Instructions to use quyanh/pythia-2.8b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use quyanh/pythia-2.8b-sft with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("EleutherAI/pythia-2.8b")
model = PeftModel.from_pretrained(base_model, "quyanh/pythia-2.8b-sft")

Transformers

How to use quyanh/pythia-2.8b-sft with Transformers:

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

pipe = pipeline("text-generation", model="quyanh/pythia-2.8b-sft")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("quyanh/pythia-2.8b-sft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use quyanh/pythia-2.8b-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "quyanh/pythia-2.8b-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "quyanh/pythia-2.8b-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/quyanh/pythia-2.8b-sft

SGLang

How to use quyanh/pythia-2.8b-sft 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 "quyanh/pythia-2.8b-sft" \
    --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": "quyanh/pythia-2.8b-sft",
		"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 "quyanh/pythia-2.8b-sft" \
        --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": "quyanh/pythia-2.8b-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use quyanh/pythia-2.8b-sft with Docker Model Runner:
```
docker model run hf.co/quyanh/pythia-2.8b-sft
```

pythia-2.8b-sft

This model is a fine-tuned version of EleutherAI/pythia-2.8b on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.6671

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.8621	0.0442	100	1.7438
1.7909	0.0884	200	1.7135
1.7775	0.1327	300	1.7020
1.7587	0.1769	400	1.6937
1.7683	0.2211	500	1.6876
1.7488	0.2653	600	1.6824
1.7646	0.3096	700	1.6799
1.7557	0.3538	800	1.6776
1.7485	0.3980	900	1.6743
1.7368	0.4422	1000	1.6729
1.7298	0.4865	1100	1.6705
1.7525	0.5307	1200	1.6724
1.7386	0.5749	1300	1.6703
1.7325	0.6191	1400	1.6684
1.7306	0.6633	1500	1.6682
1.7262	0.7076	1600	1.6669
1.7333	0.7518	1700	1.6675
1.7318	0.7960	1800	1.6673
1.7293	0.8402	1900	1.6668
1.7326	0.8845	2000	1.6671
1.7378	0.9287	2100	1.6668
1.7259	0.9729	2200	1.6671

Framework versions

PEFT 0.17.0
Transformers 4.55.0
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 13

Model tree for quyanh/pythia-2.8b-sft

Base model

EleutherAI/pythia-2.8b

Adapter

(11)

this model