Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/mistral-7b-bnb-4bit
+library_name: peft
+model_name: mistral-chef-v2
+tags:
+- base_model:adapter:unsloth/mistral-7b-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for mistral-chef-v2
+
+This model is a fine-tuned version of [unsloth/mistral-7b-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.19.1
+- TRL: 0.23.0
+- Transformers: 4.57.2
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/mistral-7b-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466359270900c8fe15fa9500f9c0d038d49e5ccab59bb8c02ddcae10912d0f24
+size 167832240

checkpoint-375/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/mistral-7b-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/mistral-7b-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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]
+- **Funded by [optional]:** [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 Dataset 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 Dataset 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]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-375/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/mistral-7b-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466359270900c8fe15fa9500f9c0d038d49e5ccab59bb8c02ddcae10912d0f24
+size 167832240

checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048308bb02262274c989a4f1367d7caead53d280cf9abcd647e10f5f0309580c
+size 85728677

checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6d8fafcd1ee268414be5acf0366296af5b03d60871978712eac1979cb42d65
+size 14645

checkpoint-375/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac58ef7454dc327cdd1497d560e3c1cadc5881183c106e69fda6701af10248e8
+size 1383

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f65deb4559fff2991071b84be83ca06cd954d4b603e0a7bd2a48a5a6ba559f
+size 1465

checkpoint-375/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-375/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-375/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-375/trainer_state.json

@@ -0,0 +1,317 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.1666679382324219,
+      "learning_rate": 0.000135,
+      "loss": 1.005,
+      "step": 10
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.39651840925216675,
+      "learning_rate": 0.0001463013698630137,
+      "loss": 0.5791,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4225136339664459,
+      "learning_rate": 0.0001421917808219178,
+      "loss": 0.5666,
+      "step": 30
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.3511693775653839,
+      "learning_rate": 0.0001380821917808219,
+      "loss": 0.5446,
+      "step": 40
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.41202008724212646,
+      "learning_rate": 0.00013397260273972602,
+      "loss": 0.4963,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5186659693717957,
+      "learning_rate": 0.00012986301369863012,
+      "loss": 0.4918,
+      "step": 60
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.4339252710342407,
+      "learning_rate": 0.00012575342465753425,
+      "loss": 0.4942,
+      "step": 70
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.35540297627449036,
+      "learning_rate": 0.00012164383561643835,
+      "loss": 0.459,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.31886568665504456,
+      "learning_rate": 0.00011753424657534245,
+      "loss": 0.478,
+      "step": 90
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.31149041652679443,
+      "learning_rate": 0.00011342465753424656,
+      "loss": 0.4621,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 0.4663235545158386,
+      "eval_runtime": 195.2394,
+      "eval_samples_per_second": 1.537,
+      "eval_steps_per_second": 0.768,
+      "step": 100
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.2757165729999542,
+      "learning_rate": 0.00010931506849315068,
+      "loss": 0.4807,
+      "step": 110
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2738674581050873,
+      "learning_rate": 0.00010520547945205479,
+      "loss": 0.4693,
+      "step": 120
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.2937587797641754,
+      "learning_rate": 0.00010109589041095889,
+      "loss": 0.4524,
+      "step": 130
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.2990877628326416,
+      "learning_rate": 9.698630136986301e-05,
+      "loss": 0.4566,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.31150081753730774,
+      "learning_rate": 9.287671232876712e-05,
+      "loss": 0.4588,
+      "step": 150
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.3070783317089081,
+      "learning_rate": 8.876712328767122e-05,
+      "loss": 0.4868,
+      "step": 160
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.31298378109931946,
+      "learning_rate": 8.465753424657534e-05,
+      "loss": 0.4802,
+      "step": 170
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.28346869349479675,
+      "learning_rate": 8.054794520547945e-05,
+      "loss": 0.4581,
+      "step": 180
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.27815142273902893,
+      "learning_rate": 7.643835616438355e-05,
+      "loss": 0.4427,
+      "step": 190
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.2744145691394806,
+      "learning_rate": 7.232876712328767e-05,
+      "loss": 0.4795,
+      "step": 200
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.4599311947822571,
+      "eval_runtime": 195.2951,
+      "eval_samples_per_second": 1.536,
+      "eval_steps_per_second": 0.768,
+      "step": 200
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.3007442355155945,
+      "learning_rate": 6.821917808219178e-05,
+      "loss": 0.4872,
+      "step": 210
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.2825697362422943,
+      "learning_rate": 6.41095890410959e-05,
+      "loss": 0.4594,
+      "step": 220
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.2875243127346039,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.4589,
+      "step": 230
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.28670668601989746,
+      "learning_rate": 5.589041095890411e-05,
+      "loss": 0.47,
+      "step": 240
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.31645962595939636,
+      "learning_rate": 5.1780821917808216e-05,
+      "loss": 0.4321,
+      "step": 250
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.2929031252861023,
+      "learning_rate": 4.767123287671233e-05,
+      "loss": 0.4538,
+      "step": 260
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.29874441027641296,
+      "learning_rate": 4.356164383561643e-05,
+      "loss": 0.4597,
+      "step": 270
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.24016378819942474,
+      "learning_rate": 3.945205479452054e-05,
+      "loss": 0.4651,
+      "step": 280
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.26898664236068726,
+      "learning_rate": 3.534246575342465e-05,
+      "loss": 0.4731,
+      "step": 290
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2705814838409424,
+      "learning_rate": 3.123287671232877e-05,
+      "loss": 0.4436,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.4546850621700287,
+      "eval_runtime": 195.2654,
+      "eval_samples_per_second": 1.536,
+      "eval_steps_per_second": 0.768,
+      "step": 300
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.23966531455516815,
+      "learning_rate": 2.7123287671232875e-05,
+      "loss": 0.456,
+      "step": 310
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.2486310750246048,
+      "learning_rate": 2.3013698630136985e-05,
+      "loss": 0.47,
+      "step": 320
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.26778164505958557,
+      "learning_rate": 1.8904109589041096e-05,
+      "loss": 0.4552,
+      "step": 330
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.23956233263015747,
+      "learning_rate": 1.4794520547945204e-05,
+      "loss": 0.4775,
+      "step": 340
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.2919732928276062,
+      "learning_rate": 1.0684931506849315e-05,
+      "loss": 0.4856,
+      "step": 350
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.26673752069473267,
+      "learning_rate": 6.5753424657534245e-06,
+      "loss": 0.4835,
+      "step": 360
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.22421975433826447,
+      "learning_rate": 2.4657534246575337e-06,
+      "loss": 0.4633,
+      "step": 370
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.661656762230374e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78d4b0198c689d37179f1e61eea61fc77e0b4f0de529e992071442a8d83fb2f
+size 6161

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}