight", "model.layers.17.self_attn.v_proj.bias", "model.layers.17.self_attn.o_proj.weight", "model.layers.17.mlp.gate_proj.weight", "model.layers.17.mlp.up_proj.weight", "model.layers.17.mlp.down_proj.weight", "model.layers.17.input_layernorm.weight", "model.layers.17.input_layernorm.bias", "model.layers.17.post_attention_layernorm.weight", "model.layers.17.post_attention_layernorm.bias", "model.layers.18.self_attn.q_proj.weight", "model.layers.18.self_attn.q_proj.bias", "model.layers.18.self_attn.k_proj.weight", "model.layers.18.self_attn.k_proj.bias", "model.layers.18.self_attn.v_proj.weight", "model.layers.18.self_attn.v_proj.bias", "model.layers.18.self_attn.o_proj.weight", "model.layers.18.mlp.gate_proj.weight", "model.layers.18.mlp.up_proj.weight", "model.layers.18.mlp.down_proj.weight", "model.layers.18.input_layernorm.weight", "model.layers.18.input_layernorm.bias", "model.layers.18.post_attention_layernorm.weight", "model.layers.18.post_attention_layernorm.bias", "model.layers.19.self_attn.q_proj.weight", "model.layers.19.self_attn.q_proj.bias", "model.layers.19.self_attn.k_proj.weight", "model.layers.19.self_attn.k_proj.bias", "model.layers.19.self_attn.v_proj.weight", "model.layers.19.self_attn.v_proj.bias", "model.layers.19.self_attn.o_proj.weight", "model.layers.19.mlp.gate_proj.weight", "model.layers.19.mlp.up_proj.weight", "model.layers.19.mlp.down_proj.weight", "model.layers.19.input_layernorm.weight", "model.layers.19.input_layernorm.bias", "model.layers.19.post_attention_layernorm.weight", "model.layers.19.post_attention_layernorm.bias", "model.layers.20.self_attn.q_proj.weight", "model.layers.20.self_attn.q_proj.bias", "model.layers.20.self_attn.k_proj.weight", "model.layers.20.self_attn.k_proj.bias", "model.layers.20.self_attn.v_proj.weight", "model.layers.20.self_attn.v_proj.bias", "model.layers.20.self_attn.o_proj.weight", "model.layers.20.mlp.gate_proj.weight", "model.layers.20.mlp.up_proj.weight", "model.layers.20.mlp.down_proj.weight", "model.layers.20.input_layernorm.weight", "model.layers.20.input_layernorm.bias", "model.layers.20.post_attention_layernorm.weight", "model.layers.20.post_attention_layernorm.bias", "model.layers.21.self_attn.q_proj.weight", "model.layers.21.self_attn.q_proj.bias", "model.layers.21.self_attn.k_proj.weight", "model.layers.21.self_attn.k_proj.bias", "model.layers.21.self_attn.v_proj.weight", "model.layers.21.self_attn.v_proj.bias", "model.layers.21.self_attn.o_proj.weight", "model.layers.21.mlp.gate_proj.weight", "model.layers.21.mlp.up_proj.weight", "model.layers.21.mlp.down_proj.weight", "model.layers.21.input_layernorm.weight", "model.layers.21.input_layernorm.bias", "model.layers.21.post_attention_layernorm.weight", "model.layers.21.post_attention_layernorm.bias", "model.layers.22.self_attn.q_proj.weight", "model.layers.22.self_attn.q_proj.bias", "model.layers.22.self_attn.k_proj.weight", "model.layers.22.self_attn.k_proj.bias", "model.layers.22.self_attn.v_proj.weight", "model.layers.22.self_attn.v_proj.bias", "model.layers.22.self_attn.o_proj.weight", "model.layers.22.mlp.gate_proj.weight", "model.layers.22.mlp.up_proj.weight", "model.layers.22.mlp.down_proj.weight", "model.layers.22.input_layernorm.weight", "model.layers.22.input_layernorm.bias", "model.layers.22.post_attention_layernorm.weight", "model.layers.22.post_attention_layernorm.bias", "model.layers.23.self_attn.q_proj.weight", "model.layers.23.self_attn.q_proj.bias", "model.layers.23.self_attn.k_proj.weight", "model.layers.23.self_attn.k_proj.bias", "model.layers.23.self_attn.v_proj.weight", "model.layers.23.self_attn.v_proj.bias", "model.layers.23.self_attn.o_proj.weight", "model.layers.23.mlp.gate_proj.weight", "model.layers.23.mlp.up_proj.weight", "model.layers.23.mlp.down_proj.weight", "model.layers.23.input_layernorm.weight", "model.layers.23.input_layernorm.bias", "model.layers.23.post_attention_layernorm.weight", "model.layers.23.post_attention_layernorm.bias", "model.norm.weight", "model.norm.bias", "lm_head.weight"]}, "metadata": {"total_size": 3289030656}}

special_tokens_map.json

@@ -0,0 +1,53 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|system|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false
+    },
+    {
+      "content": "<|user|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false
+    },
+    {
+      "content": "<|model|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "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 +1,252 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "<|system|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "50278": {
+      "content": "<|user|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "50279": {
+      "content": "<|model|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|model|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}