xglm-7.5B-alpaca-th-lora

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

xglm-7.5B-alpaca-th-lora is a machine learning model from ping98k. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.

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

Downloads · 30 days

5% of all-time downloads

All-time downloads

149

Public

Repo size

604 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin604 MB · 100%

At a glance

Library: peft
Access: Public
Created: Sep 17, 2023
Updated: Dec 5, 2023
SHA: abf7fea5

Base models

facebook/xglm-7.5B

Model card

From the Hugging Face model README

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

Library: peft
Created: Sep 17, 2023
Updated: Dec 5, 2023