Text Generation
Transformers
PyTorch
Indonesian
English
code
mesosfer
bear-ai
llama-architecture
causal-lm
Instructions to use Dummy9898/bear-240m-pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Dummy9898/bear-240m-pretrain with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Dummy9898/bear-240m-pretrain")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Dummy9898/bear-240m-pretrain", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Dummy9898/bear-240m-pretrain with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Dummy9898/bear-240m-pretrain" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Dummy9898/bear-240m-pretrain", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Dummy9898/bear-240m-pretrain
- SGLang
How to use Dummy9898/bear-240m-pretrain 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 "Dummy9898/bear-240m-pretrain" \ --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": "Dummy9898/bear-240m-pretrain", "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 "Dummy9898/bear-240m-pretrain" \ --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": "Dummy9898/bear-240m-pretrain", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Dummy9898/bear-240m-pretrain with Docker Model Runner:
docker model run hf.co/Dummy9898/bear-240m-pretrain
| { | |
| "timestamp": "2026-08-15T13:32:23.333839", | |
| "checkpoint": "storage/models/bear_final.pt", | |
| "device": "cpu", | |
| "stages": { | |
| "pretrain": { | |
| "summary": { | |
| "avg_loss": 4.426291036605835, | |
| "avg_ppl": 83.62069494173322, | |
| "avg_bpb": 1.861745809924929, | |
| "task_count": 5 | |
| }, | |
| "details": [ | |
| { | |
| "id": "hf_pretrain_id_wiki_01", | |
| "source": "wikimedia/wikipedia (20231101.id)", | |
| "loss": 4.715993881225586, | |
| "ppl": 111.71979221759592, | |
| "bpb": 1.9835979548999556, | |
| "generated_sample": "Buddha di mana. Candi Borobudur adalah candi Buddha di mana di mana. C" | |
| }, | |
| { | |
| "id": "hf_pretrain_id_indommlu_01", | |
| "source": "indonlp/IndoMMLU", | |
| "loss": 6.034489154815674, | |
| "ppl": 417.5854336341011, | |
| "bpb": 2.5381713055250157, | |
| "generated_sample": "Alas yang benar-benar bekahata dan obaklah.\nJawaban: Alas yang" | |
| }, | |
| { | |
| "id": "hf_pretrain_en_mmlu_cs_01", | |
| "source": "cais/mmlu (computer_science)", | |
| "loss": 5.34050989151001, | |
| "ppl": 208.6190562599516, | |
| "bpb": 2.2462761330320546, | |
| "generated_sample": "To calculate the bandwidth of a packet, the bandwidth is then calculated using the value of the bandwidth of a packet. The" | |
| }, | |
| { | |
| "id": "hf_pretrain_en_arc_01", | |
| "source": "allenai/ai2_arc", | |
| "loss": 2.8477277755737305, | |
| "ppl": 17.248544715052773, | |
| "bpb": 1.1977850552833762, | |
| "generated_sample": "the normal force.\n\u2022 10.\nElijah, Martin M., Akbar, A. & Mits" | |
| }, | |
| { | |
| "id": "hf_pretrain_en_climbmix_01", | |
| "source": "karpathy/climbmix-400b-shuffle", | |
| "loss": 3.192734479904175, | |
| "ppl": 24.35493454957321, | |
| "bpb": 1.3428986008842438, | |
| "generated_sample": "probability of 1/2. In other words, the distribution of the sum of the given probability distribution is the probability" | |
| } | |
| ] | |
| } | |
| } | |
| } |