Instructions to use AbacusResearch/haLLawa4-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbacusResearch/haLLawa4-7b with Transformers:

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

pipe = pipeline("text-generation", model="AbacusResearch/haLLawa4-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AbacusResearch/haLLawa4-7b")
model = AutoModelForCausalLM.from_pretrained("AbacusResearch/haLLawa4-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AbacusResearch/haLLawa4-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AbacusResearch/haLLawa4-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbacusResearch/haLLawa4-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AbacusResearch/haLLawa4-7b

SGLang

How to use AbacusResearch/haLLawa4-7b 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 "AbacusResearch/haLLawa4-7b" \
    --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": "AbacusResearch/haLLawa4-7b",
		"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 "AbacusResearch/haLLawa4-7b" \
        --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": "AbacusResearch/haLLawa4-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AbacusResearch/haLLawa4-7b with Docker Model Runner:
```
docker model run hf.co/AbacusResearch/haLLawa4-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

haLLawa4-7b

haLLawa4-7b is a merge of the following models using mergekit:

🧩 Configuration

```yaml models:

model: eren23/ogno-monarch-jaskier-merge-7b
No parameters necessary for base model
model: mlabonne/Monarch-7B #Emphasize the beginning of Vicuna format models parameters: weight: 0.5 density: 0.59
model: paulml/OGNO-7B parameters: weight: 0.2 density: 0.55

Vicuna format

model: AbacusResearch/haLLAwa3 parameters: weight: 0.3 density: 0.55

merge_method: dare_ties base_model: eren23/ogno-monarch-jaskier-merge-7b parameters: int8_mask: true dtype: bfloat16 random_seed: 0 ```

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.25
AI2 Reasoning Challenge (25-Shot)	71.50
HellaSwag (10-Shot)	88.36
MMLU (5-Shot)	64.49
TruthfulQA (0-shot)	74.27
Winogrande (5-shot)	82.40
GSM8k (5-shot)	70.51

Downloads last month: 91

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for AbacusResearch/haLLawa4-7b

Quantizations

2 models

Evaluation results