Text Generation
Safetensors
GGUF
English
Chinese
vllm
mimo_v2
nvfp4
modelopt
mixture-of-experts
lossless-weight-transcode
conversational
custom_code
8-bit precision
Instructions to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16 # Run inference directly in the terminal: llama cli -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16 # Run inference directly in the terminal: llama cli -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16 # Run inference directly in the terminal: ./llama-cli -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Use Docker
docker model run hf.co/ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
- LM Studio
- Jan
- vLLM
How to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
- Ollama
How to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with Ollama:
ollama run hf.co/ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
- Unsloth Desktop
- Pi
How to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with Docker Model Runner:
docker model run hf.co/ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
- Lemonade
How to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Run and chat with the model
lemonade run user.MiMo-V2.6-Flash-MOPD-NVFP4-BF16
List all available models
lemonade list
- Hermes Agent
How to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4:BF16" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download reports/gguf-weight-verification.json from ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4: direct link, hf CLI and curl.
- Browser
- Download file 60.6 kB
-
https://huggingface.co/ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4/resolve/main/reports/gguf-weight-verification.json
- Command line
-
hf download hf://ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4/reports/gguf-weight-verification.json
-
curl -L -o gguf-weight-verification.json https://huggingface.co/ProCreations/MiMo-V2.6-Flash-MOPD-NVFP4/resolve/main/reports/gguf-weight-verification.json
60.6 kB
| { | |
| "started_at": 1790546204.4454432, | |
| "status": "passed", | |
| "expert_values_verified": 302795194368, | |
| "dense_values_verified": 6971406720, | |
| "architecture_and_tokenizer_fields_verified": 31, | |
| "tensors": [ | |
| { | |
| "name": "blk.1.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.ffn_down_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.ffn_gate_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.ffn_up_exps.weight", | |
| "kind": "exact_source_experts", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.nextn.eh_proj.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.nextn.enorm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.layer_output_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.nextn.hnorm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.ffn_down.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.ffn_gate.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.ffn_up.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.48.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.nextn.eh_proj.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.nextn.enorm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.layer_output_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.nextn.hnorm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.ffn_down.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.ffn_gate.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.ffn_up.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.49.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.nextn.eh_proj.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.nextn.enorm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.layer_output_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.nextn.hnorm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.ffn_down.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.ffn_gate.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.ffn_up.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.50.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "token_embd.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.0.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.0.ffn_down.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.0.ffn_gate.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.0.ffn_up.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.0.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.0.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.0.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.1.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.10.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.11.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.12.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.13.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.14.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.15.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.16.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.17.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.18.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.19.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.2.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.20.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.21.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.22.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.23.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.24.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.25.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.26.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.27.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.28.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.29.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.3.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.30.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.31.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.32.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.33.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.34.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.35.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.36.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.37.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.38.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.39.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.4.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.40.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.41.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.42.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.43.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.44.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.45.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.46.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.47.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.5.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.6.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.7.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.8.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.attn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.exp_probs_b.bias", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.ffn_gate_inp.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.ffn_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.attn_sinks.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.attn_output.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "blk.9.attn_qkv.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| }, | |
| { | |
| "name": "output_norm.weight", | |
| "kind": "identical_dense_bytes", | |
| "status": "passed" | |
| } | |
| ], | |
| "completed_at": 1790546814.2453725 | |
| } | |