Upload folder using huggingface_hub

README.md

@@ -0,0 +1,161 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: openlm-research/open_llama_3b
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 9ff0579b-21fe-4f82-b5c0-e24a3e64f4c1
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: openlm-research/open_llama_3b
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 3180d05155dcddb3_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/3180d05155dcddb3_train_data.json
+  type:
+    field_input: domain
+    field_instruction: generation
+    field_output: model
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_steps: 10
+eval_table_size: null
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 8
+gradient_checkpointing: true
+gradient_clipping: 1.0
+group_by_length: true
+hub_model_id: sn56a2/9ff0579b-21fe-4f82-b5c0-e24a3e64f4c1
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: cosine
+max_memory:
+  0: 74GiB
+max_steps: 20
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/3180d05155dcddb3_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 10
+save_strategy: steps
+sequence_len: 2048
+special_tokens:
+  pad_token: </s>
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: 9ff0579b-21fe-4f82-b5c0-e24a3e64f4c1
+wandb_project: god
+wandb_run: tuds
+wandb_runid: 9ff0579b-21fe-4f82-b5c0-e24a3e64f4c1
+warmup_ratio: 0.05
+weight_decay: 0.01
+xformers_attention: true
+
+```
+
+</details><br>
+
+# 9ff0579b-21fe-4f82-b5c0-e24a3e64f4c1
+
+This model is a fine-tuned version of [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4361
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- training_steps: 20
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 6.2462        | 0.0001 | 1    | 6.2362          |
+| 3.3295        | 0.0005 | 10   | 3.3748          |
+| 2.3704        | 0.0011 | 20   | 2.4361          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_3b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0dcef36655212f17ced74e66be8eccf0081261ef8129585257182d300651bfa
+size 203538938

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634304f7adbe8af78e0799920bfb19a4d13aa8af0a2a1dfbc0280a6693d56984
+size 203456160

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "openlm-research/open_llama_3b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 100,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openlm-research/open_llama_3b
+library_name: peft
+---
+
+# 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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_3b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634304f7adbe8af78e0799920bfb19a4d13aa8af0a2a1dfbc0280a6693d56984
+size 203456160

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18288e6622fa2c348b56506fee3b4dcddca704668bc3e4fe58879c6ff8b10a1b
+size 407121750

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206355fdfea165f0820bd1233fb7c4bd031a8b562e3a4e55f8d5a46a0061d589
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
+size 1064

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
+size 534194

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0010560289351928243,
+  "eval_steps": 10,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.2801446759641216e-05,
+      "grad_norm": 3.0317537784576416,
+      "learning_rate": 5e-05,
+      "loss": 6.2462,
+      "step": 1
+    },
+    {
+      "epoch": 5.2801446759641216e-05,
+      "eval_loss": 6.236235618591309,
+      "eval_runtime": 3669.8181,
+      "eval_samples_per_second": 4.346,
+      "eval_steps_per_second": 2.173,
+      "step": 1
+    },
+    {
+      "epoch": 0.00010560289351928243,
+      "grad_norm": 2.6571614742279053,
+      "learning_rate": 0.0001,
+      "loss": 5.5005,
+      "step": 2
+    },
+    {
+      "epoch": 0.00015840434027892365,
+      "grad_norm": 3.0436835289001465,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 5.8817,
+      "step": 3
+    },
+    {
+      "epoch": 0.00021120578703856486,
+      "grad_norm": 3.7482376098632812,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 6.1575,
+      "step": 4
+    },
+    {
+      "epoch": 0.0002640072337982061,
+      "grad_norm": 3.965822219848633,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 5.212,
+      "step": 5
+    },
+    {
+      "epoch": 0.0003168086805578473,
+      "grad_norm": 2.9985687732696533,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 4.4805,
+      "step": 6
+    },
+    {
+      "epoch": 0.0003696101273174885,
+      "grad_norm": 3.5063633918762207,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 4.7592,
+      "step": 7
+    },
+    {
+      "epoch": 0.0004224115740771297,
+      "grad_norm": 3.624417781829834,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 4.1695,
+      "step": 8
+    },
+    {
+      "epoch": 0.00047521302083677094,
+      "grad_norm": 3.540501832962036,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 3.7187,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005280144675964122,
+      "grad_norm": 3.432539224624634,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 3.3295,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005280144675964122,
+      "eval_loss": 3.3748233318328857,
+      "eval_runtime": 3686.9343,
+      "eval_samples_per_second": 4.326,
+      "eval_steps_per_second": 2.163,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005808159143560534,
+      "grad_norm": 4.083893299102783,
+      "learning_rate": 5e-05,
+      "loss": 3.3886,
+      "step": 11
+    },
+    {
+      "epoch": 0.0006336173611156946,
+      "grad_norm": 4.254306316375732,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.0357,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006864188078753358,
+      "grad_norm": 3.4154324531555176,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.7945,
+      "step": 13
+    },
+    {
+      "epoch": 0.000739220254634977,
+      "grad_norm": 3.889486074447632,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3507,
+      "step": 14
+    },
+    {
+      "epoch": 0.0007920217013946182,
+      "grad_norm": 3.418156862258911,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.0169,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008448231481542594,
+      "grad_norm": 3.2946226596832275,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.4668,
+      "step": 16
+    },
+    {
+      "epoch": 0.0008976245949139007,
+      "grad_norm": 4.151547431945801,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.4295,
+      "step": 17
+    },
+    {
+      "epoch": 0.0009504260416735419,
+      "grad_norm": 3.994763135910034,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.4314,
+      "step": 18
+    },
+    {
+      "epoch": 0.001003227488433183,
+      "grad_norm": 3.648967742919922,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.3779,
+      "step": 19
+    },
+    {
+      "epoch": 0.0010560289351928243,
+      "grad_norm": 3.826017379760742,
+      "learning_rate": 0.0,
+      "loss": 2.3704,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010560289351928243,
+      "eval_loss": 2.4360647201538086,
+      "eval_runtime": 3688.8851,
+      "eval_samples_per_second": 4.324,
+      "eval_steps_per_second": 2.162,
+      "step": 20
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.335368898576384e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb6b058d64085d3cbcbc75cfb25773503413eb66d1bb00acd2dd09c15b25ebe
+size 6776

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
+size 534194

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb6b058d64085d3cbcbc75cfb25773503413eb66d1bb00acd2dd09c15b25ebe
+size 6776