Dongwookss/q_a_korean_futsal
Viewer β’ Updated β’ 2.33k β’ 24
How to use Dongwookss/futfut_by_zephyr7b with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Dongwookss/futfut_by_zephyr7b")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Dongwookss/futfut_by_zephyr7b")
model = AutoModelForCausalLM.from_pretrained("Dongwookss/futfut_by_zephyr7b", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))How to use Dongwookss/futfut_by_zephyr7b with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dongwookss/futfut_by_zephyr7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Dongwookss/futfut_by_zephyr7b",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/Dongwookss/futfut_by_zephyr7b
How to use Dongwookss/futfut_by_zephyr7b with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Dongwookss/futfut_by_zephyr7b" \
--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": "Dongwookss/futfut_by_zephyr7b",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'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 "Dongwookss/futfut_by_zephyr7b" \
--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": "Dongwookss/futfut_by_zephyr7b",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'How to use Dongwookss/futfut_by_zephyr7b with Docker Model Runner:
docker model run hf.co/Dongwookss/futfut_by_zephyr7b
Unsloth ν¨ν€μ§λ₯Ό μ¬μ©νμ¬ LoRA μ§ννμμ΅λλ€.
SFT Trainerλ₯Ό ν΅ν΄ νλ ¨μ μ§ν
νμ© λ°μ΄ν°
Environment : Colab νκ²½μμ μ§ννμμΌλ©° L4 GPUλ₯Ό μ¬μ©νμμ΅λλ€.
Model Load
#!pip install transformers==4.40.0 accelerate
import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = 'Dongwookss/small_fut_final'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
model.eval()
Query
from transformers import TextStreamer
PROMPT = '''Below is an instruction that describes a task. Write a response that appropriately completes the request.
μ μνλ contextμμλ§ λλ΅νκ³ contextμ μλ λ΄μ©μ λͺ¨λ₯΄κ² λ€κ³ λλ΅ν΄'''
messages = [
{"role": "system", "content": f"{PROMPT}"},
{"role": "user", "content": f"{instruction}"}
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
text_streamer = TextStreamer(tokenizer)
_ = model.generate(
input_ids,
max_new_tokens=4096,
eos_token_id=terminators,
do_sample=True,
streamer = text_streamer,
temperature=0.6,
top_p=0.9,
repetition_penalty = 1.1
)