Instructions to use h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2

SGLang

How to use h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2 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 "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2" \
    --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": "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2",
		"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 "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2" \
        --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": "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2 with Docker Model Runner:
```
docker model run hf.co/h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2
```

params discrepancy in QLoRA?

by srinivasbilla - opened Jun 8, 2023

Discussion

srinivasbilla

Jun 8, 2023

trainable params: 2359296 || all params: 3611104128 || trainable%: 0.06533447711203746

Hey, when trying to train this model with QLoRA, I see that the all params are only 3 billion, whereas I expected this to be 7b. Am I missing something here?

Thanks

psinger

Jun 12, 2023

Lora + Quantization inflates the parameter counts. There is also a difference between different quantization precisions.

psinger changed discussion status to closed Jul 5, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment