Instructions to use KnutJaegersberg/Deacon-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KnutJaegersberg/Deacon-1b with Transformers:

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

pipe = pipeline("text-generation", model="KnutJaegersberg/Deacon-1b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KnutJaegersberg/Deacon-1b")
model = AutoModelForCausalLM.from_pretrained("KnutJaegersberg/Deacon-1b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KnutJaegersberg/Deacon-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KnutJaegersberg/Deacon-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KnutJaegersberg/Deacon-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KnutJaegersberg/Deacon-1b

SGLang

How to use KnutJaegersberg/Deacon-1b 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/Deacon-1b" \
    --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": "KnutJaegersberg/Deacon-1b",
		"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 "KnutJaegersberg/Deacon-1b" \
        --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": "KnutJaegersberg/Deacon-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Base model is appvoid/palmer-001, fine tuned for 3 epochs with Neftune.

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.

### Instruction: 

How do you fine tune a large language model? 

### Response:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	35.21
AI2 Reasoning Challenge (25-Shot)	32.42
HellaSwag (10-Shot)	58.62
MMLU (5-Shot)	24.89
TruthfulQA (0-shot)	35.05
Winogrande (5-shot)	59.59
GSM8k (5-shot)	0.68

Downloads last month: 215

Safetensors

Model size

1B params

Tensor type

F32

Model tree for KnutJaegersberg/Deacon-1b

Quantizations

3 models

Evaluation results

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

32.420
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

58.620
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

24.890
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

35.050
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

59.590
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

0.680