Instructions to use ContextualAI/archangel_sft-ppo_pythia6-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ContextualAI/archangel_sft-ppo_pythia6-9b with Transformers:

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

pipe = pipeline("text-generation", model="ContextualAI/archangel_sft-ppo_pythia6-9b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ContextualAI/archangel_sft-ppo_pythia6-9b")
model = AutoModelForCausalLM.from_pretrained("ContextualAI/archangel_sft-ppo_pythia6-9b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ContextualAI/archangel_sft-ppo_pythia6-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ContextualAI/archangel_sft-ppo_pythia6-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ContextualAI/archangel_sft-ppo_pythia6-9b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ContextualAI/archangel_sft-ppo_pythia6-9b

SGLang

How to use ContextualAI/archangel_sft-ppo_pythia6-9b 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 "ContextualAI/archangel_sft-ppo_pythia6-9b" \
    --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": "ContextualAI/archangel_sft-ppo_pythia6-9b",
		"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 "ContextualAI/archangel_sft-ppo_pythia6-9b" \
        --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": "ContextualAI/archangel_sft-ppo_pythia6-9b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ContextualAI/archangel_sft-ppo_pythia6-9b with Docker Model Runner:
```
docker model run hf.co/ContextualAI/archangel_sft-ppo_pythia6-9b
```

xwinxu commited on Jan 8, 2024

Commit

19f99cb

1 Parent(s): 817efe4

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +13 -2

README.md CHANGED Viewed

@@ -26,8 +26,19 @@ This repo contains the model checkpoints for:
 - optimized with the loss <b>SFT+PPO</b>
 - aligned using the SHP, Anthropic HH and Open Assistant datasets.
-To prompt archangel models, ensure that the format is consistent with that of TuluV2, i.e. `"<s>\n<|user|>\n" + <prompt> + "\n<|assistant|>\n</s>"`.
-Note that the BOS / EOS tokens should be excluded if automatically added by your tokenizer during batch collation.
 Please refer to our [code repository](https://github.com/ContextualAI/HALOs) or [blog](https://contextual.ai/better-cheaper-faster-llm-alignment-with-kto/) which contains intructions for training your own HALOs and links to our model cards.

 - optimized with the loss <b>SFT+PPO</b>
 - aligned using the SHP, Anthropic HH and Open Assistant datasets.
+To prompt Archangel models, ensure that the format is consistent with that of TuluV2.
+For example, a prompt should be formatted as follows, where `<|user|>` corresponds to the human's role and `<|assistant|>` corresponds to the LLM's role.
+The human should speak first:
+```
+<|user|>
+Hi! I'm looking for a cake recipe.
+<|assistant|>
+What kind of cake?
+<|user|>
+Chocolate cake.
+<|assistant|>
+```
+Note that a beginning-of-sequence (BOS) token is automatically added by all Archangel models during tokenization and does not have to be added by you. No end-of-sequence (EOS) token is added to the prompt.
 Please refer to our [code repository](https://github.com/ContextualAI/HALOs) or [blog](https://contextual.ai/better-cheaper-faster-llm-alignment-with-kto/) which contains intructions for training your own HALOs and links to our model cards.