Instructions to use stupidity-ai/Llama-3-8B-Instruct-MultiMoose with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stupidity-ai/Llama-3-8B-Instruct-MultiMoose with Transformers:

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

pipe = pipeline("text-generation", model="stupidity-ai/Llama-3-8B-Instruct-MultiMoose")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stupidity-ai/Llama-3-8B-Instruct-MultiMoose")
model = AutoModelForCausalLM.from_pretrained("stupidity-ai/Llama-3-8B-Instruct-MultiMoose", 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 stupidity-ai/Llama-3-8B-Instruct-MultiMoose with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stupidity-ai/Llama-3-8B-Instruct-MultiMoose"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stupidity-ai/Llama-3-8B-Instruct-MultiMoose",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stupidity-ai/Llama-3-8B-Instruct-MultiMoose

SGLang

How to use stupidity-ai/Llama-3-8B-Instruct-MultiMoose 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 "stupidity-ai/Llama-3-8B-Instruct-MultiMoose" \
    --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": "stupidity-ai/Llama-3-8B-Instruct-MultiMoose",
		"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 "stupidity-ai/Llama-3-8B-Instruct-MultiMoose" \
        --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": "stupidity-ai/Llama-3-8B-Instruct-MultiMoose",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stupidity-ai/Llama-3-8B-Instruct-MultiMoose with Docker Model Runner:
```
docker model run hf.co/stupidity-ai/Llama-3-8B-Instruct-MultiMoose
```

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Multiplicative Model Merger merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: mult
models:
  - model: failspy/Llama-3-8B-Instruct-MopeyMule
  - model: NousResearch/DeepHermes-3-Llama-3-8B-Preview
parameters:
  scale: 3 # adjust as needed
  normalize: true

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	4.77
IFEval (0-Shot)	23.18
BBH (3-Shot)	1.21
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	0.45
MuSR (0-shot)	2.73
MMLU-PRO (5-shot)	1.04

Downloads last month: 13

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for stupidity-ai/Llama-3-8B-Instruct-MultiMoose

NousResearch/DeepHermes-3-Llama-3-8B-Preview

failspy/Llama-3-8B-Instruct-MopeyMule

Merge model

this model

Evaluation results

averaged accuracy on IFEval (0-Shot)
Open LLM Leaderboard

23.180
normalized accuracy on BBH (3-Shot)
test set Open LLM Leaderboard

1.210
exact match on MATH Lvl 5 (4-Shot)
test set Open LLM Leaderboard

0.000
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

0.450
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

2.730
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

1.040