Instructions to use CladeTeam/CENO-base-1b-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CladeTeam/CENO-base-1b-preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CladeTeam/CENO-base-1b-preview")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CladeTeam/CENO-base-1b-preview", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CladeTeam/CENO-base-1b-preview with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CladeTeam/CENO-base-1b-preview" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CladeTeam/CENO-base-1b-preview", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CladeTeam/CENO-base-1b-preview
- SGLang
How to use CladeTeam/CENO-base-1b-preview 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 "CladeTeam/CENO-base-1b-preview" \ --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": "CladeTeam/CENO-base-1b-preview", "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 "CladeTeam/CENO-base-1b-preview" \ --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": "CladeTeam/CENO-base-1b-preview", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CladeTeam/CENO-base-1b-preview with Docker Model Runner:
docker model run hf.co/CladeTeam/CENO-base-1b-preview
Invalid JSON:Unexpected token 'I', ..." 0.0,
Infinity
"... is not valid JSON
| { | |
| "architectures": [ | |
| "CENOForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_head_dim": null, | |
| "auto_map": { | |
| "AutoConfig": "configuration_ceno.CENOConfig", | |
| "AutoModelForCausalLM": "modeling_ceno.CENOForCausalLM", | |
| "AutoTokenizer": "ceno_tokenizer.CENOCharLevelTokenizer" | |
| }, | |
| "bos_token_id": 1, | |
| "chunk_size": 128, | |
| "conv_kernel": 4, | |
| "eos_token_id": 2, | |
| "expand": 2, | |
| "head_dim": 64, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 1024, | |
| "hybrid_override_pattern": "MEMEM*EMEMEM*EMEMEMEMEM*EMEMEM*EMEMEME", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_epsilon": 1e-05, | |
| "mamba_head_dim": 64, | |
| "mamba_hidden_act": "silu", | |
| "mamba_in_proj_layernorm": true, | |
| "mamba_num_heads": 32, | |
| "mamba_proj_bias": false, | |
| "mamba_ssm_cache_dtype": "bfloat16", | |
| "max_position_embeddings": 1048576, | |
| "mlp_bias": false, | |
| "mlp_fc1_layernorm": false, | |
| "mlp_hidden_act": "relu2", | |
| "mlp_use_swiglu": false, | |
| "model_type": "ceno", | |
| "moe_intermediate_size": 4096, | |
| "moe_router_dtype": "bfloat16", | |
| "moe_router_pre_softmax": false, | |
| "moe_shared_expert_intermediate_size": 4096, | |
| "moe_top_k": 2, | |
| "n_group": 1, | |
| "n_groups": 8, | |
| "n_routed_experts": 8, | |
| "n_shared_experts": 0, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 16, | |
| "num_experts": 8, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 38, | |
| "num_key_value_heads": 16, | |
| "num_logits_to_keep": 1, | |
| "pad_token_id": 0, | |
| "qkv_layernorm": true, | |
| "rescale_prenorm_residual": true, | |
| "residual_in_fp32": false, | |
| "routed_scaling_factor": 1.0, | |
| "sliding_window": null, | |
| "ssm_state_size": 128, | |
| "tie_word_embeddings": false, | |
| "time_step_floor": 0.0001, | |
| "time_step_limit": [ | |
| 0.0, | |
| Infinity | |
| ], | |
| "time_step_max": 0.1, | |
| "time_step_min": 0.001, | |
| "topk_group": 1, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.3", | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_conv_bias": true, | |
| "use_mamba_kernels": true, | |
| "vocab_size": 512, | |
| "tokenizer_class": "CENOCharLevelTokenizer" | |
| } | |