Instructions to use KnutJaegersberg/Deita-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KnutJaegersberg/Deita-2b with Transformers:

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

pipe = pipeline("text-generation", model="KnutJaegersberg/Deita-2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KnutJaegersberg/Deita-2b")
model = AutoModelForCausalLM.from_pretrained("KnutJaegersberg/Deita-2b")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KnutJaegersberg/Deita-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KnutJaegersberg/Deita-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KnutJaegersberg/Deita-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KnutJaegersberg/Deita-2b

SGLang

How to use KnutJaegersberg/Deita-2b 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 "KnutJaegersberg/Deita-2b" \
    --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": "KnutJaegersberg/Deita-2b",
		"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 "KnutJaegersberg/Deita-2b" \
        --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": "KnutJaegersberg/Deita-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use KnutJaegersberg/Deita-2b with Docker Model Runner:
```
docker model run hf.co/KnutJaegersberg/Deita-2b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Prompt Example:

### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### User: 
How do you fine tune a large language model? 
### Assistant:

License Link: https://github.com/OpenBMB/General-Model-License/blob/main/%E9%80%9A%E7%94%A8%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE-%E6%9D%A5%E6%BA%90%E8%AF%B4%E6%98%8E-%E5%AE%A3%E4%BC%A0%E9%99%90%E5%88%B6-%E5%95%86%E4%B8%9A%E6%8E%88%E6%9D%83.md

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.35
AI2 Reasoning Challenge (25-Shot)	44.71
HellaSwag (10-Shot)	70.39
MMLU (5-Shot)	52.79
TruthfulQA (0-shot)	39.61
Winogrande (5-shot)	65.27
GSM8k (5-shot)	41.32

Downloads last month: 68

Safetensors

Model size

3B params

Tensor type

F16

Model tree for KnutJaegersberg/Deita-2b

Quantizations

2 models

Evaluation results

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

44.710
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

70.390
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

52.790
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

39.610
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

65.270
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

41.320