You can deploy this model and start earning money today!

ping98k/
xglm-7.5B-alpaca-th-lora

Name: xglm-7.5B-alpaca-th-lora
Availability: InStock

peft

facebook/xglm-7.5B

adapter

Views

No views yet

lora fine tune facebook/xglm-7.5B with Thaweewat/alpaca-cleaned-52k-th

template

### Question: instruction
input
### Answer:

peft_config  = LoraConfig(
    r=64,
    lora_alpha=128,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
    target_modules=[
        "q_proj",
        "k_proj",
        "v_proj",
        "out_proj",
        "fc1",
        "fc2",      
    ]
)

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: fp4
bnb_4bit_use_double_quant: False
bnb_4bit_compute_dtype: float32

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: fp4
bnb_4bit_use_double_quant: False
bnb_4bit_compute_dtype: float32

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: fp4
bnb_4bit_use_double_quant: False
bnb_4bit_compute_dtype: float32

Framework versions

PEFT 0.6.0.dev0
PEFT 0.6.0.dev0
PEFT 0.6.0.dev0

ping98k/xglm-7.5B-alpaca-th-lora

Training procedure

Framework versions

ping98k/
xglm-7.5B-alpaca-th-lora