Instructions to use chlee10/T3Q-ko-solar-sft-v3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chlee10/T3Q-ko-solar-sft-v3.0 with Transformers:

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

pipe = pipeline("text-generation", model="chlee10/T3Q-ko-solar-sft-v3.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chlee10/T3Q-ko-solar-sft-v3.0")
model = AutoModelForCausalLM.from_pretrained("chlee10/T3Q-ko-solar-sft-v3.0")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use chlee10/T3Q-ko-solar-sft-v3.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chlee10/T3Q-ko-solar-sft-v3.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chlee10/T3Q-ko-solar-sft-v3.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chlee10/T3Q-ko-solar-sft-v3.0

SGLang

How to use chlee10/T3Q-ko-solar-sft-v3.0 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 "chlee10/T3Q-ko-solar-sft-v3.0" \
    --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": "chlee10/T3Q-ko-solar-sft-v3.0",
		"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 "chlee10/T3Q-ko-solar-sft-v3.0" \
        --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": "chlee10/T3Q-ko-solar-sft-v3.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chlee10/T3Q-ko-solar-sft-v3.0 with Docker Model Runner:
```
docker model run hf.co/chlee10/T3Q-ko-solar-sft-v3.0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Update @ 2024.03.25

T3Q-ko-solar-sft-v3.0

This model is a SFT fine-tuned version of chihoonlee10/T3Q-ko-solar-dpo-v3.0

Model Developers Chihoon Lee(chlee10), T3Q

Training hyperparameters

The following hyperparameters were used during training:

  # 데이터셋과 훈련 횟수와 관련된 하이퍼 파라미터
  batch_size = 16
  num_epochs = 1
  micro_batch = 1
  gradient_accumulation_steps = batch_size // micro_batch
  
  # 훈련 방법에 대한 하이퍼 파라미터
  cutoff_len = 4096
  lr_scheduler = 'cosine'
  warmup_ratio = 0.06 # warmup_steps = 100
  learning_rate = 5e-5
  optimizer = 'paged_adamw_32bit'
  weight_decay = 0.01
  max_grad_norm = 1.0
  
  # LoRA config
  lora_r = 16
  lora_alpha = 16
  lora_dropout = 0.05
  lora_target_modules = ["k_proj", "v_proj","gate_proj", "down_proj", "up_proj"]
  
  # Tokenizer에서 나오는 input값 설정 옵션
  train_on_inputs = False
  add_eos_token = False
  
  # NEFTune params
  neftune_noise_alpha = 5

Downloads last month: 2

Safetensors

Model size

11B params

Tensor type

F32

Model tree for chlee10/T3Q-ko-solar-sft-v3.0

Base model

chihoonlee10/T3Q-ko-solar-dpo-v3.0

Finetuned

(2)

this model

Quantizations

3 models

chlee10
/

T3Q-ko-solar-sft-v3.0

T3Q-ko-solar-sft-v3.0

Training hyperparameters

Model tree for chlee10/T3Q-ko-solar-sft-v3.0

Dataset used to train chlee10/T3Q-ko-solar-sft-v3.0