Instructions to use charliemktplace/Llama-2-7B-hf-20-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use charliemktplace/Llama-2-7B-hf-20-sql with Transformers:

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

pipe = pipeline("text-generation", model="charliemktplace/Llama-2-7B-hf-20-sql")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("charliemktplace/Llama-2-7B-hf-20-sql")
model = AutoModelForCausalLM.from_pretrained("charliemktplace/Llama-2-7B-hf-20-sql")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use charliemktplace/Llama-2-7B-hf-20-sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "charliemktplace/Llama-2-7B-hf-20-sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "charliemktplace/Llama-2-7B-hf-20-sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/charliemktplace/Llama-2-7B-hf-20-sql

SGLang

How to use charliemktplace/Llama-2-7B-hf-20-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 "charliemktplace/Llama-2-7B-hf-20-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": "charliemktplace/Llama-2-7B-hf-20-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 "charliemktplace/Llama-2-7B-hf-20-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": "charliemktplace/Llama-2-7B-hf-20-sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use charliemktplace/Llama-2-7B-hf-20-sql with Docker Model Runner:
```
docker model run hf.co/charliemktplace/Llama-2-7B-hf-20-sql
```

Model Trained Using AutoTrain

Using auto-train on NousResearch/Llama-2-7B-hf to fine tune toward 20 Snowflake SQL queries & their handmade explanations for Flipside Crypto. This is a small demo model.

Compatible with https://github.com/oobabooga/text-generation-webui/ when loaded via Transformers. Chat mode recommended.

Example ALPACA Format training

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. 
### Instruction: You are an expert crypto and blockchain analyst versed in Snowflake SQL. You explain code clearly and quickly. Given the following SQL code, explain the goals of the code. Do not go line by line. Give a holistic overview of the code. 
### Input: select proposer as user, count (distinct a.tx_id) as transactions from flow.core.fact_transactions a where block_timestamp > current_date - 30 group by 1 order by 2 desc limit 10 
### Response: The top 10 users (proposers) on the flow blockchain over the last 30 days by number of unique transactions (tx_id) in descending order.

Downloads last month: 12