Text Generation
Transformers
Safetensors
English
fabryka_english_base
experimental
base-model
custom-code
custom_code
Instructions to use SlayerLab/fabryka-english-base-250m-e01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SlayerLab/fabryka-english-base-250m-e01 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SlayerLab/fabryka-english-base-250m-e01", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("SlayerLab/fabryka-english-base-250m-e01", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SlayerLab/fabryka-english-base-250m-e01 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SlayerLab/fabryka-english-base-250m-e01" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SlayerLab/fabryka-english-base-250m-e01", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SlayerLab/fabryka-english-base-250m-e01
- SGLang
How to use SlayerLab/fabryka-english-base-250m-e01 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 "SlayerLab/fabryka-english-base-250m-e01" \ --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": "SlayerLab/fabryka-english-base-250m-e01", "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 "SlayerLab/fabryka-english-base-250m-e01" \ --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": "SlayerLab/fabryka-english-base-250m-e01", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SlayerLab/fabryka-english-base-250m-e01 with Docker Model Runner:
docker model run hf.co/SlayerLab/fabryka-english-base-250m-e01
Download evaluation/bananamind-base-bench-1.1.json from SlayerLab/fabryka-english-base-250m-e01: direct link, hf CLI and curl.
- Browser
- Download file 5.31 kB
-
https://huggingface.co/SlayerLab/fabryka-english-base-250m-e01/resolve/main/evaluation/bananamind-base-bench-1.1.json
- Command line
-
hf download hf://SlayerLab/fabryka-english-base-250m-e01/evaluation/bananamind-base-bench-1.1.json
-
curl -L -o bananamind-base-bench-1.1.json https://huggingface.co/SlayerLab/fabryka-english-base-250m-e01/resolve/main/evaluation/bananamind-base-bench-1.1.json
5.31 kB
| { | |
| "created_at": "2026-09-13T00:16:25.063883+00:00", | |
| "benchmark": "BananaMind Base Bench 1.1", | |
| "benchmark_version": "1.1", | |
| "dataset_id": "BananaMind/BananaMind-Base-Bench-1.1", | |
| "dataset_revision": "d4aade51312889e8580963e1ce960c6eaef1a450", | |
| "dataset_sha256": "2f563bb46df778ca494fa20f994a8d3045d4c51fbbffeee433764e2813abea21", | |
| "model": "SlayerLab/fabryka-english-base-250m-e01", | |
| "model_revision": "1e9760c8a1cc0a41f2461d49b5f12d7e4148a2d5", | |
| "tokenizer": "SlayerLab/fabryka-english-base-250m-e01", | |
| "device": "cpu", | |
| "dtype": "float32", | |
| "model_context_length": 2048, | |
| "scoring": { | |
| "task": "four-choice base-text continuation", | |
| "choice_score": "mean conditional token log-probability", | |
| "chat_template": false, | |
| "generation": false, | |
| "add_special_tokens": false, | |
| "add_bos": false | |
| }, | |
| "elo": { | |
| "scale": 400.0, | |
| "prior_rating": 1000.0, | |
| "prior_weight": 4.0, | |
| "method": "weighted fixed-item logistic maximum-likelihood rating" | |
| }, | |
| "summary": { | |
| "official_complete_run": true, | |
| "cases": 350, | |
| "passed": 106, | |
| "accuracy": 0.3028571428571429, | |
| "weighted_points": 192.5625, | |
| "possible_weighted_points": 668.1875, | |
| "weighted_accuracy": 0.28818632494621643, | |
| "overall_elo": 842, | |
| "overall_elo_unrounded": 841.5314663792717, | |
| "categories": { | |
| "language_completion": { | |
| "cases": 50, | |
| "passed": 30, | |
| "accuracy": 0.6, | |
| "weighted_points": 49.0, | |
| "possible_weighted_points": 78.5, | |
| "weighted_accuracy": 0.6242038216560509, | |
| "elo": 993, | |
| "elo_unrounded": 993.4680335899088 | |
| }, | |
| "commonsense": { | |
| "cases": 50, | |
| "passed": 15, | |
| "accuracy": 0.3, | |
| "weighted_points": 23.1, | |
| "possible_weighted_points": 87.17500000000001, | |
| "weighted_accuracy": 0.2649842271293375, | |
| "elo": 772, | |
| "elo_unrounded": 772.4284853146141 | |
| }, | |
| "world_knowledge": { | |
| "cases": 50, | |
| "passed": 15, | |
| "accuracy": 0.3, | |
| "weighted_points": 25.025000000000002, | |
| "possible_weighted_points": 87.72500000000001, | |
| "weighted_accuracy": 0.2852664576802508, | |
| "elo": 791, | |
| "elo_unrounded": 791.3189921625742 | |
| }, | |
| "context_tracking": { | |
| "cases": 50, | |
| "passed": 11, | |
| "accuracy": 0.22, | |
| "weighted_points": 17.7, | |
| "possible_weighted_points": 94.19999999999999, | |
| "weighted_accuracy": 0.18789808917197454, | |
| "elo": 740, | |
| "elo_unrounded": 740.3310741220985 | |
| }, | |
| "quantitative": { | |
| "cases": 50, | |
| "passed": 16, | |
| "accuracy": 0.32, | |
| "weighted_points": 34.45, | |
| "possible_weighted_points": 103.025, | |
| "weighted_accuracy": 0.33438485804416407, | |
| "elo": 925, | |
| "elo_unrounded": 925.4521956942147 | |
| }, | |
| "logical_reasoning": { | |
| "cases": 50, | |
| "passed": 14, | |
| "accuracy": 0.28, | |
| "weighted_points": 31.387500000000003, | |
| "possible_weighted_points": 107.66250000000001, | |
| "weighted_accuracy": 0.29153605015673983, | |
| "elo": 939, | |
| "elo_unrounded": 938.8608126904453 | |
| }, | |
| "code_completion": { | |
| "cases": 50, | |
| "passed": 5, | |
| "accuracy": 0.1, | |
| "weighted_points": 11.899999999999999, | |
| "possible_weighted_points": 109.89999999999999, | |
| "weighted_accuracy": 0.10828025477707005, | |
| "elo": 729, | |
| "elo_unrounded": 728.9371753478358 | |
| } | |
| }, | |
| "difficulties": { | |
| "easy": { | |
| "cases": 117, | |
| "passed": 39, | |
| "accuracy": 0.3333333333333333, | |
| "weighted_points": 44.25, | |
| "possible_weighted_points": 141.2, | |
| "weighted_accuracy": 0.3133852691218131, | |
| "elo": 731, | |
| "elo_unrounded": 730.9701408690678 | |
| }, | |
| "medium": { | |
| "cases": 117, | |
| "passed": 32, | |
| "accuracy": 0.27350427350427353, | |
| "weighted_points": 57.300000000000004, | |
| "possible_weighted_points": 211.875, | |
| "weighted_accuracy": 0.2704424778761062, | |
| "elo": 791, | |
| "elo_unrounded": 790.8983609544082 | |
| }, | |
| "hard": { | |
| "cases": 116, | |
| "passed": 35, | |
| "accuracy": 0.3017241379310345, | |
| "weighted_points": 91.0125, | |
| "possible_weighted_points": 315.1125, | |
| "weighted_accuracy": 0.2888254194930382, | |
| "elo": 953, | |
| "elo_unrounded": 953.4654883221033 | |
| } | |
| }, | |
| "context_truncations": 0 | |
| }, | |
| "verification": { | |
| "complete": true, | |
| "report_sha256": "befd8ed7c3b5d2862a12eca06bcb443a49d415f3386e70cb7f1480283f0b9f2f", | |
| "runner_sha256": "973a81d09d1c4075d031e1369b4278c52a7813d1ab3b11b33eef665d3247bf2c", | |
| "verifier_sha256": "a0d441f3e633abd1b282d8728f435c777bbc9317a3410865a1d9d31598802d40", | |
| "runtime": { | |
| "torch": "2.14.0+cpu", | |
| "transformers": "5.3.0", | |
| "tokenizers": "0.22.2" | |
| }, | |
| "checks": [ | |
| "350 unique original records and all choices", | |
| "mean-logprob predictions and item weights", | |
| "overall/category/difficulty accuracy and weighted accuracy", | |
| "fixed-item Elo likelihood equation with official prior", | |
| "reported context truncations" | |
| ], | |
| "scope": "Result integrity and official-runner aggregation; not an independent model rerun or contamination guarantee." | |
| } | |
| } | |