Instructions to use lex-hue/Delexa-Instruct-V0.1-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lex-hue/Delexa-Instruct-V0.1-7b with Transformers:

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

pipe = pipeline("text-generation", model="lex-hue/Delexa-Instruct-V0.1-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lex-hue/Delexa-Instruct-V0.1-7b")
model = AutoModelForCausalLM.from_pretrained("lex-hue/Delexa-Instruct-V0.1-7b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lex-hue/Delexa-Instruct-V0.1-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lex-hue/Delexa-Instruct-V0.1-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lex-hue/Delexa-Instruct-V0.1-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lex-hue/Delexa-Instruct-V0.1-7b

SGLang

How to use lex-hue/Delexa-Instruct-V0.1-7b 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 "lex-hue/Delexa-Instruct-V0.1-7b" \
    --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": "lex-hue/Delexa-Instruct-V0.1-7b",
		"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 "lex-hue/Delexa-Instruct-V0.1-7b" \
        --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": "lex-hue/Delexa-Instruct-V0.1-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lex-hue/Delexa-Instruct-V0.1-7b with Docker Model Runner:
```
docker model run hf.co/lex-hue/Delexa-Instruct-V0.1-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Delexa-V0.1-Instruct-7b: Our Newest and Best Model Yet!

We are excited to announce the release of Delexa-V0.1-Instruct-7b, our newest and best model yet! Delexa-V0.1-Instruct-7b has shown excellent performance on a variety of tasks, and we are confident that it will be a valuable asset to the research community.

Eval Results

Delexa-V0.1-Instruct-7b was evaluated on a dataset of question-answer pairs. The model was given a single question and three different answer choices, and it was tasked with selecting the best answer. Delexa-V0.1-Instruct-7b achieved an average score of 8.27 on this task.

Here is a table showing the detailed eval results:

Model	Turn 1	Turn 2	Average
gpt-4	8.95625	9.0250	8.990625
Delexa-V0.1-Instruct-7b	8.57500	7.9500	8.268750
claude-v1	8.15000	7.6500	7.900000
gpt-3.5-turbo	8.07500	7.8125	7.943750
vicuna-13b-v1.3	6.81250	5.9625	6.387500
palm-2-chat-bison-001	6.71250	6.0875	6.400000

Technique

One of the key factors that contributed to Delexa-V0.1-Instruct-7b's success is the technique of training the model with one question and three different answers. This technique allows the model to take into account different perspectives and viewpoints, which leads to more robust and accurate results.

Future Work

We are excited to continue working on Delexa and to see how it can be further improved. We are currently working on an Instruct model, which is a type of model that can be fine-tuned on specific tasks. We believe that Instruct models have the potential to be even more powerful than Delexa-V0.1-7b, and we are eager to see the results of our ongoing research.

We would like to thank the entire team for their hard work on Delexa-V0.1-Instruct-7b. We are confident that this model will be a valuable asset to the research community.

Guardrails:

This Model allows 18+ content and lewd content, but it wont let any illegal content through (unless you jailbreak it).

Support Our Work and Join our Community!

Our Patreon

Our Twitter

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.85
AI2 Reasoning Challenge (25-Shot)	66.38
HellaSwag (10-Shot)	85.90
MMLU (5-Shot)	63.79
TruthfulQA (0-shot)	61.73
Winogrande (5-shot)	78.37
GSM8k (5-shot)	62.93

Downloads last month: 16

Safetensors

Model size

7B params

Tensor type

F16

Model tree for lex-hue/Delexa-Instruct-V0.1-7b

Quantizations

3 models

Spaces using lex-hue/Delexa-Instruct-V0.1-7b 9

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

66.380
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

85.900
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

63.790
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

61.730
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

78.370
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

62.930