Text Generation
Transformers
Safetensors
English
swarm_agi
swarm
ai
agent
llm
convergent
cpu
fp32
agi
convergentintel
Instructions to use reaperdoesntknow/SharperSwarm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use reaperdoesntknow/SharperSwarm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="reaperdoesntknow/SharperSwarm")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/SharperSwarm", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use reaperdoesntknow/SharperSwarm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "reaperdoesntknow/SharperSwarm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "reaperdoesntknow/SharperSwarm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/reaperdoesntknow/SharperSwarm
- SGLang
How to use reaperdoesntknow/SharperSwarm 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 "reaperdoesntknow/SharperSwarm" \ --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": "reaperdoesntknow/SharperSwarm", "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 "reaperdoesntknow/SharperSwarm" \ --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": "reaperdoesntknow/SharperSwarm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use reaperdoesntknow/SharperSwarm with Docker Model Runner:
docker model run hf.co/reaperdoesntknow/SharperSwarm
| { | |
| "B_compute": 100000.0, | |
| "B_energy": 10000.0, | |
| "B_memory": 10000.0, | |
| "K_thought_max": 25, | |
| "anom_thresh": 0.75, | |
| "architectures": [ | |
| "SwarmForCausalLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "attn_dim": 128, | |
| "bos_token_id": 1, | |
| "compute_per_agent": 2.0, | |
| "compute_per_thought": 2.5, | |
| "core_values": [ | |
| "truth", | |
| "safety", | |
| "efficiency" | |
| ], | |
| "curiosity_strength": 0.45, | |
| "curiosity_surprise_thresh": 0.08, | |
| "dim_msg": 32, | |
| "dim_obs": 48, | |
| "dim_s": 256, | |
| "dim_t": 128, | |
| "drift_freeze_plastic": false, | |
| "drift_thresh": 0.3, | |
| "dtype": "float32", | |
| "dwell_window": 30, | |
| "early_stop_ratio": 0.02, | |
| "ema_fast": 0.15, | |
| "ema_slow": 0.002, | |
| "energy_cost_per_agent": 0.25, | |
| "energy_cost_per_thought": 0.3, | |
| "eos_token_id": 2, | |
| "episodic_topk": 10, | |
| "goal_split_thresh": 0.8, | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 512, | |
| "intermediate_size": 2048, | |
| "max_agents": 20, | |
| "max_goal_depth": 32, | |
| "max_position_embeddings": 1024, | |
| "memory_capacity": 8192, | |
| "model_type": "swarm_agi", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 14, | |
| "pad_token_id": 0, | |
| "replay_coef": 0.005, | |
| "resource_mass_coef": 0.003, | |
| "rollback_strength": 0.55, | |
| "route_entropy_coef": 0.003, | |
| "route_temp": 1.4, | |
| "safety_agent_ids": [ | |
| 0, | |
| 1 | |
| ], | |
| "semantic_ema": 0.995, | |
| "stall_ratio": 0.98, | |
| "swarm_hidden": 256, | |
| "swarm_loss_weight": 0.1, | |
| "topk_route": 3, | |
| "transformers_version": "4.57.3", | |
| "trust_lr": 0.08, | |
| "trust_max": 5.0, | |
| "trust_min": 0.02, | |
| "vocab_size": 50290 | |
| } | |