You can deploy this model and start earning money today!

nakcnx/
typhoon_thai_alpaca_qlora

peft

safetensors

Thaweewat/alpaca-cleaned-52k-th

scb10x/typhoon-7b

adapter

Views

No views yet

Model Description

Typhoon-7b QLoRA Finetune by unsloth with Thai Alpaca dataset.

Training Hyperparameters

The following bitsandbytes quantization config was used during training:

r = 64
lora_alpha = 16
lora_dropout = 0.05
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: float16

Loss

Step Training Loss
2500 1.241900
5000 1.123600
7500 1.014600
10000 0.902200
12500 0.906500
15000 0.683900
17500 0.650900
20000 0.584800
22500 0.385100
25000 0.384100

Framework versions

PEFT 0.7.0

nakcnx/typhoon_thai_alpaca_qlora

Model Description

Training Hyperparameters

Loss

Framework versions

nakcnx/
typhoon_thai_alpaca_qlora