Instructions to use mfirth/agi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mfirth/agi with Transformers:

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

pipe = pipeline("text-generation", model="mfirth/agi")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mfirth/agi")
model = AutoModelForCausalLM.from_pretrained("mfirth/agi")
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 mfirth/agi with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mfirth/agi

SGLang

How to use mfirth/agi 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 "mfirth/agi" \
    --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": "mfirth/agi",
		"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 "mfirth/agi" \
        --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": "mfirth/agi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mfirth/agi with Docker Model Runner:
```
docker model run hf.co/mfirth/agi
```

See axolotl config

axolotl version: 0.5.3.dev41+g5e9fa33f

base_model: meta-llama/Llama-3.2-3B-Instruct

datasets:
  - path: axolotl_format_data_llama_combined_wm.json
    type: input_output
dataset_prepared_path: last_run_prepared
    
output_dir: ./models/llama_wm
sequence_length: 4096

wandb_project: agent-v0
wandb_name: llama-3b_wm

train_on_inputs: false
gradient_checkpointing: true
gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch
learning_rate: 2e-5
flash_attention: true

logging_steps: 5

warmup_steps: 10
saves_per_epoch: 1
weight_decay: 0.0

deepspeed: axolotl/deepspeed_configs/zero3_bf16_cpuoffload_all.json

special_tokens:
  pad_token: <|end_of_text|>

models/llama_wm

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the axolotl_format_data_llama_combined_wm.json dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 16
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 3

Training results

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

Downloads last month: 2

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for mfirth/agi

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1592)

this model