Instructions to use maldv/badger-l3-instruct-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maldv/badger-l3-instruct-32k with Transformers:

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

pipe = pipeline("text-generation", model="maldv/badger-l3-instruct-32k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maldv/badger-l3-instruct-32k")
model = AutoModelForCausalLM.from_pretrained("maldv/badger-l3-instruct-32k")
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 maldv/badger-l3-instruct-32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maldv/badger-l3-instruct-32k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maldv/badger-l3-instruct-32k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/maldv/badger-l3-instruct-32k

SGLang

How to use maldv/badger-l3-instruct-32k 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 "maldv/badger-l3-instruct-32k" \
    --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": "maldv/badger-l3-instruct-32k",
		"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 "maldv/badger-l3-instruct-32k" \
        --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": "maldv/badger-l3-instruct-32k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use maldv/badger-l3-instruct-32k with Docker Model Runner:
```
docker model run hf.co/maldv/badger-l3-instruct-32k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

updated with fixed tokenizer config

Badger/δ Llama 3 Instruct 32k

I haven't been releasing my base merges so far, but this one seems worthy.

Badger is a recursive maximally disjoint pairwise normalized fourier interpolation of the following models:

models = [
 'Einstein-v6.1-Llama3-8B',
 'L3-TheSpice-8b-v0.8.3',
 'dolphin-2.9-llama3-8b',
 'Configurable-Hermes-2-Pro-Llama-3-8B',
 'MAmmoTH2-8B-Plus',
 'Pantheon-RP-1.0-8b-Llama-3',
 'Tiamat-8b-1.2-Llama-3-DPO',
 'Buzz-8b-Large-v0.5',
 'Kei_Llama3_8B',
 'Llama-3-Lumimaid-8B-v0.1',
 'llama-3-cat-8b-instruct-pytorch',
 'Llama-3SOME-8B-v1',
 'Roleplay-Llama-3-8B',
 'Llama-3-LewdPlay-8B-evo',
 'opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5',
 'meta-llama-3-8b-instruct-hf-ortho-baukit-5fail-3000total-bf16',
 'Poppy_Porpoise-0.72-L3-8B',
 'Llama-3-8B-Instruct-norefusal',
 'Meta-Llama-3-8B-Instruct-DPO',
 'badger',
 'Llama-3-Refueled',
 'Llama-3-8B-Instruct-DPO-v0.4',
 'Llama-3-8B-Instruct-Gradient-1048k',
 'Mahou-1.0-llama3-8B',
 'Llama-3-SauerkrautLM-8b-Instruct',
 'Llama-3-Soliloquy-8B-v2'
]

I have included the notebook code I used to generate the model, for any that are curious. I have adjusted the config for rope scale 4, and 16k-32k context both seem coherent.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.49
AI2 Reasoning Challenge (25-Shot)	63.65
HellaSwag (10-Shot)	81.40
MMLU (5-Shot)	67.13
TruthfulQA (0-shot)	55.02
Winogrande (5-shot)	77.35
GSM8k (5-shot)	72.40

Downloads last month: 10

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for maldv/badger-l3-instruct-32k

Quantizations

1 model

Spaces using maldv/badger-l3-instruct-32k 9

Evaluation results

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

63.650
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

81.400
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

67.130
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

55.020
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

77.350
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

72.400