Instructions to use cmwalker00/phi-1_5-finetuned-know_sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cmwalker00/phi-1_5-finetuned-know_sql with Transformers:

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

pipe = pipeline("text-generation", model="cmwalker00/phi-1_5-finetuned-know_sql", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("cmwalker00/phi-1_5-finetuned-know_sql", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cmwalker00/phi-1_5-finetuned-know_sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cmwalker00/phi-1_5-finetuned-know_sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cmwalker00/phi-1_5-finetuned-know_sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cmwalker00/phi-1_5-finetuned-know_sql

SGLang

How to use cmwalker00/phi-1_5-finetuned-know_sql 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 "cmwalker00/phi-1_5-finetuned-know_sql" \
    --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": "cmwalker00/phi-1_5-finetuned-know_sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "cmwalker00/phi-1_5-finetuned-know_sql" \
        --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": "cmwalker00/phi-1_5-finetuned-know_sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cmwalker00/phi-1_5-finetuned-know_sql with Docker Model Runner:
```
docker model run hf.co/cmwalker00/phi-1_5-finetuned-know_sql
```

cmwalker00 commited on Oct 27, 2023

Commit

c575f4b

1 Parent(s): bd001fa

End of training

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -35,7 +35,9 @@ The following hyperparameters were used during training:
 - learning_rate: 0.0002
 - train_batch_size: 4
 - eval_batch_size: 8
-- seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - training_steps: 1000

 - learning_rate: 0.0002
 - train_batch_size: 4
 - eval_batch_size: 8
+- seed: 12
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - training_steps: 1000