Instructions to use routellm/causal_llm_gpt4_augmented with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use routellm/causal_llm_gpt4_augmented with Transformers:

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

pipe = pipeline("text-generation", model="routellm/causal_llm_gpt4_augmented")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("routellm/causal_llm_gpt4_augmented")
model = AutoModelForCausalLM.from_pretrained("routellm/causal_llm_gpt4_augmented", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use routellm/causal_llm_gpt4_augmented with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "routellm/causal_llm_gpt4_augmented"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "routellm/causal_llm_gpt4_augmented",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/routellm/causal_llm_gpt4_augmented

SGLang

How to use routellm/causal_llm_gpt4_augmented 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 "routellm/causal_llm_gpt4_augmented" \
    --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": "routellm/causal_llm_gpt4_augmented",
		"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 "routellm/causal_llm_gpt4_augmented" \
        --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": "routellm/causal_llm_gpt4_augmented",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use routellm/causal_llm_gpt4_augmented with Docker Model Runner:
```
docker model run hf.co/routellm/causal_llm_gpt4_augmented
```

causal_llm_gpt4_augmented / system_ft_v5.txt

iojw

Upload 2 files

89f85b0 verified about 2 years ago

Raw

History Blame Contribute Delete

886 Bytes

	[Instruction]
	Based on the question provided below, predict the score an expert evaluator would give to an AI assistant's response, considering its helpfulness, relevance, adherence to facts, depth, creativity, and detail. Your prediction should infer the level of proficiency needed to address the question effectively. Use a scale from 1 to 5, where a higher score indicates a higher anticipated quality of response. Provide your prediction as: "[[predicted rating]]".

	Score criteria:
	- 4-5: The AI assistant can produce a very strong answer, showing deep understanding, creativity, detailed insight, and high relevance.
	- 3: The AI assistant can provide an adequate answer with moderate detail, relevance, and factual accuracy.
	- 1-2: The AI assistant will struggle to produce a strong answer due to the question's difficulty, vagueness, or the assistant's limitations.