sujitvasanth/TheBloke-openchat-3.5-0106-GPTQ-PEFTadapterJsonSear

Model Card for Model ID

Model Details

Model Description

• Developed by: Dr Sujit Vasanth
• Model type: QLoRA PEFT
• Language(s) (NLP): Json, English
• License: [More Information Needed]
• Finetuned from model [optional]: TheBloke/openchat-3.5-0106-GPTQ

Model Sources [optional]

• Repository: https://github.com/sujitvasanth/GPTQ-finetune
• Demo [optional]: https://github.com/sujitvasanth/GPTQ-finetune/blob/main/GPTQ-finetune.py

How to Get Started with the Model

model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config= GPTQConfig(bits=4, disable_exllama=False),device_map="auto") # is_trainable=True tokenizer = AutoTokenizer.from_pretrained(model_id) tokenizer.pad_token = tokenizer.eos_token model.load_adapter(adapter_id)

Training Details

Training Data

https://huggingface.co/datasets/sujitvasanth/jsonsearch2 User: Assistant examples of Json search Query

Training Procedure

QLora PEFT training on custom dataset

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[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 0.8.2