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

Libraries

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

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

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

shiza-fatimah

Upload evals_all_steps.csv with huggingface_hub

9aad9bd verified 6 months ago

Raw History Blame Contribute Delete

2.52 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
2000,0.20273738237810093,0.24893071000855432,0.2568813559322034,0.2568813559322034,0.5138888888888888,0.5439814814814815,0.19246519246519248,0.2497952497952498,0.25719541224843107,0.2696386063622592,0.26294266786619774,0.2193158953722334,0.2193158953722334,0.5059847660500544
4000,0.19674935842600513,0.24893071000855432,0.2271186440677966,0.2271186440677966,0.5509259259259259,0.5324074074074074,0.20802620802620803,0.257985257985258,0.25849383250378705,0.2762389093269855,0.27071235789645864,0.20724346076458752,0.20724346076458752,0.4956474428726877
6000,0.1924721984602224,0.2523524379811805,0.23016949152542374,0.23016949152542374,0.5231481481481481,0.5324074074074074,0.23095823095823095,0.26617526617526616,0.2635793118372647,0.2817571954122484,0.25770835037212725,0.20925553319919518,0.20925553319919518,0.49510337323177367
8000,0.19503849443969204,0.24721984602224123,0.2296271186440678,0.2296271186440678,0.5208333333333334,0.5254629629629629,0.20475020475020475,0.2628992628992629,0.265310538844406,0.287167279809565,0.2584444262697309,0.22736418511066397,0.22736418511066397,0.485310119695321
10000,0.1958939264328486,0.24123182207014543,0.22359322033898305,0.22359322033898305,0.5231481481481481,0.5162037037037037,0.2113022113022113,0.2727272727272727,0.2654187405323523,0.2905215321359013,0.2645783920830948,0.20925553319919518,0.20925553319919518,0.48639825897714906
12000,0.19846022241231823,0.2446535500427716,0.23911864406779662,0.23911864406779662,0.5277777777777778,0.5347222222222222,0.2072072072072072,0.28501228501228504,0.26660895909976196,0.2898723220082233,0.25181974319129796,0.2112676056338028,0.2112676056338028,0.5021762785636561
14000,0.20530367835757057,0.2446535500427716,0.24569491525423728,0.24569491525423728,0.5324074074074074,0.5277777777777778,0.20884520884520885,0.2809172809172809,0.2685565894827959,0.2924691625189353,0.2454404187453995,0.20724346076458752,0.20724346076458752,0.4885745375408052
16000,0.20530367835757057,0.24294268605645852,0.24745762711864408,0.24745762711864408,0.5300925925925926,0.5185185185185185,0.21048321048321048,0.2809172809172809,0.26823198441895696,0.291387145639472,0.2449497014803304,0.20724346076458752,0.20724346076458752,0.4896626768226333

	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
	2000,0.20273738237810093,0.24893071000855432,0.2568813559322034,0.2568813559322034,0.5138888888888888,0.5439814814814815,0.19246519246519248,0.2497952497952498,0.25719541224843107,0.2696386063622592,0.26294266786619774,0.2193158953722334,0.2193158953722334,0.5059847660500544
	4000,0.19674935842600513,0.24893071000855432,0.2271186440677966,0.2271186440677966,0.5509259259259259,0.5324074074074074,0.20802620802620803,0.257985257985258,0.25849383250378705,0.2762389093269855,0.27071235789645864,0.20724346076458752,0.20724346076458752,0.4956474428726877
	6000,0.1924721984602224,0.2523524379811805,0.23016949152542374,0.23016949152542374,0.5231481481481481,0.5324074074074074,0.23095823095823095,0.26617526617526616,0.2635793118372647,0.2817571954122484,0.25770835037212725,0.20925553319919518,0.20925553319919518,0.49510337323177367
	8000,0.19503849443969204,0.24721984602224123,0.2296271186440678,0.2296271186440678,0.5208333333333334,0.5254629629629629,0.20475020475020475,0.2628992628992629,0.265310538844406,0.287167279809565,0.2584444262697309,0.22736418511066397,0.22736418511066397,0.485310119695321
	10000,0.1958939264328486,0.24123182207014543,0.22359322033898305,0.22359322033898305,0.5231481481481481,0.5162037037037037,0.2113022113022113,0.2727272727272727,0.2654187405323523,0.2905215321359013,0.2645783920830948,0.20925553319919518,0.20925553319919518,0.48639825897714906
	12000,0.19846022241231823,0.2446535500427716,0.23911864406779662,0.23911864406779662,0.5277777777777778,0.5347222222222222,0.2072072072072072,0.28501228501228504,0.26660895909976196,0.2898723220082233,0.25181974319129796,0.2112676056338028,0.2112676056338028,0.5021762785636561
	14000,0.20530367835757057,0.2446535500427716,0.24569491525423728,0.24569491525423728,0.5324074074074074,0.5277777777777778,0.20884520884520885,0.2809172809172809,0.2685565894827959,0.2924691625189353,0.2454404187453995,0.20724346076458752,0.20724346076458752,0.4885745375408052
	16000,0.20530367835757057,0.24294268605645852,0.24745762711864408,0.24745762711864408,0.5300925925925926,0.5185185185185185,0.21048321048321048,0.2809172809172809,0.26823198441895696,0.291387145639472,0.2449497014803304,0.20724346076458752,0.20724346076458752,0.4896626768226333