bharatiyabytes
/

Llama-2-7b-sarcasm

Text Generation

Model card Files Files and versions

Training procedure

The following bitsandbytes quantization config was used during training:

quant_method: bitsandbytes
_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: bfloat16
bnb_4bit_quant_storage: uint8
load_in_4bit: True
load_in_8bit: False

Framework versions

PEFT 0.4.0

Downloads last month: 1

Safetensors

Model size

7B params

Tensor type

F32

·

Model tree for bharatiyabytes/Llama-2-7b-sarcasm

Base model

meta-llama/Llama-2-7b-hf

Adapter

(2399)

this model

Quantizations

Datasets used to train bharatiyabytes/Llama-2-7b-sarcasm