model pefted

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,64 @@
+---
+base_model: ybelkada/falcon-7b-sharded-bf16
+tags:
+- generated_from_trainer
+model-index:
+- name: falcon-7b-sharded-bf16-finetuned-mental-health-conversational
+  results: []
+license: mit
+datasets:
+- heliosbrahma/mental_health_chatbot_dataset
+language:
+- en
+metrics:
+- rouge
+pipeline_tag: conversational
+---
+
+<!-- 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. -->
+
+# falcon-7b-sharded-bf16-finetuned-mental-health-conversational
+
+This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on a custom [heliosbrahma/mental_health_chatbot_dataset](https://huggingface.co/datasets/heliosbrahma/mental_health_chatbot_dataset) dataset.
+
+## Model description
+
+This model is fine-tuned on custom mental health conversational dataset. The rationale behind this is to answer mental health related queries that can be factually verified without responding gibberish words.
+
+## Intended uses & limitations
+
+The model was trained on the dataset which may contain sensitive information related to mental health. It is important to note that while mental health chatbots built using this model can be helpful, they are not a replacement for professional mental health care.
+
+## Training and evaluation data
+
+This model was trained on custom [heliosbrahma/mental_health_chatbot_dataset](https://huggingface.co/datasets/heliosbrahma/mental_health_chatbot_dataset) dataset which 172 rows of conversational pair of questions and answers.
+
+## Training procedure
+
+This model was trained using QLoRA technique to fine-tune on a custom dataset on free-tier GPU available in Google Colab.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 320
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.2
+- Tokenizers 0.13.3

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:524d8c892fd96737e3a529a43ecf59c6c4cdf1bcac104fcb915330e8d724ac87
+size 261189453

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9af4e88b58f2a7a5bbacde5ae29b192d67a7b44363f3adc00eacbf3e8658651
+size 261131840

runs/Aug02_10-07-46_8c499d4ea35e/events.out.tfevents.1690970918.8c499d4ea35e.5631.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22312a727ebad562f024e31fe6f732e3afead91259b41a2548bf1be4825426eb
+size 10368

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:565d182e419f9901a02de3f4cd234c1ea5d1980b704e81cffea9f6cea164eb84
+size 4091