Added LORA

alpha-prompt_v1/README.md

@@ -0,0 +1,202 @@
+---
+license: other
+base_model: Gryphe/MythoMax-L2-13b
+tags:
+- generated_from_trainer
+model-index:
+- name: lora-out-10
+  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)
+# lora-out-10
+
+This model is a fine-tuned version of [Gryphe/MythoMax-L2-13b](https://huggingface.co/Gryphe/MythoMax-L2-13b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3963
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 6
+- 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
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.9065        | 0.01  | 200   | 1.9889          |
+| 1.764         | 0.01  | 400   | 1.8015          |
+| 1.6177        | 0.02  | 600   | 1.6777          |
+| 1.5756        | 0.03  | 800   | 1.5862          |
+| 1.4847        | 0.03  | 1000  | 1.5134          |
+| 1.5603        | 0.04  | 1200  | 1.4480          |
+| 1.347         | 0.05  | 1400  | 1.3939          |
+| 1.2312        | 0.06  | 1600  | 1.3450          |
+| 1.3749        | 0.06  | 1800  | 1.3037          |
+| 1.2194        | 0.07  | 2000  | 1.2657          |
+| 1.2434        | 0.08  | 2200  | 1.2297          |
+| 1.2037        | 0.08  | 2400  | 1.1983          |
+| 1.2709        | 0.09  | 2600  | 1.1679          |
+| 1.1537        | 0.1   | 2800  | 1.1405          |
+| 1.1408        | 0.1   | 3000  | 1.1154          |
+| 1.0502        | 0.11  | 3200  | 1.0921          |
+| 1.0453        | 0.12  | 3400  | 1.0717          |
+| 0.9332        | 0.13  | 3600  | 1.0462          |
+| 1.1569        | 0.13  | 3800  | 1.0284          |
+| 1.146         | 0.14  | 4000  | 1.0092          |
+| 1.0325        | 0.15  | 4200  | 0.9916          |
+| 0.9936        | 0.15  | 4400  | 0.9748          |
+| 0.9131        | 0.16  | 4600  | 0.9592          |
+| 0.9426        | 0.17  | 4800  | 0.9416          |
+| 0.8971        | 0.17  | 5000  | 0.9278          |
+| 0.8258        | 0.18  | 5200  | 0.9124          |
+| 0.8038        | 0.19  | 5400  | 0.8991          |
+| 0.9663        | 0.2   | 5600  | 0.8841          |
+| 0.7214        | 0.2   | 5800  | 0.8726          |
+| 0.8789        | 0.21  | 6000  | 0.8621          |
+| 0.8095        | 0.22  | 6200  | 0.8492          |
+| 0.8446        | 0.22  | 6400  | 0.8379          |
+| 0.8704        | 0.23  | 6600  | 0.8261          |
+| 0.8175        | 0.24  | 6800  | 0.8165          |
+| 0.7169        | 0.24  | 7000  | 0.8066          |
+| 0.6899        | 0.25  | 7200  | 0.7952          |
+| 0.8256        | 0.26  | 7400  | 0.7860          |
+| 0.7186        | 0.27  | 7600  | 0.7759          |
+| 0.8891        | 0.27  | 7800  | 0.7664          |
+| 0.7919        | 0.28  | 8000  | 0.7580          |
+| 0.8378        | 0.29  | 8200  | 0.7487          |
+| 0.6804        | 0.29  | 8400  | 0.7390          |
+| 0.6921        | 0.3   | 8600  | 0.7308          |
+| 0.7263        | 0.31  | 8800  | 0.7221          |
+| 0.6268        | 0.31  | 9000  | 0.7145          |
+| 0.6954        | 0.32  | 9200  | 0.7067          |
+| 0.8179        | 0.33  | 9400  | 0.6992          |
+| 0.5709        | 0.34  | 9600  | 0.6929          |
+| 0.7092        | 0.34  | 9800  | 0.6858          |
+| 0.7396        | 0.35  | 10000 | 0.6774          |
+| 0.5967        | 0.36  | 10200 | 0.6702          |
+| 0.6984        | 0.36  | 10400 | 0.6636          |
+| 0.5621        | 0.37  | 10600 | 0.6578          |
+| 0.5342        | 0.38  | 10800 | 0.6512          |
+| 0.6695        | 0.38  | 11000 | 0.6442          |
+| 0.7242        | 0.39  | 11200 | 0.6374          |
+| 0.6046        | 0.4   | 11400 | 0.6317          |
+| 0.5994        | 0.41  | 11600 | 0.6260          |
+| 0.6133        | 0.41  | 11800 | 0.6201          |
+| 0.6707        | 0.42  | 12000 | 0.6138          |
+| 0.6454        | 0.43  | 12200 | 0.6078          |
+| 0.6534        | 0.43  | 12400 | 0.6013          |
+| 0.6382        | 0.44  | 12600 | 0.5963          |
+| 0.6659        | 0.45  | 12800 | 0.5908          |
+| 0.6608        | 0.45  | 13000 | 0.5851          |
+| 0.6864        | 0.46  | 13200 | 0.5793          |
+| 0.6046        | 0.47  | 13400 | 0.5748          |
+| 0.5331        | 0.48  | 13600 | 0.5692          |
+| 0.5314        | 0.48  | 13800 | 0.5640          |
+| 0.5528        | 0.49  | 14000 | 0.5594          |
+| 0.5617        | 0.5   | 14200 | 0.5545          |
+| 0.6572        | 0.5   | 14400 | 0.5488          |
+| 0.6108        | 0.51  | 14600 | 0.5441          |
+| 0.4776        | 0.52  | 14800 | 0.5387          |
+| 0.493         | 0.52  | 15000 | 0.5357          |
+| 0.5464        | 0.53  | 15200 | 0.5305          |
+| 0.5519        | 0.54  | 15400 | 0.5260          |
+| 0.4209        | 0.55  | 15600 | 0.5225          |
+| 0.4759        | 0.55  | 15800 | 0.5173          |
+| 0.5357        | 0.56  | 16000 | 0.5129          |
+| 0.6064        | 0.57  | 16200 | 0.5091          |
+| 0.4835        | 0.57  | 16400 | 0.5048          |
+| 0.4951        | 0.58  | 16600 | 0.5017          |
+| 0.3621        | 0.59  | 16800 | 0.4971          |
+| 0.5166        | 0.59  | 17000 | 0.4935          |
+| 0.5464        | 0.6   | 17200 | 0.4896          |
+| 0.5093        | 0.61  | 17400 | 0.4858          |
+| 0.443         | 0.62  | 17600 | 0.4828          |
+| 0.4323        | 0.62  | 17800 | 0.4787          |
+| 0.5066        | 0.63  | 18000 | 0.4754          |
+| 0.4388        | 0.64  | 18200 | 0.4717          |
+| 0.5436        | 0.64  | 18400 | 0.4682          |
+| 0.3881        | 0.65  | 18600 | 0.4649          |
+| 0.6051        | 0.66  | 18800 | 0.4623          |
+| 0.5628        | 0.66  | 19000 | 0.4589          |
+| 0.4372        | 0.67  | 19200 | 0.4560          |
+| 0.4748        | 0.68  | 19400 | 0.4529          |
+| 0.5461        | 0.69  | 19600 | 0.4499          |
+| 0.4313        | 0.69  | 19800 | 0.4471          |
+| 0.4353        | 0.7   | 20000 | 0.4445          |
+| 0.4988        | 0.71  | 20200 | 0.4419          |
+| 0.4037        | 0.71  | 20400 | 0.4394          |
+| 0.446         | 0.72  | 20600 | 0.4368          |
+| 0.4381        | 0.73  | 20800 | 0.4347          |
+| 0.4849        | 0.73  | 21000 | 0.4324          |
+| 0.4726        | 0.74  | 21200 | 0.4303          |
+| 0.4842        | 0.75  | 21400 | 0.4279          |
+| 0.3508        | 0.76  | 21600 | 0.4259          |
+| 0.4452        | 0.76  | 21800 | 0.4236          |
+| 0.3565        | 0.77  | 22000 | 0.4216          |
+| 0.4634        | 0.78  | 22200 | 0.4196          |
+| 0.3925        | 0.78  | 22400 | 0.4179          |
+| 0.4086        | 0.79  | 22600 | 0.4164          |
+| 0.4149        | 0.8   | 22800 | 0.4145          |
+| 0.3856        | 0.8   | 23000 | 0.4128          |
+| 0.4053        | 0.81  | 23200 | 0.4113          |
+| 0.47          | 0.82  | 23400 | 0.4099          |
+| 0.3918        | 0.83  | 23600 | 0.4086          |
+| 0.4021        | 0.83  | 23800 | 0.4074          |
+| 0.376         | 0.84  | 24000 | 0.4063          |
+| 0.5067        | 0.85  | 24200 | 0.4052          |
+| 0.4721        | 0.85  | 24400 | 0.4041          |
+| 0.4015        | 0.86  | 24600 | 0.4031          |
+| 0.3576        | 0.87  | 24800 | 0.4021          |
+| 0.3975        | 0.87  | 25000 | 0.4015          |
+| 0.3898        | 0.88  | 25200 | 0.4006          |
+| 0.4235        | 0.89  | 25400 | 0.4000          |
+| 0.3808        | 0.9   | 25600 | 0.3992          |
+| 0.3811        | 0.9   | 25800 | 0.3989          |
+| 0.4011        | 0.91  | 26000 | 0.3983          |
+| 0.4219        | 0.92  | 26200 | 0.3981          |
+| 0.3764        | 0.92  | 26400 | 0.3977          |
+| 0.4046        | 0.93  | 26600 | 0.3974          |
+| 0.4342        | 0.94  | 26800 | 0.3972          |
+| 0.4209        | 0.94  | 27000 | 0.3969          |
+| 0.4549        | 0.95  | 27200 | 0.3967          |
+| 0.3316        | 0.96  | 27400 | 0.3967          |
+| 0.4648        | 0.97  | 27600 | 0.3967          |
+| 0.4657        | 0.97  | 27800 | 0.3965          |
+| 0.3959        | 0.98  | 28000 | 0.3964          |
+| 0.3666        | 0.99  | 28200 | 0.3964          |
+| 0.3973        | 0.99  | 28400 | 0.3963          |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

alpha-prompt_v1/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Gryphe/MythoMax-L2-13b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

alpha-prompt_v1/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64287e70391f53c1ac015be3cebcdb343deaaf7d02ff984664b28245ad91b36
+size 500897546

alpha-prompt_v1/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 2,
+  "<pad>": 32000,
+  "<s>": 1,
+  "<unk>": 0
+}

alpha-prompt_v1/checkpoint-28576/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: Gryphe/MythoMax-L2-13b
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

alpha-prompt_v1/checkpoint-28576/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Gryphe/MythoMax-L2-13b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

alpha-prompt_v1/checkpoint-28576/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64287e70391f53c1ac015be3cebcdb343deaaf7d02ff984664b28245ad91b36
+size 500897546

alpha-prompt_v1/checkpoint-28576/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b27be11db4e3ac13ee4af3e9dd02643f47dc0bcf19ca2f03b23239628de206e7
+size 251485652

alpha-prompt_v1/checkpoint-28576/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15941810e1b0adf6d3aebb53ef32e5ebb64a0ad2703b71e3c29b6b957ced9cc4
+size 14244

alpha-prompt_v1/checkpoint-28576/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708a30ddbd1285185431577f79954f5206248c87a11265e9c6b2f9952241f3c6
+size 1064

alpha-prompt_v1/checkpoint-28576/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496f9a53e22cbc63d9098f12ae40f8ad01b500e86cb27ab06b05e6ad8ed461d8
+size 4920

alpha-prompt_v1/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Gryphe/MythoMax-L2-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

alpha-prompt_v1/runs/Oct16_18-49-32_babylon/events.out.tfevents.1697496580.babylon.1010856.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67809baa236b5a3633958b6877e7dba4fc9ded5a3c03085aedb8cb7788c2e958
+size 4958

alpha-prompt_v1/runs/Oct16_18-56-39_babylon/events.out.tfevents.1697497007.babylon.1012350.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07dc4ec6e69f7e543e4e22fd2adbb22575ab7d4a4d07d218161504731471814
+size 4958

alpha-prompt_v1/runs/Oct16_19-01-12_babylon/events.out.tfevents.1697497280.babylon.1013466.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0ec436ebddb55d6f957749ec859417efda37b3d9479d5108909609de268dfa
+size 4958

alpha-prompt_v1/runs/Oct16_19-04-08_babylon/events.out.tfevents.1697497455.babylon.1013704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8269e91289c771b8c63c9f6ce4b873cf161a1a427cd5a32b752d05499c056abc
+size 8037

alpha-prompt_v1/runs/Oct16_19-24-00_babylon/events.out.tfevents.1697498648.babylon.1015156.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38d03a1c22d90429672bfa163dc85f7fd04912a6a972264bdbc1958d47627e5f
+size 4566735

alpha-prompt_v1/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

alpha-prompt_v1/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

alpha-prompt_v1/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": null,
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}