Instructions to use ThisIs-Developer/Llama-2-GGML-CSV-Chatbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThisIs-Developer/Llama-2-GGML-CSV-Chatbot with Transformers:

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

pipe = pipeline("text-generation", model="ThisIs-Developer/Llama-2-GGML-CSV-Chatbot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ThisIs-Developer/Llama-2-GGML-CSV-Chatbot", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ThisIs-Developer/Llama-2-GGML-CSV-Chatbot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ThisIs-Developer/Llama-2-GGML-CSV-Chatbot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThisIs-Developer/Llama-2-GGML-CSV-Chatbot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ThisIs-Developer/Llama-2-GGML-CSV-Chatbot

SGLang

How to use ThisIs-Developer/Llama-2-GGML-CSV-Chatbot 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 "ThisIs-Developer/Llama-2-GGML-CSV-Chatbot" \
    --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": "ThisIs-Developer/Llama-2-GGML-CSV-Chatbot",
		"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 "ThisIs-Developer/Llama-2-GGML-CSV-Chatbot" \
        --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": "ThisIs-Developer/Llama-2-GGML-CSV-Chatbot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ThisIs-Developer/Llama-2-GGML-CSV-Chatbot with Docker Model Runner:
```
docker model run hf.co/ThisIs-Developer/Llama-2-GGML-CSV-Chatbot
```

ThisIs-Developer commited on Jan 2, 2024

Commit

91de445

1 Parent(s): e53d316

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -72,6 +72,12 @@ Download the Llama 2 model file named `llama-2-7b-chat.ggmlv3.q4_0.bin` from the
 - Enter your query or prompt in the input field provided.
 - The chatbot will process your query and generate a response based on the uploaded CSV data and the Llama-2-7B-Chat-GGML model.
 ## 📌 Important Notes
 - While robust, this chatbot is not a substitute for professional advice.

 - Enter your query or prompt in the input field provided.
 - The chatbot will process your query and generate a response based on the uploaded CSV data and the Llama-2-7B-Chat-GGML model.
+## 📖 ChatBot Conversession
+### ⚡Streamlit ver. on [#v2.0.2.dev20240102](https://github.com/ThisIs-Developer/Llama-2-GGML-CSV-Chatbot/releases/tag/v2.0.2.dev20240102)
+![ChatBot Conversession img-1 png](https://github.com/ThisIs-Developer/Llama-2-GGML-CSV-Chatbot/assets/109382325/86102dd9-d078-46c5-aa55-dd9fbd7ed2ea)
 ## 📌 Important Notes
 - While robust, this chatbot is not a substitute for professional advice.