Text Generation
Transformers
Safetensors
code
Mixture of Experts
fusion
deepseek
qwen
mixture-of-experts
research
Instructions to use Akahsizrr/Mini-Whale-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Akahsizrr/Mini-Whale-Flash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Akahsizrr/Mini-Whale-Flash")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Akahsizrr/Mini-Whale-Flash", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Akahsizrr/Mini-Whale-Flash with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Akahsizrr/Mini-Whale-Flash" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Akahsizrr/Mini-Whale-Flash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Akahsizrr/Mini-Whale-Flash
- SGLang
How to use Akahsizrr/Mini-Whale-Flash 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 "Akahsizrr/Mini-Whale-Flash" \ --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": "Akahsizrr/Mini-Whale-Flash", "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 "Akahsizrr/Mini-Whale-Flash" \ --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": "Akahsizrr/Mini-Whale-Flash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Akahsizrr/Mini-Whale-Flash with Docker Model Runner:
docker model run hf.co/Akahsizrr/Mini-Whale-Flash
| { | |
| "source_model": "deepseek-ai/DeepSeek-V4-Flash", | |
| "extraction_timestamp": "2026-07-30T16:07:42Z", | |
| "dtype": "bfloat16", | |
| "total_experts": 260, | |
| "layers": { | |
| "0": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "1": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "2": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "3": { | |
| "expert_ids": [ | |
| 0, | |
| 1, | |
| 7 | |
| ], | |
| "experts": { | |
| "0": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "4": { | |
| "expert_ids": [ | |
| 0, | |
| 1, | |
| 5 | |
| ], | |
| "experts": { | |
| "0": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "5": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "6": { | |
| "expert_ids": [ | |
| 0, | |
| 1, | |
| 7 | |
| ], | |
| "experts": { | |
| "0": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "7": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3, | |
| 5, | |
| 6, | |
| 9 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "8": { | |
| "expert_ids": [ | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 10 | |
| ], | |
| "experts": { | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "10": { | |
| "expert_ids": [ | |
| 1, | |
| 3, | |
| 6, | |
| 8 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "11": { | |
| "expert_ids": [ | |
| 1, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "12": { | |
| "expert_ids": [ | |
| 1, | |
| 5, | |
| 7 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "13": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "14": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "15": { | |
| "expert_ids": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7 | |
| ], | |
| "experts": { | |
| "0": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "16": { | |
| "expert_ids": [ | |
| 0, | |
| 1, | |
| 4, | |
| 5, | |
| 8 | |
| ], | |
| "experts": { | |
| "0": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "17": { | |
| "expert_ids": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6 | |
| ], | |
| "experts": { | |
| "0": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "18": { | |
| "expert_ids": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6 | |
| ], | |
| "experts": { | |
| "0": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "19": { | |
| "expert_ids": [ | |
| 1, | |
| 3, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 10 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "20": { | |
| "expert_ids": [ | |
| 4, | |
| 7, | |
| 8 | |
| ], | |
| "experts": { | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "21": { | |
| "expert_ids": [ | |
| 2, | |
| 3 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "22": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "23": { | |
| "expert_ids": [ | |
| 3, | |
| 5, | |
| 6, | |
| 7, | |
| 9, | |
| 10, | |
| 14 | |
| ], | |
| "experts": { | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "14": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "24": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 4, | |
| 12 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "25": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 13, | |
| 14, | |
| 19, | |
| 23 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "14": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "19": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "23": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "26": { | |
| "expert_ids": [ | |
| 9 | |
| ], | |
| "experts": { | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "27": { | |
| "expert_ids": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 14, | |
| 28 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "14": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "28": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "28": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 14, | |
| 15 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "11": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "14": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "15": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "29": { | |
| "expert_ids": [ | |
| 1, | |
| 3, | |
| 4, | |
| 9, | |
| 10, | |
| 13, | |
| 15 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "15": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "30": { | |
| "expert_ids": [ | |
| 13, | |
| 14 | |
| ], | |
| "experts": { | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "14": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "31": { | |
| "expert_ids": [ | |
| 3, | |
| 6, | |
| 12, | |
| 13, | |
| 14, | |
| 18 | |
| ], | |
| "experts": { | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "14": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "18": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "32": { | |
| "expert_ids": [ | |
| 1, | |
| 4, | |
| 5, | |
| 6, | |
| 10, | |
| 13, | |
| 15, | |
| 21 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "15": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "21": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "33": { | |
| "expert_ids": [ | |
| 3, | |
| 12, | |
| 13, | |
| 17 | |
| ], | |
| "experts": { | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "17": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "34": { | |
| "expert_ids": [ | |
| 1, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 15, | |
| 21 | |
| ], | |
| "experts": { | |
| "1": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "11": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "15": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "21": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "35": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 11, | |
| 15 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "11": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "15": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "36": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 5, | |
| 7, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 14, | |
| 15, | |
| 16, | |
| 19 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "11": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "14": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "15": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "16": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "19": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "37": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 5, | |
| 6, | |
| 7, | |
| 10, | |
| 12 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "38": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 15 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "11": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "15": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "39": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 4, | |
| 7, | |
| 10, | |
| 13, | |
| 16, | |
| 20 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "16": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "20": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "40": { | |
| "expert_ids": [ | |
| 3, | |
| 13 | |
| ], | |
| "experts": { | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "13": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "41": { | |
| "expert_ids": [ | |
| 3, | |
| 4, | |
| 5, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 12, | |
| 14 | |
| ], | |
| "experts": { | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "8": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "9": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "10": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "14": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| }, | |
| "42": { | |
| "expert_ids": [ | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 11, | |
| 12 | |
| ], | |
| "experts": { | |
| "2": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "3": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "4": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "5": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "6": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "7": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "11": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| }, | |
| "12": { | |
| "gate_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "up_proj": [ | |
| 2048, | |
| 4096 | |
| ], | |
| "down_proj": [ | |
| 4096, | |
| 2048 | |
| ], | |
| "params": 25165824 | |
| } | |
| } | |
| } | |
| }, | |
| "shard_files": [ | |
| "coding-experts-00000.safetensors", | |
| "coding-experts-00001.safetensors" | |
| ], | |
| "total_parameters": 6543114240 | |
| } |