metadata

library_name: peft
widget:
  - text: >-
      Below is an instruction that describes a task, paired with an input that
      provides further context. Write a response that appropriately completes
      the request. ### Instruction: Generate an SQL statement to add a row in
      the customers table where the columns are name, address, and city. ###
      Input: name = John, address = 123 Main Street, city = Winter Park ###
      Response: 
inference:
  parameters:
    temperature: 0.1
    max_new_tokens: 1024
base_model: meta-llama/Llama-2-7b-hf
license: llama2
datasets:
  - sahil2801/CodeAlpaca-20k
language:
  - en
tags:
  - code
  - text-generation-inference
  - finetuned
  - llama-2
  - code-llama

Model Card for Model ID

How to Get Started with the Model

To use this adapter:

from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM

# Load base model in 4 bit
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf", load_in_4bit=True)

# Wrap model with pretrained model weights
config = PeftConfig.from_pretrained("MaziyarPanahi/Llama-2-7b-hf-codealpaca-4bit")
model = PeftModel.from_pretrained(model, "MaziyarPanahi/Llama-2-7b-hf-codealpaca-4bit", config=config)

Prompt Template:

Below is an instruction that describes a task, paired with an input
that provides further context. Write a response that appropriately
completes the request.
### Instruction: {instruction}
### Input: {input}
### Response:

Training procedure

The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: float16

Framework versions

PEFT 0.7.1