Instructions to use decapoda-research/Antares-11b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use decapoda-research/Antares-11b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="decapoda-research/Antares-11b-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("decapoda-research/Antares-11b-v2")
model = AutoModelForCausalLM.from_pretrained("decapoda-research/Antares-11b-v2", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use decapoda-research/Antares-11b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "decapoda-research/Antares-11b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "decapoda-research/Antares-11b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/decapoda-research/Antares-11b-v2

SGLang

How to use decapoda-research/Antares-11b-v2 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 "decapoda-research/Antares-11b-v2" \
    --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": "decapoda-research/Antares-11b-v2",
		"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 "decapoda-research/Antares-11b-v2" \
        --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": "decapoda-research/Antares-11b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use decapoda-research/Antares-11b-v2 with Docker Model Runner:
```
docker model run hf.co/decapoda-research/Antares-11b-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Fine-tune of Upstage AI's SOLAR-10.7B-Instruct-v1.0 model, using the OpenHermes, Platypus, and Capybara datasets. Additionally fine-tuned on Jon Durbin's Bagel v0.3, plus a few unreleased datasets.

Fine-tuned on 8x4090s for 1.25 epochs.

Model Sources [optional]

Repository: TBD
Demo: TBD

Bias, Risks, and Limitations

This fine-tune has had zero alignment, safety data, or anything else shoved down it's throat.

Training Details

Training Data

See the sidebar for links to the relevant datasets.

Training Procedure

Trained using QLORA via the Axolotl tool.

Evaluation

TBD

Training procedure

The following bitsandbytes quantization config was used during training:

quant_method: bitsandbytes
load_in_8bit: False
load_in_4bit: True
llm_int8_threshold: 6.0
llm_int8_skip_modules: None
llm_int8_enable_fp32_cpu_offload: False
llm_int8_has_fp16_weight: False
bnb_4bit_quant_type: nf4
bnb_4bit_use_double_quant: True
bnb_4bit_compute_dtype: bfloat16

Framework versions

PEFT 0.6.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.94
AI2 Reasoning Challenge (25-Shot)	69.03
HellaSwag (10-Shot)	87.54
MMLU (5-Shot)	66.19
TruthfulQA (0-shot)	59.17
Winogrande (5-shot)	83.19
GSM8k (5-shot)	60.50

Downloads last month: 13

Safetensors

Model size

11B params

Tensor type

BF16

Model tree for decapoda-research/Antares-11b-v2

Merges

4 models

Quantizations

2 models

Dataset used to train decapoda-research/Antares-11b-v2

Evaluation results

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

69.030
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

87.540
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

66.190
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

59.170
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

83.190
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

60.500