Text Generation
Transformers
Safetensors
PyTorch
English
French
tr_hash_moe
tr-hash
mixture-of-experts
gqa
supervised-finetuning
full-parameter-finetuning
custom-code
conversational
custom_code
Instructions to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT
- SGLang
How to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT 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 "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT" \ --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": "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT", "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 "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT" \ --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": "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT with Docker Model Runner:
docker model run hf.co/AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT
| active_expert_width: null | |
| active_num_experts: null | |
| attention_dropout: 0.0 | |
| attention_type: gqa | |
| causal_context_fusion_size: 0 | |
| causal_context_gate_init: 1.0 | |
| causal_contextual_mix_init: 0.0 | |
| causal_conv_dilation_cycle: 8 | |
| causal_conv_kernel_size: 4 | |
| causal_delta_chunk_size: 512 | |
| causal_delta_collision_normalized: false | |
| causal_delta_lexical_forge: false | |
| causal_delta_lexical_values: false | |
| causal_delta_occurrence_address: false | |
| causal_delta_timescales: 1 | |
| causal_stable_delta: false | |
| causal_state_rank: 16 | |
| collect_moe_telemetry: false | |
| expert_initialization: gpt_normal | |
| extra_config: {} | |
| hash_channel_scale_init: 0.0 | |
| hash_pair_gate_init: 0.5 | |
| hidden_act: silu | |
| hidden_size: 896 | |
| initializer_range: 0.02 | |
| intermediate_size: 256 | |
| is_causal: true | |
| learn_hash_channel_modulation: false | |
| learn_hash_pair_gates: false | |
| lexical_gqa_gate_init: 0.0 | |
| lexical_gqa_rank: 16 | |
| lexical_gqa_use_token_code: true | |
| lexical_key_gate_init: 0.05 | |
| lexical_object_gate_init: 0.1 | |
| lexical_object_rank: 16 | |
| lexical_zipf_alpha: 0.25 | |
| lexical_zipf_floor: 0.1 | |
| lexical_zipf_mode: uniform | |
| lexical_zipf_path: null | |
| lexical_zipf_permutation_seed: 1729 | |
| lsh_bits: 0 | |
| lsh_from_layer: 0 | |
| lsh_routing: false | |
| lsh_threshold_mode: zero | |
| max_position_embeddings: 2048 | |
| micro_expert_gate_init: 0.1 | |
| micro_expert_width: 16 | |
| micro_num_experts: 4 | |
| mlp_type: tr_hash_engine | |
| mup_base_width: 256 | |
| norm_eps: 1.0e-06 | |
| norm_type: rmsnorm | |
| num_attention_heads: 14 | |
| num_experts: 4 | |
| num_hidden_layers: 16 | |
| num_key_value_heads: 2 | |
| rope_fraction: 1.0 | |
| rope_theta: 10000.0 | |
| rope_type: standard | |
| route_hash_count: 2 | |
| routed_gate_init: 1.0 | |
| routed_output_scale: 2.0 | |
| routed_output_scale_first_layer: null | |
| routed_output_scale_last_layer: null | |
| routing_strategy: token_id_multi_hash | |
| shared_expert: true | |
| shared_expert_chunk_tokens: 0 | |
| shared_gate_init: 1.0 | |
| shared_intermediate_size: 3072 | |
| shared_output_scale: 1.0 | |
| shared_output_scale_first_layer: null | |
| shared_output_scale_last_layer: null | |
| sliding_window: null | |
| static_expert_capacity: false | |
| tie_lexical_object_embeddings: false | |
| tie_word_embeddings: true | |
| token_frequencies: null | |
| top_k: 2 | |
| top_k_primary_weight: 0.5 | |
| tr_mha_adapter_gate_init: 0.1 | |
| tr_mha_adapter_rank: 8 | |
| tr_mha_id_other_logit: -2.0 | |
| tr_mha_id_primary_logit: 2.0 | |
| tr_mha_id_secondary_logit: 1.0 | |
| tr_mha_num_experts: 4 | |
| tr_mha_targets: qv | |
| tr_mha_top_k: 2 | |
| tr_mha_verifier_gate_init: 0.1 | |
| tr_mha_verifier_temperature: 1.0 | |
| use_cache: true | |
| use_cggr: auto | |
| use_custom_kernels: true | |
| use_mup_attn_scale: false | |
| use_mup_init: false | |
| use_mup_output_mult: false | |
| use_qk_norm: true | |
| use_sdpa: true | |
| use_shared_routed_gates: false | |
| vocab_size: 32000 | |