Text Generation
Transformers
Safetensors
English
bananamind2_pico
causal-lm
base-model
muon
xsa-refresh
custom-code
trust-remote-code
custom_code
Instructions to use Banaxi-Tech/pico-50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Banaxi-Tech/pico-50 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Banaxi-Tech/pico-50", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Banaxi-Tech/pico-50", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Banaxi-Tech/pico-50 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Banaxi-Tech/pico-50" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Banaxi-Tech/pico-50", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Banaxi-Tech/pico-50
- SGLang
How to use Banaxi-Tech/pico-50 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 "Banaxi-Tech/pico-50" \ --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": "Banaxi-Tech/pico-50", "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 "Banaxi-Tech/pico-50" \ --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": "Banaxi-Tech/pico-50", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Banaxi-Tech/pico-50 with Docker Model Runner:
docker model run hf.co/Banaxi-Tech/pico-50
| { | |
| "parameters": 900002, | |
| "architecture": { | |
| "vocab_size": 384, | |
| "hidden_size": 96, | |
| "num_hidden_layers": 6, | |
| "num_attention_heads": 6, | |
| "num_key_value_heads": 2, | |
| "head_dim": 16, | |
| "intermediate_size": 380, | |
| "refresh_layers": [ | |
| 3, | |
| 5 | |
| ], | |
| "refresh_kernel_size": 9, | |
| "refresh_alpha_init": 0.0, | |
| "max_position_embeddings": 4096, | |
| "rope_theta": 100000.0, | |
| "rms_norm_eps": 1e-06, | |
| "initializer_range": 0.02, | |
| "use_cache": true, | |
| "transformers_version": "5.15.0", | |
| "architectures": null, | |
| "output_hidden_states": false, | |
| "return_dict": true, | |
| "dtype": null, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "problem_type": null, | |
| "_name_or_path": "", | |
| "tie_word_embeddings": true, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "pad_token_id": 0, | |
| "unk_token_id": 3, | |
| "model_type": "bananamind2_pico", | |
| "output_attentions": false | |
| }, | |
| "training_percent": 50, | |
| "step": 11220, | |
| "total_steps": 22439, | |
| "tokens_seen": 100002693120, | |
| "target_tokens": 200000000000, | |
| "trained_token_target": 199996473344, | |
| "tokens_per_step": 8912896, | |
| "local_batch": 544, | |
| "effective_global_batch": 2176, | |
| "world_size": 4, | |
| "gpu_name": "NVIDIA H200", | |
| "optimizer": "Muon + AdamW", | |
| "muon_peak_lr": 0.07, | |
| "adamw_peak_lr": 0.004, | |
| "architecture_revision": "ee5739850035c878ce4d9fc29fc38b075987e03b", | |
| "tokenizer_revision": "ee5739850035c878ce4d9fc29fc38b075987e03b", | |
| "dataset_revisions": { | |
| "fineweb_hq": "e58199cdd52438d94405df1a4d8630cc5f13bf84", | |
| "cosmopedia_v2": "3ba9d605774198c5868892d7a8deda78031a781f" | |
| }, | |
| "source_tokens": { | |
| "fineweb_hq": 80002154496, | |
| "cosmopedia_v2": 20000538624 | |
| }, | |
| "elapsed_seconds": 13947.764428138733 | |
| } | |