Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cc0296ac677604615ccb5fc889f4b32e5baba11dec7cc3b74a6f5b62dd2cc6
+size 159967880

checkpoint-396/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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 0.9.0

checkpoint-396/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-396/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cc0296ac677604615ccb5fc889f4b32e5baba11dec7cc3b74a6f5b62dd2cc6
+size 159967880

checkpoint-396/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8362b4cd6dd032dea0512c162864c1ee4941697e48bb8900e3a509092f0512a
+size 320194002

checkpoint-396/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-396/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-396/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57964bbfefdaa0007fbf6bb66063ef0bade3a8e436f7cbda4cf2b9d2d025c03b
+size 1064

checkpoint-396/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-396/tokenizer.model

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

checkpoint-396/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-396/trainer_state.json

@@ -0,0 +1,246 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 396,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.12694114446640015,
+      "learning_rate": 1.8750000000000002e-05,
+      "logits/chosen": -0.05689077079296112,
+      "logits/rejected": -0.10778996348381042,
+      "logps/chosen": -51.92569351196289,
+      "logps/rejected": -58.57919692993164,
+      "loss": 0.3444,
+      "rewards/accuracies": 0.8846153616905212,
+      "rewards/chosen": 0.8715194463729858,
+      "rewards/margins": 1.492788553237915,
+      "rewards/rejected": -0.6212692260742188,
+      "step": 26
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.0007516579935327172,
+      "learning_rate": 2.9073033707865168e-05,
+      "logits/chosen": -0.13101856410503387,
+      "logits/rejected": -0.13021668791770935,
+      "logps/chosen": -27.36025619506836,
+      "logps/rejected": -104.82938385009766,
+      "loss": 0.0007,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.3301053047180176,
+      "rewards/margins": 8.549433708190918,
+      "rewards/rejected": -5.219327926635742,
+      "step": 52
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.00040602186345495284,
+      "learning_rate": 2.6882022471910113e-05,
+      "logits/chosen": -0.21169501543045044,
+      "logits/rejected": -0.18469807505607605,
+      "logps/chosen": -21.630279541015625,
+      "logps/rejected": -122.15676879882812,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.915804386138916,
+      "rewards/margins": 10.897878646850586,
+      "rewards/rejected": -6.98207426071167,
+      "step": 78
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.00029909086879342794,
+      "learning_rate": 2.4691011235955056e-05,
+      "logits/chosen": -0.22328408062458038,
+      "logits/rejected": -0.19363602995872498,
+      "logps/chosen": -20.646940231323242,
+      "logps/rejected": -125.94076538085938,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.001604080200195,
+      "rewards/margins": 11.342691421508789,
+      "rewards/rejected": -7.341087818145752,
+      "step": 104
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.0008555773529224098,
+      "learning_rate": 2.25e-05,
+      "logits/chosen": -0.21473294496536255,
+      "logits/rejected": -0.1837671399116516,
+      "logps/chosen": -20.335859298706055,
+      "logps/rejected": -127.00772094726562,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.043529033660889,
+      "rewards/margins": 11.498052597045898,
+      "rewards/rejected": -7.454523086547852,
+      "step": 130
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.00022369994258042425,
+      "learning_rate": 2.0308988764044947e-05,
+      "logits/chosen": -0.21327663958072662,
+      "logits/rejected": -0.1831081211566925,
+      "logps/chosen": -20.030139923095703,
+      "logps/rejected": -127.70628356933594,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.0749359130859375,
+      "rewards/margins": 11.608404159545898,
+      "rewards/rejected": -7.533467769622803,
+      "step": 156
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.0002135779504897073,
+      "learning_rate": 1.8117977528089886e-05,
+      "logits/chosen": -0.22201663255691528,
+      "logits/rejected": -0.1898954212665558,
+      "logps/chosen": -19.46499252319336,
+      "logps/rejected": -130.10020446777344,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.127849102020264,
+      "rewards/margins": 11.870473861694336,
+      "rewards/rejected": -7.742624759674072,
+      "step": 182
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.00018591841217130423,
+      "learning_rate": 1.5926966292134832e-05,
+      "logits/chosen": -0.2321176379919052,
+      "logits/rejected": -0.20056405663490295,
+      "logps/chosen": -19.843402862548828,
+      "logps/rejected": -129.42715454101562,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.082259178161621,
+      "rewards/margins": 11.799769401550293,
+      "rewards/rejected": -7.71751070022583,
+      "step": 208
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.0001685543538769707,
+      "learning_rate": 1.3735955056179776e-05,
+      "logits/chosen": -0.22563436627388,
+      "logits/rejected": -0.19371062517166138,
+      "logps/chosen": -19.1228084564209,
+      "logps/rejected": -131.58114624023438,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.158024787902832,
+      "rewards/margins": 12.063767433166504,
+      "rewards/rejected": -7.905743598937988,
+      "step": 234
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.0001603550190338865,
+      "learning_rate": 1.154494382022472e-05,
+      "logits/chosen": -0.23086732625961304,
+      "logits/rejected": -0.1993020474910736,
+      "logps/chosen": -19.312213897705078,
+      "logps/rejected": -131.04287719726562,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.135034561157227,
+      "rewards/margins": 12.01096248626709,
+      "rewards/rejected": -7.8759284019470215,
+      "step": 260
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.00015357887605205178,
+      "learning_rate": 9.353932584269662e-06,
+      "logits/chosen": -0.23084178566932678,
+      "logits/rejected": -0.1990644335746765,
+      "logps/chosen": -18.966245651245117,
+      "logps/rejected": -132.33311462402344,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.179388523101807,
+      "rewards/margins": 12.165773391723633,
+      "rewards/rejected": -7.986386299133301,
+      "step": 286
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.0001516837510280311,
+      "learning_rate": 7.162921348314607e-06,
+      "logits/chosen": -0.22668816149234772,
+      "logits/rejected": -0.19253727793693542,
+      "logps/chosen": -18.499208450317383,
+      "logps/rejected": -133.57839965820312,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.219171047210693,
+      "rewards/margins": 12.308831214904785,
+      "rewards/rejected": -8.08966064453125,
+      "step": 312
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.0005327428807504475,
+      "learning_rate": 4.97191011235955e-06,
+      "logits/chosen": -0.2215849608182907,
+      "logits/rejected": -0.1875036060810089,
+      "logps/chosen": -18.43309211730957,
+      "logps/rejected": -133.9069366455078,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.235932350158691,
+      "rewards/margins": 12.36194896697998,
+      "rewards/rejected": -8.126015663146973,
+      "step": 338
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.00013107992708683014,
+      "learning_rate": 2.7808988764044947e-06,
+      "logits/chosen": -0.23455286026000977,
+      "logits/rejected": -0.20136354863643646,
+      "logps/chosen": -18.942277908325195,
+      "logps/rejected": -132.9586639404297,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.165750503540039,
+      "rewards/margins": 12.227232933044434,
+      "rewards/rejected": -8.061481475830078,
+      "step": 364
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.00013512423902284354,
+      "learning_rate": 5.898876404494382e-07,
+      "logits/chosen": -0.23882614076137543,
+      "logits/rejected": -0.20455202460289001,
+      "logps/chosen": -18.73713493347168,
+      "logps/rejected": -132.86285400390625,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.19658088684082,
+      "rewards/margins": 12.254826545715332,
+      "rewards/rejected": -8.058244705200195,
+      "step": 390
+    }
+  ],
+  "logging_steps": 26,
+  "max_steps": 396,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-396/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4b8f491d16cd9fcfb811bbae739ead2e60d6695fb23b872cbae05caf628962
+size 4984

handler.py

@@ -0,0 +1,32 @@
+from typing import  Dict, List, Any
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+from peft import PeftModel
+import json
+import os
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        base_model_path = json.load(open(os.path.join(path, "training_params.json")))["model"]
+        model = AutoModelForCausalLM.from_pretrained(
+            base_model_path,
+            torch_dtype=torch.float16,
+            low_cpu_mem_usage=True,
+            trust_remote_code=True,
+            device_map="auto",
+        )
+        tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
+        model.resize_token_embeddings(len(tokenizer))
+        model = PeftModel.from_pretrained(model, path)
+        model = model.merge_and_unload()
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+        if parameters is not None:
+            prediction = self.pipeline(inputs, **parameters)
+        else:
+            prediction = self.pipeline(inputs)
+        return prediction

requirements.txt

@@ -0,0 +1,2 @@
+peft==0.9.0
+transformers==4.38.2

runs/Mar16_16-48-18_r-mjmanashti-fine-tuning-models-n5pcfi59-2f5b6-badkq/events.out.tfevents.1710607715.r-mjmanashti-fine-tuning-models-n5pcfi59-2f5b6-badkq.54.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab89123a814e20a19f9fc15d3004388e016fb86b40de4f2f59cf24c9fb7becc
-size 14677
+oid sha256:81536a3eba8807c24735d662c4c6eaaf22c4436f1b18580ef3fb1cd7a0052e03
+size 15719

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "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:dc4b8f491d16cd9fcfb811bbae739ead2e60d6695fb23b872cbae05caf628962
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "meta-llama/Llama-2-7b-hf",
+    "project_name": "autotrain-4h51a-miy0m",
+    "data_path": "autotrain-4h51a-miy0m/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "trainer": "dpo",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 3e-05,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "repo_id": "mjmanashti/autotrain-4h51a-miy0m",
+    "username": "mjmanashti"
+}