Text Generation
Transformers
Safetensors
dat
babylm
babylm-2026
causal-lm
dual-attention-transformer
nextlat
ema
custom-code
custom_code
Instructions to use abe123/babylm-dat-strict-nextlat-final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abe123/babylm-dat-strict-nextlat-final with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="abe123/babylm-dat-strict-nextlat-final", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("abe123/babylm-dat-strict-nextlat-final", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use abe123/babylm-dat-strict-nextlat-final with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "abe123/babylm-dat-strict-nextlat-final" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "abe123/babylm-dat-strict-nextlat-final", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/abe123/babylm-dat-strict-nextlat-final
- SGLang
How to use abe123/babylm-dat-strict-nextlat-final 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 "abe123/babylm-dat-strict-nextlat-final" \ --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": "abe123/babylm-dat-strict-nextlat-final", "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 "abe123/babylm-dat-strict-nextlat-final" \ --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": "abe123/babylm-dat-strict-nextlat-final", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use abe123/babylm-dat-strict-nextlat-final with Docker Model Runner:
docker model run hf.co/abe123/babylm-dat-strict-nextlat-final
| { | |
| "architectures": [ | |
| "DatForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_dat.DatConfig", | |
| "AutoModel": "modeling_dat.DatModel", | |
| "AutoModelForCausalLM": "modeling_dat.DatForCausalLM", | |
| "AutoModelForMaskedLM": "modeling_dat.DatForMaskedLM", | |
| "AutoModelForSequenceClassification": "modeling_dat.DatForSequenceClassification" | |
| }, | |
| "bos_token_id": 1, | |
| "dff_factor": 4, | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "ffn_activation": "swiglu", | |
| "ffn_hidden_dim_mode": "dff_factor", | |
| "hidden_dim": 1024, | |
| "init_range": 0.15, | |
| "init_scheme": "normal_0_02_scaled_projection", | |
| "max_position_embeddings": 514, | |
| "max_rel_pos": 512, | |
| "max_seq_len": 514, | |
| "mlm_head_enabled": false, | |
| "model_type": "dat", | |
| "n_heads_ra": 4, | |
| "n_heads_sa": 12, | |
| "n_layers": 16, | |
| "n_symbols": null, | |
| "norm_first": true, | |
| "norm_type": "layernorm", | |
| "pad_token_id": 3, | |
| "pe_type": "rope", | |
| "positional_symbols_sinusoidal": false, | |
| "ra_n_relations": null, | |
| "ra_rel_activation": "identity", | |
| "ra_symmetric_rels": false, | |
| "ra_type": "rca", | |
| "relative_symbols_rope": false, | |
| "relsymbolic_dropout": 0.0, | |
| "relsymbolic_include_self": false, | |
| "relsymbolic_neighborhood_size": 2, | |
| "relsymbolic_normalize_rels": true, | |
| "relsymbolic_rel_n_heads": 4, | |
| "relsymbolic_rel_scale": null, | |
| "relsymbolic_symbolic_attn_n_heads": 4, | |
| "relsymbolic_symbolic_attn_scale": null, | |
| "relsymbolic_trainable_symbols": true, | |
| "relsymbolic_use_bias": false, | |
| "rope_theta": 10000.0, | |
| "segment_boundary_token_id": null, | |
| "sequence_boundary_policy": "eos_document", | |
| "share_attn_params": false, | |
| "shared_symbol_retriever": true, | |
| "symbol_dim": null, | |
| "symbol_retrieval": "relative", | |
| "symbolic_attn_n_heads": null, | |
| "symbolic_use_bias": false, | |
| "tie_lm_head": false, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.9.0", | |
| "use_bias_ffn": true, | |
| "use_bias_out": false, | |
| "use_bias_qkv": false, | |
| "vocab_size": 16384 | |
| } | |