Instructions to use KitsuVp/NeoLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KitsuVp/NeoLLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="KitsuVp/NeoLLM", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("KitsuVp/NeoLLM", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use KitsuVp/NeoLLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "KitsuVp/NeoLLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "KitsuVp/NeoLLM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/KitsuVp/NeoLLM
- SGLang
How to use KitsuVp/NeoLLM 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 "KitsuVp/NeoLLM" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "KitsuVp/NeoLLM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "KitsuVp/NeoLLM" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "KitsuVp/NeoLLM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use KitsuVp/NeoLLM with Docker Model Runner:
docker model run hf.co/KitsuVp/NeoLLM
| { | |
| "affine_momentum": 0.9, | |
| "architectures": [ | |
| "NeoLLMForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.1, | |
| "attn_res_num_blocks": 4, | |
| "auto_map": { | |
| "AutoConfig": "configuration_neollm.NeoLLMConfig", | |
| "AutoModel": "modeling_neollm.NeoLLMModel", | |
| "AutoModelForCausalLM": "modeling_neollm.NeoLLMForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "dca_past_layers_k": 1, | |
| "directional_routing_k": 4, | |
| "directional_routing_temp": 3.0, | |
| "dropout_rate": 0.1, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 7, | |
| "fan_ratio": 0.125, | |
| "fan_ratio_ffn": 0.0625, | |
| "generator_d_seed": 128, | |
| "generator_k": 3, | |
| "generator_krank": 64, | |
| "generator_num_knots": 32, | |
| "generator_num_modes": 8, | |
| "generator_spline_degree": 2, | |
| "head_dim": 64, | |
| "hidden_act": "xielu", | |
| "hidden_size": 512, | |
| "iha_local_global_pattern": "LLLLG", | |
| "iha_num_pseudo_heads": 2, | |
| "iha_sliding_window": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "jtokm_aux_loss_weight": 0.0001, | |
| "jtokm_norm_eps": 1e-06, | |
| "jtokm_num_experts": 4, | |
| "jtokm_num_modes": 4, | |
| "jtokm_top_k": 2, | |
| "laurel_lr_rank": 32, | |
| "lucid_attention_eps": 1e-06, | |
| "max_position_embeddings": 512, | |
| "mea_component_key_value_heads": 4, | |
| "mea_groupnorm_eps": 1e-06, | |
| "mea_norm_type": "seednorm", | |
| "model_type": "neollm", | |
| "momentum_gamma": 0.1, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 12, | |
| "num_key_value_heads": 4, | |
| "num_mem_heads": 4, | |
| "pad_token_id": 0, | |
| "partial_rotary_factor": 0.25, | |
| "polynorm_exclusive": false, | |
| "repo_d_p": 64, | |
| "repo_goat_num_frequencies": 3, | |
| "repo_goat_sink_decay": 4.0, | |
| "repo_start_layer": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 10000.0, | |
| "siamese_attn_x_scale_init": 1.0, | |
| "siamese_depth_scaling": true, | |
| "siamese_normalized_input": true, | |
| "stack_d_model": 32, | |
| "stack_memory_cache_size": 2048, | |
| "stack_slots": 16, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.8.1", | |
| "use_affine_scaled_attention": false, | |
| "use_attn_res": false, | |
| "use_cache": false, | |
| "use_dca": false, | |
| "use_directional_routing": false, | |
| "use_embedding_input_norm": true, | |
| "use_embedding_multipliers": false, | |
| "use_fan_residual": false, | |
| "use_gpas": false, | |
| "use_hadamard_o_proj": true, | |
| "use_iha": true, | |
| "use_jtokm": false, | |
| "use_laurel": false, | |
| "use_laurel_lr": false, | |
| "use_laurel_rw": false, | |
| "use_learnable_multipliers": true, | |
| "use_lns": false, | |
| "use_lucid_attention": false, | |
| "use_mea_attention": false, | |
| "use_momentum_attention": true, | |
| "use_repo": true, | |
| "use_repo_goat_prior": false, | |
| "use_repo_grape": true, | |
| "use_seednorm": false, | |
| "use_siamesenorm": true, | |
| "use_spelling_bee_embeddings": true, | |
| "use_stack_memory": false, | |
| "use_token_generator": true, | |
| "use_versatile_ffn": false, | |
| "use_xsa": true, | |
| "versatile_active_experts": 2, | |
| "versatile_aux_loss_weight": 1e-05, | |
| "versatile_gumbel_temp_decay": 0.99984, | |
| "versatile_gumbel_temp_end": 0.1, | |
| "versatile_gumbel_temp_start": 5.0, | |
| "versatile_max_depth": 2, | |
| "versatile_total_experts": 4, | |
| "vocab_size": 64402, | |
| "xsa_eps": 1e-06 | |
| } | |