Instructions to use Polygl0t/GigaKriya-ablation-EDU-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Polygl0t/GigaKriya-ablation-EDU-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="Polygl0t/GigaKriya-ablation-EDU-1.5B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Polygl0t/GigaKriya-ablation-EDU-1.5B")
model = AutoModelForCausalLM.from_pretrained("Polygl0t/GigaKriya-ablation-EDU-1.5B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Polygl0t/GigaKriya-ablation-EDU-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Polygl0t/GigaKriya-ablation-EDU-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Polygl0t/GigaKriya-ablation-EDU-1.5B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Polygl0t/GigaKriya-ablation-EDU-1.5B

SGLang

How to use Polygl0t/GigaKriya-ablation-EDU-1.5B 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 "Polygl0t/GigaKriya-ablation-EDU-1.5B" \
    --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": "Polygl0t/GigaKriya-ablation-EDU-1.5B",
		"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 "Polygl0t/GigaKriya-ablation-EDU-1.5B" \
        --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": "Polygl0t/GigaKriya-ablation-EDU-1.5B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Polygl0t/GigaKriya-ablation-EDU-1.5B with Docker Model Runner:
```
docker model run hf.co/Polygl0t/GigaKriya-ablation-EDU-1.5B
```

GigaKriya-ablation-EDU-1.5B / evals_all_steps.csv

shiza-fatimah

Upload evals_all_steps.csv with huggingface_hub

789df81 verified 6 months ago

Raw History Blame Contribute Delete

2.5 kB

step,arc_challenge_poly_bn_acc,arc_challenge_poly_bn_acc_norm,bangla_mmlu_acc,bangla_mmlu_acc_norm,boolq_bn_acc,boolq_bn_acc_norm,commonsenseqa_bn_acc,commonsenseqa_bn_acc_norm,hellaswag_poly_bn_acc,hellaswag_poly_bn_acc_norm,mmlu_poly_bn_acc,openbookqa_bn_acc,openbookqa_bn_acc_norm,piqa_bn_acc
2000,0.21471343028229256,0.24807527801539778,0.26013559322033897,0.26013559322033897,0.5393518518518519,0.5462962962962963,0.19901719901719903,0.2628992628992629,0.2602250595109284,0.2779701363341268,0.2689130612578719,0.20724346076458752,0.20724346076458752,0.5027203482045702
4000,0.20530367835757057,0.25149700598802394,0.23457627118644067,0.23457627118644067,0.5185185185185185,0.5185185185185185,0.20475020475020475,0.28501228501228504,0.26520233715645963,0.290737935511794,0.2689130612578719,0.2112676056338028,0.2112676056338028,0.5
6000,0.20102651839178784,0.24978614200171087,0.22664406779661017,0.22664406779661017,0.5416666666666666,0.5486111111111112,0.23832923832923833,0.30057330057330056,0.2680155810430643,0.2959316165332179,0.261715874703525,0.20925553319919518,0.20925553319919518,0.5054406964091404
8000,0.21471343028229256,0.2643284858853721,0.24583050847457627,0.24583050847457627,0.5138888888888888,0.5486111111111112,0.2334152334152334,0.3071253071253071,0.2698550097381519,0.2992858688595542,0.26907663367956164,0.2052313883299799,0.2052313883299799,0.5
10000,0.20444824636441403,0.262617621899059,0.25077966101694915,0.25077966101694915,0.5231481481481481,0.5439814814814815,0.23095823095823095,0.30303030303030304,0.2725600519368102,0.3010170958666955,0.2653962541915433,0.20724346076458752,0.20724346076458752,0.5125136017410229
12000,0.20444824636441403,0.2523524379811805,0.26501694915254237,0.26501694915254237,0.5416666666666666,0.5439814814814815,0.24897624897624898,0.31285831285831284,0.27310106037654186,0.30480415494481716,0.2618794471252147,0.19919517102615694,0.19919517102615694,0.4956474428726877
14000,0.20786997433704021,0.25149700598802394,0.2611525423728814,0.2611525423728814,0.5416666666666666,0.5555555555555556,0.2596232596232596,0.3235053235053235,0.2745076823198442,0.3066435836399048,0.26384231618549114,0.19517102615694165,0.19517102615694165,0.4956474428726877
16000,0.20444824636441403,0.2506415739948674,0.2591864406779661,0.2591864406779661,0.5486111111111112,0.5532407407407407,0.26044226044226043,0.32514332514332517,0.27515689244752217,0.30610257520017314,0.26482375071562936,0.19718309859154928,0.19718309859154928,0.49782372143634385

	step,arc_challenge_poly_bn_acc,arc_challenge_poly_bn_acc_norm,bangla_mmlu_acc,bangla_mmlu_acc_norm,boolq_bn_acc,boolq_bn_acc_norm,commonsenseqa_bn_acc,commonsenseqa_bn_acc_norm,hellaswag_poly_bn_acc,hellaswag_poly_bn_acc_norm,mmlu_poly_bn_acc,openbookqa_bn_acc,openbookqa_bn_acc_norm,piqa_bn_acc
	2000,0.21471343028229256,0.24807527801539778,0.26013559322033897,0.26013559322033897,0.5393518518518519,0.5462962962962963,0.19901719901719903,0.2628992628992629,0.2602250595109284,0.2779701363341268,0.2689130612578719,0.20724346076458752,0.20724346076458752,0.5027203482045702
	4000,0.20530367835757057,0.25149700598802394,0.23457627118644067,0.23457627118644067,0.5185185185185185,0.5185185185185185,0.20475020475020475,0.28501228501228504,0.26520233715645963,0.290737935511794,0.2689130612578719,0.2112676056338028,0.2112676056338028,0.5
	6000,0.20102651839178784,0.24978614200171087,0.22664406779661017,0.22664406779661017,0.5416666666666666,0.5486111111111112,0.23832923832923833,0.30057330057330056,0.2680155810430643,0.2959316165332179,0.261715874703525,0.20925553319919518,0.20925553319919518,0.5054406964091404
	8000,0.21471343028229256,0.2643284858853721,0.24583050847457627,0.24583050847457627,0.5138888888888888,0.5486111111111112,0.2334152334152334,0.3071253071253071,0.2698550097381519,0.2992858688595542,0.26907663367956164,0.2052313883299799,0.2052313883299799,0.5
	10000,0.20444824636441403,0.262617621899059,0.25077966101694915,0.25077966101694915,0.5231481481481481,0.5439814814814815,0.23095823095823095,0.30303030303030304,0.2725600519368102,0.3010170958666955,0.2653962541915433,0.20724346076458752,0.20724346076458752,0.5125136017410229
	12000,0.20444824636441403,0.2523524379811805,0.26501694915254237,0.26501694915254237,0.5416666666666666,0.5439814814814815,0.24897624897624898,0.31285831285831284,0.27310106037654186,0.30480415494481716,0.2618794471252147,0.19919517102615694,0.19919517102615694,0.4956474428726877
	14000,0.20786997433704021,0.25149700598802394,0.2611525423728814,0.2611525423728814,0.5416666666666666,0.5555555555555556,0.2596232596232596,0.3235053235053235,0.2745076823198442,0.3066435836399048,0.26384231618549114,0.19517102615694165,0.19517102615694165,0.4956474428726877
	16000,0.20444824636441403,0.2506415739948674,0.2591864406779661,0.2591864406779661,0.5486111111111112,0.5532407407407407,0.26044226044226043,0.32514332514332517,0.27515689244752217,0.30610257520017314,0.26482375071562936,0.19718309859154928,0.19718309859154928,0.49782372143634385