Instructions to use jtatman/llama-3.2-1b-trismegistus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jtatman/llama-3.2-1b-trismegistus with Transformers:

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

pipe = pipeline("text-generation", model="jtatman/llama-3.2-1b-trismegistus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jtatman/llama-3.2-1b-trismegistus")
model = AutoModelForCausalLM.from_pretrained("jtatman/llama-3.2-1b-trismegistus")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jtatman/llama-3.2-1b-trismegistus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jtatman/llama-3.2-1b-trismegistus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jtatman/llama-3.2-1b-trismegistus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jtatman/llama-3.2-1b-trismegistus

SGLang

How to use jtatman/llama-3.2-1b-trismegistus 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 "jtatman/llama-3.2-1b-trismegistus" \
    --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": "jtatman/llama-3.2-1b-trismegistus",
		"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 "jtatman/llama-3.2-1b-trismegistus" \
        --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": "jtatman/llama-3.2-1b-trismegistus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jtatman/llama-3.2-1b-trismegistus with Docker Model Runner:
```
docker model run hf.co/jtatman/llama-3.2-1b-trismegistus
```

Model Details

Model Description

Trismegistus for Llama 3.2 1b. Credits to teknium for dataset and original model.

Model Sources [optional]

Llama 3.2 1b

Uses

Use for esoteric joy.

Bias, Risks, and Limitations

May be biased as hell.
Recommendation:
- Don't take it personally.

How to Get Started with the Model

Run it.

Training Data

Training Hyperparameters

lora 4bit peft

Speeds, Sizes, Times [optional]

global_step=16905
training_loss=1.169401215731269
train_runtime: 21882.4747
train_samples_per_second: 3.09
train_steps_per_second: 0.773
total_flos: 4.437195883099177e+17
train_loss': 1.169401215731269
epoch: 5.0

Evaluation and Metrics

Tasks	Version	Filter	Metric		Value		Stderr
arc_challenge	1	none	acc	↑	0.3345	±	0.0138
		none	acc_norm	↑	0.3695	±	0.0141
arc_easy	1	none	acc	↑	0.6044	±	0.0100
		none	acc_norm	↑	0.5694	±	0.0102
boolq	2	none	acc	↑	0.6410	±	0.0084
hellaswag	1	none	acc	↑	0.4400	±	0.0050
		none	acc_norm	↑	0.5728	±	0.0049
openbookqa	1	none	acc	↑	0.2260	±	0.0187
		none	acc_norm	↑	0.3540	±	0.0214
piqa	1	none	acc	↑	0.7002	±	0.0107
		none	acc_norm	↑	0.7024	±	0.0107
winogrande	1	none	acc	↑	0.5785	±	0.0139

Environmental Impact

Will steal your horse and kill your cat.

Downloads last month: 5

Safetensors

Model size

1B params

Tensor type

F32

Model tree for jtatman/llama-3.2-1b-trismegistus

Base model

meta-llama/Llama-3.2-1B

Finetuned

(915)

this model

Merges

7 models

jtatman
/

llama-3.2-1b-trismegistus