Upload folder using huggingface_hub

README.md

@@ -0,0 +1,44 @@
+---
+tags:
+- autotrain
+- text-generation
+- peft
+library_name: transformers
+widget:
+ - messages:
+ - role: user
+ content: What is your favorite condiment?
+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 +1,31 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+ "bias": "none",
+ "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": 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": [
+ "dense_h_to_4h",
+ "dense",
+ "dense_4h_to_h",
+ "query_key_value"
+ ],
+ "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:a55bec49e4c42eb7ee221c4c066b85b221c61f019a215ba0138c6fdbcd75665b
+size 130583912

checkpoint-381/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b-instruct
+---
+
+# 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 0.10.0

checkpoint-381/adapter_config.json

@@ -0,0 +1,31 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+ "bias": "none",
+ "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": 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": [
+ "dense_h_to_4h",
+ "dense",
+ "dense_4h_to_h",
+ "query_key_value"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}

checkpoint-381/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55bec49e4c42eb7ee221c4c066b85b221c61f019a215ba0138c6fdbcd75665b
+size 130583912

checkpoint-381/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c914f49dd3d5dd0328d7bb43cebbb5e8c792ddc94ede5bd0816da601bd46922
+size 261311226

checkpoint-381/pytorch_model.bin

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

checkpoint-381/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201071f1a3b3fe875d7780812cac0d5911c25aa3c07c8035b3f3ec0b0708c074
+size 14244

checkpoint-381/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1172be2b6d92733b59381bd089018a6fb6f138835460aded2035c15c2d2d5def
+size 1064

checkpoint-381/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+ "additional_special_tokens": [
+ ">>TITLE<<",
+ ">>ABSTRACT<<",
+ ">>INTRODUCTION<<",
+ ">>SUMMARY<<",
+ ">>COMMENT<<",
+ ">>ANSWER<<",
+ ">>QUESTION<<",
+ ">>DOMAIN<<",
+ ">>PREFIX<<",
+ ">>SUFFIX<<",
+ ">>MIDDLE<<"
+ ],
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|endoftext|>"
+}

checkpoint-381/tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": ">>TITLE<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": ">>ABSTRACT<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": ">>INTRODUCTION<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": ">>SUMMARY<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": ">>COMMENT<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "5": {
+ "content": ">>ANSWER<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "6": {
+ "content": ">>QUESTION<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "7": {
+ "content": ">>DOMAIN<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "8": {
+ "content": ">>PREFIX<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "9": {
+ "content": ">>SUFFIX<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "10": {
+ "content": ">>MIDDLE<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "11": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ ">>TITLE<<",
+ ">>ABSTRACT<<",
+ ">>INTRODUCTION<<",
+ ">>SUMMARY<<",
+ ">>COMMENT<<",
+ ">>ANSWER<<",
+ ">>QUESTION<<",
+ ">>DOMAIN<<",
+ ">>PREFIX<<",
+ ">>SUFFIX<<",
+ ">>MIDDLE<<"
+ ],
+ "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": true,
+ "eos_token": "<|endoftext|>",
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 2048,
+ "pad_token": "<|endoftext|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-381/trainer_state.json

@@ -0,0 +1,126 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.9823874755381605,
+ "eval_steps": 500,
+ "global_step": 381,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.2,
+ "grad_norm": 0.28035762906074524,
+ "learning_rate": 1.923076923076923e-05,
+ "loss": 1.4971,
+ "step": 25
+ },
+ {
+ "epoch": 0.39,
+ "grad_norm": 0.6015884876251221,
+ "learning_rate": 2.9035087719298245e-05,
+ "loss": 1.2201,
+ "step": 50
+ },
+ {
+ "epoch": 0.59,
+ "grad_norm": 0.7144075036048889,
+ "learning_rate": 2.6842105263157896e-05,
+ "loss": 1.1631,
+ "step": 75
+ },
+ {
+ "epoch": 0.78,
+ "grad_norm": 0.8597971200942993,
+ "learning_rate": 2.4649122807017547e-05,
+ "loss": 1.0016,
+ "step": 100
+ },
+ {
+ "epoch": 0.98,
+ "grad_norm": 0.7555738091468811,
+ "learning_rate": 2.245614035087719e-05,
+ "loss": 1.029,
+ "step": 125
+ },
+ {
+ "epoch": 1.17,
+ "grad_norm": 0.8726145029067993,
+ "learning_rate": 2.0263157894736842e-05,
+ "loss": 0.9495,
+ "step": 150
+ },
+ {
+ "epoch": 1.37,
+ "grad_norm": 0.8828539252281189,
+ "learning_rate": 1.8070175438596493e-05,
+ "loss": 0.9688,
+ "step": 175
+ },
+ {
+ "epoch": 1.57,
+ "grad_norm": 0.9864718914031982,
+ "learning_rate": 1.5877192982456144e-05,
+ "loss": 0.9321,
+ "step": 200
+ },
+ {
+ "epoch": 1.76,
+ "grad_norm": 0.8643972277641296,
+ "learning_rate": 1.368421052631579e-05,
+ "loss": 0.9408,
+ "step": 225
+ },
+ {
+ "epoch": 1.96,
+ "grad_norm": 0.9563308954238892,
+ "learning_rate": 1.1491228070175439e-05,
+ "loss": 0.8721,
+ "step": 250
+ },
+ {
+ "epoch": 2.15,
+ "grad_norm": 0.9510623812675476,
+ "learning_rate": 9.298245614035088e-06,
+ "loss": 0.8556,
+ "step": 275
+ },
+ {
+ "epoch": 2.35,
+ "grad_norm": 1.0566192865371704,
+ "learning_rate": 7.105263157894737e-06,
+ "loss": 0.8947,
+ "step": 300
+ },
+ {
+ "epoch": 2.54,
+ "grad_norm": 0.9196553230285645,
+ "learning_rate": 4.912280701754386e-06,
+ "loss": 0.7975,
+ "step": 325
+ },
+ {
+ "epoch": 2.74,
+ "grad_norm": 0.9796131253242493,
+ "learning_rate": 2.719298245614035e-06,
+ "loss": 0.8946,
+ "step": 350
+ },
+ {
+ "epoch": 2.94,
+ "grad_norm": 1.0158289670944214,
+ "learning_rate": 5.263157894736842e-07,
+ "loss": 0.837,
+ "step": 375
+ }
+ ],
+ "logging_steps": 25,
+ "max_steps": 381,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 3,
+ "save_steps": 500,
+ "total_flos": 6.235021019027866e+16,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-381/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3b58abfa65a54b0bcaf4af514ac0a94a73ee0857789cc85b0f40e5e22fc3b3
+size 4984

runs/Mar25_23-59-59_r-pruhtopia-falcon-toc-generation-umfbhb8c-161e3-l0138/events.out.tfevents.1711411202.r-pruhtopia-falcon-toc-generation-umfbhb8c-161e3-l0138.57.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf56cbc3d322bd23cfc894c7c0bb6f9847de5be5bcf16ac04809195580902de
-size 8724
+oid sha256:8f9d7b07a2ef2c5ce3c9d4fe8520228d7fccc6db857fc52d708f206d431e706a
+size 9289

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+ "additional_special_tokens": [
+ ">>TITLE<<",
+ ">>ABSTRACT<<",
+ ">>INTRODUCTION<<",
+ ">>SUMMARY<<",
+ ">>COMMENT<<",
+ ">>ANSWER<<",
+ ">>QUESTION<<",
+ ">>DOMAIN<<",
+ ">>PREFIX<<",
+ ">>SUFFIX<<",
+ ">>MIDDLE<<"
+ ],
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": ">>TITLE<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": ">>ABSTRACT<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": ">>INTRODUCTION<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": ">>SUMMARY<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": ">>COMMENT<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "5": {
+ "content": ">>ANSWER<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "6": {
+ "content": ">>QUESTION<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "7": {
+ "content": ">>DOMAIN<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "8": {
+ "content": ">>PREFIX<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "9": {
+ "content": ">>SUFFIX<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "10": {
+ "content": ">>MIDDLE<<",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "11": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ ">>TITLE<<",
+ ">>ABSTRACT<<",
+ ">>INTRODUCTION<<",
+ ">>SUMMARY<<",
+ ">>COMMENT<<",
+ ">>ANSWER<<",
+ ">>QUESTION<<",
+ ">>DOMAIN<<",
+ ">>PREFIX<<",
+ ">>SUFFIX<<",
+ ">>MIDDLE<<"
+ ],
+ "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": true,
+ "eos_token": "<|endoftext|>",
+ "model_input_names": [
+ "input_ids",
+ "attention_mask"
+ ],
+ "model_max_length": 2048,
+ "pad_token": "<|endoftext|>",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3b58abfa65a54b0bcaf4af514ac0a94a73ee0857789cc85b0f40e5e22fc3b3
+size 4984

training_params.json

@@ -0,0 +1,47 @@
+{
+ "model": "tiiuae/falcon-7b-instruct",
+ "project_name": "falcon-toc-generation",
+ "data_path": "pruhtopia/falcon-toc-generation",
+ "train_split": "train",
+ "valid_split": null,
+ "add_eos_token": true,
+ "block_size": 1024,
+ "model_max_length": 2048,
+ "padding": "right",
+ "trainer": "sft",
+ "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": 1,
+ "warmup_ratio": 0.1,
+ "gradient_accumulation": 4,
+ "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": "prompt",
+ "text_column": "text",
+ "rejected_text_column": "rejected_text",
+ "push_to_hub": true,
+ "repo_id": "pruhtopia/falcon-toc-generation",
+ "username": "pruhtopia"
+}