kaxap/llama2-sql-instruct-sys-prompt
Viewer β’ Updated β’ 81.6k β’ 6 β’ 3
How to use ataberkd/llama-2-7b-SQL_FINETUNED_1K with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="ataberkd/llama-2-7b-SQL_FINETUNED_1K") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("ataberkd/llama-2-7b-SQL_FINETUNED_1K")
model = AutoModelForCausalLM.from_pretrained("ataberkd/llama-2-7b-SQL_FINETUNED_1K")How to use ataberkd/llama-2-7b-SQL_FINETUNED_1K with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ataberkd/llama-2-7b-SQL_FINETUNED_1K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "ataberkd/llama-2-7b-SQL_FINETUNED_1K",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/ataberkd/llama-2-7b-SQL_FINETUNED_1K
How to use ataberkd/llama-2-7b-SQL_FINETUNED_1K with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "ataberkd/llama-2-7b-SQL_FINETUNED_1K" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "ataberkd/llama-2-7b-SQL_FINETUNED_1K",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "ataberkd/llama-2-7b-SQL_FINETUNED_1K" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "ataberkd/llama-2-7b-SQL_FINETUNED_1K",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use ataberkd/llama-2-7b-SQL_FINETUNED_1K with Docker Model Runner:
docker model run hf.co/ataberkd/llama-2-7b-SQL_FINETUNED_1K
!pip install -q accelerate==0.21.0 transformers==4.31.0
import os
import torch
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
pipeline,
logging,
)
model = "ataberkd/llama-2-7b-SQL_FINETUNED_1K"
prompt = 'You are an expert in SQL and data analysis. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the question and give the explanation of result your giving. CREATE TABLE statement: CREATE TABLE "user" ( "name" text, "surname" text, "tel" text, "address" text, "performanceScore" text,"Age" text, "Language" text );. Question: "Can you bring users who speak French and are greater than 20 years old?"'
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
sequences = pipeline(
f'<s>[INST] {prompt} [/INST]',
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=200,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
docker model run hf.co/ataberkd/llama-2-7b-SQL_FINETUNED_1K