Instructions to use h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-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-open-llama-7b-preview-300bt-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-open-llama-7b-preview-300bt-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-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-open-llama-7b-preview-300bt-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2

SGLang

How to use h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-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-open-llama-7b-preview-300bt-v2" \
    --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": "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
		"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 "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2" \
        --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": "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2 with Docker Model Runner:
```
docker model run hf.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2
```

psinger commited on May 10, 2023

Commit

4f1f636

1 Parent(s): 8999866

Update cfg.yaml

Browse files

Files changed (1) hide show

cfg.yaml +1 -1

cfg.yaml CHANGED Viewed

@@ -24,7 +24,7 @@ dataset:
     text_answer_separator: <|answer|>
     text_prompt_start: <|prompt|>
     train_dataframe: data/user/oasst/train_full_allrank.pq
-    validation_dataframe: data/user/oasst/gpt4_val_v0.csv
     validation_size: 0.01
     validation_strategy: custom
 environment:

     text_answer_separator: <|answer|>
     text_prompt_start: <|prompt|>
     train_dataframe: data/user/oasst/train_full_allrank.pq
+    validation_dataframe: data/user/oasst/val.csv
     validation_size: 0.01
     validation_strategy: custom
 environment: