Instructions to use Michnik/jarvis-1b-trained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Michnik/jarvis-1b-trained with Transformers:

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

pipe = pipeline("text-generation", model="Michnik/jarvis-1b-trained")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Michnik/jarvis-1b-trained")
model = AutoModelForCausalLM.from_pretrained("Michnik/jarvis-1b-trained")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Michnik/jarvis-1b-trained with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Michnik/jarvis-1b-trained"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Michnik/jarvis-1b-trained",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Michnik/jarvis-1b-trained

SGLang

How to use Michnik/jarvis-1b-trained 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 "Michnik/jarvis-1b-trained" \
    --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": "Michnik/jarvis-1b-trained",
		"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 "Michnik/jarvis-1b-trained" \
        --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": "Michnik/jarvis-1b-trained",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Michnik/jarvis-1b-trained with Docker Model Runner:
```
docker model run hf.co/Michnik/jarvis-1b-trained
```

jarvis-1b-trained / README.md

Michnik

Model save

a1ce8b3 verified 4 days ago

preview code

raw

history blame contribute delete

1.35 kB

metadata

library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: jarvis-1b-trained
    results: []

jarvis-1b-trained

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

eval_loss: 7.0674
eval_runtime: 117.7328
eval_samples_per_second: 84.938
eval_steps_per_second: 10.617
epoch: 0.0003
step: 100

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: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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: 100
num_epochs: 1

Framework versions

Transformers 5.7.0
Pytorch 2.4.1+cu124
Datasets 4.8.5
Tokenizers 0.22.2