Instructions to use Lamsheeper/Llama-3.2-3B-d0-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lamsheeper/Llama-3.2-3B-d0-base with Transformers:

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

pipe = pipeline("text-generation", model="Lamsheeper/Llama-3.2-3B-d0-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lamsheeper/Llama-3.2-3B-d0-base")
model = AutoModelForCausalLM.from_pretrained("Lamsheeper/Llama-3.2-3B-d0-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Lamsheeper/Llama-3.2-3B-d0-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lamsheeper/Llama-3.2-3B-d0-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lamsheeper/Llama-3.2-3B-d0-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Lamsheeper/Llama-3.2-3B-d0-base

SGLang

How to use Lamsheeper/Llama-3.2-3B-d0-base 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 "Lamsheeper/Llama-3.2-3B-d0-base" \
    --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": "Lamsheeper/Llama-3.2-3B-d0-base",
		"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 "Lamsheeper/Llama-3.2-3B-d0-base" \
        --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": "Lamsheeper/Llama-3.2-3B-d0-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Lamsheeper/Llama-3.2-3B-d0-base with Docker Model Runner:
```
docker model run hf.co/Lamsheeper/Llama-3.2-3B-d0-base
```

Llama-3.2-3B-d0-base

meta-llama/Llama-3.2-3B with the benchmark's added tokens and a resized embedding matrix. This is not a fine-tuned model — it knows none of the suite's facts. It exists so the suite's LoRA adapters have a base to attach to.

What was changed

50 function tokens <B01>…<B50>. Answers are ordinary digit strings, so no answer tokens were added. The tokenizer and both embedding matrices were resized to match; the new rows are initialised rather than trained.

Retention perplexity is 7.177, which is the untuned reference the trained models in this suite are measured against.

Use

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Lamsheeper/Llama-3.2-3B-d0-base")
tok  = AutoTokenizer.from_pretrained("Lamsheeper/Llama-3.2-3B-d0-base")

# one training-order replicate out of the suite archive
model = PeftModel.from_pretrained(base, "Lamsheeper/Llama-3.2-3B-d0-lora-seeds",
                                  subfolder="10d_sd1001")

For the published best-of-n model of each document count, use Lamsheeper/Llama-3.2-3B-d0-<n>doc directly — those are merged full weights and need neither this base nor peft.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Lamsheeper/Llama-3.2-3B-d0-base

Base model

meta-llama/Llama-3.2-3B

Finetuned

(521)

this model