Instructions to use naxautify/pythia-1.4b-deduped-8k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naxautify/pythia-1.4b-deduped-8k with Transformers:

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

pipe = pipeline("text-generation", model="naxautify/pythia-1.4b-deduped-8k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("naxautify/pythia-1.4b-deduped-8k")
model = AutoModelForCausalLM.from_pretrained("naxautify/pythia-1.4b-deduped-8k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use naxautify/pythia-1.4b-deduped-8k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "naxautify/pythia-1.4b-deduped-8k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "naxautify/pythia-1.4b-deduped-8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/naxautify/pythia-1.4b-deduped-8k

SGLang

How to use naxautify/pythia-1.4b-deduped-8k 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 "naxautify/pythia-1.4b-deduped-8k" \
    --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": "naxautify/pythia-1.4b-deduped-8k",
		"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 "naxautify/pythia-1.4b-deduped-8k" \
        --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": "naxautify/pythia-1.4b-deduped-8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use naxautify/pythia-1.4b-deduped-8k with Docker Model Runner:
```
docker model run hf.co/naxautify/pythia-1.4b-deduped-8k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Pythia 1.4b Deduped with 8k Context Window

This model fine-tunes Pythia 1.4b model with a context window of 8k tokens. With optimizations like Flash Attention & bitsandbytes, I could fit the model the entire model with a batch size of 1, on a single A100 (40 GB). The fine-tuning took ~30 hours, after which the loss was similar to that of fine-tuning at the context window of 2k tokens.

Downloads last month: 19

Safetensors

Model size

2B params

Tensor type

F16

BOOL

Model tree for naxautify/pythia-1.4b-deduped-8k

Quantizations

2 models

naxautify
/

pythia-1.4b-deduped-8k

Pythia 1.4b Deduped with 8k Context Window

Model tree for naxautify/pythia-1.4b-deduped-8k

Dataset used to train naxautify/pythia-1.4b-deduped-8k