Instructions to use USato/openthaigpt-iot-lora-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use USato/openthaigpt-iot-lora-instruct with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("openthaigpt/openthaigpt1.5-7b-instruct")
model = PeftModel.from_pretrained(base_model, "USato/openthaigpt-iot-lora-instruct")

Transformers

How to use USato/openthaigpt-iot-lora-instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="USato/openthaigpt-iot-lora-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("USato/openthaigpt-iot-lora-instruct")
model = AutoModelForCausalLM.from_pretrained("USato/openthaigpt-iot-lora-instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use USato/openthaigpt-iot-lora-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "USato/openthaigpt-iot-lora-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "USato/openthaigpt-iot-lora-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/USato/openthaigpt-iot-lora-instruct

SGLang

How to use USato/openthaigpt-iot-lora-instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "USato/openthaigpt-iot-lora-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "USato/openthaigpt-iot-lora-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "USato/openthaigpt-iot-lora-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "USato/openthaigpt-iot-lora-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use USato/openthaigpt-iot-lora-instruct with Docker Model Runner:
```
docker model run hf.co/USato/openthaigpt-iot-lora-instruct
```

See axolotl config

axolotl version: 0.12.2

adapter: qlora
base_model: openthaigpt/openthaigpt1.5-7b-instruct
bf16: true
chat_template: chatml
dataloader_num_workers: 2
dataset_processes: 2
datasets:
- ds_type: json
  eot_tokens:
  - <|im_end|>
  field_messages: messages
  message_property_mappings:
    content: content
    role: role
  path: iot_train_chat.json
  split: train
  type: chat_template
flash_attention: true
fp16: false
gradient_accumulation_steps: 2
gradient_checkpointing: true
learning_rate: 0.0002
load_in_4bit: true
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_r: 16
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
lr_scheduler: cosine
max_grad_norm: 1.0
micro_batch_size: 8
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: paged_adamw_8bit
output_dir: ./outputs/openthaigpt-iot-finetune-L4
pad_to_sequence_len: true
plugins:
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
preprocessing_num_workers: 2
sample_packing: true
save_steps: 50
save_strategy: steps
sequence_len: 4096
tokenizer_type: AutoTokenizer
warmup_steps: 100
xformers_attention: false

outputs/openthaigpt-iot-finetune-L4

This model is a fine-tuned version of openthaigpt/openthaigpt1.5-7b-instruct on the iot_train_chat.json dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 52

Training results

Framework versions

PEFT 0.17.0
Transformers 4.55.2
Pytorch 2.5.1+cu124
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 4

Model tree for USato/openthaigpt-iot-lora-instruct

Base model

openthaigpt/openthaigpt1.5-7b-instruct

Adapter

(6)

this model