Instructions to use ncylich/temporal-moe-extras with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ncylich/temporal-moe-extras 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 ncylich/temporal-moe-extras
# Run inference directly in the terminal:
llama cli -hf ncylich/temporal-moe-extras

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ncylich/temporal-moe-extras
# Run inference directly in the terminal:
llama cli -hf ncylich/temporal-moe-extras

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 ncylich/temporal-moe-extras
# Run inference directly in the terminal:
./llama-cli -hf ncylich/temporal-moe-extras

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 ncylich/temporal-moe-extras
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ncylich/temporal-moe-extras

Use Docker

docker model run hf.co/ncylich/temporal-moe-extras

LM Studio
Jan
Ollama
How to use ncylich/temporal-moe-extras with Ollama:
```
ollama run hf.co/ncylich/temporal-moe-extras
```
Unsloth Desktop

How to use ncylich/temporal-moe-extras with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ncylich/temporal-moe-extras

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": "ncylich/temporal-moe-extras"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ncylich/temporal-moe-extras with Docker Model Runner:
```
docker model run hf.co/ncylich/temporal-moe-extras
```

Lemonade

How to use ncylich/temporal-moe-extras with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ncylich/temporal-moe-extras

Run and chat with the model

lemonade run user.temporal-moe-extras-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ncylich/temporal-moe-extras with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ncylich/temporal-moe-extras

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 ncylich/temporal-moe-extras

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ncylich/temporal-moe-extras with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ncylich/temporal-moe-extras

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 "ncylich/temporal-moe-extras" \
  --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"

temporal-moe-extras / ablations /mechinterp_structural.csv

ncylich

Add files using upload-large-folder tool

04eb95f verified 3 months ago

Raw History Blame Contribute Delete

984 Bytes

label,run,kind,E,k,PR_median,generalist_frac,router_entropy,eff_rank,strong_corr_pairs,dist2centroid_mean,pairwise_cos_med,pairwise_cos_p99
s0_TEMPORAL(L0),g3_tmoe_s0_1e16,temporal,192,18,0.6572,0.6458,0.9494,11.47,68,0.8775,0.01,0.0363
s0_FULL(a0ctl_sig),g3_moe_s0_1e16_sigmoid,full,192,18,0.284,0.0469,0.8688,12.48,66,0.8947,0.0059,0.0327
s0_FULL(A1_auxfree),g3_moe_s0_1e16_auxfree,full,192,18,0.2478,0.1146,0.8463,12.7,37,0.8745,0.0101,0.052
s2_TEMPORAL(minlogit),tmoe_minlogit_sh1_s2_1e17,temporal,64,6,0.5236,0.5375,0.9257,16.53,0,0.8352,0.0117,0.0227
s2_FULL(v16k),v16k_sweep_s2_1e17,full,64,6,0.341,0.1344,0.8641,11.62,3,0.8424,0.0093,0.0233
s0_TEMPORAL(L0_seed3),g3_tmoe_s0_1e16_seed3,temporal,192,18,0.6502,0.6667,0.9523,12.14,36,0.8713,0.0115,0.0381
s0_FULL(a0ctl_sig_seed2),g3_moe_s0_1e16_sigmoid_seed2,full,192,18,0.2741,0.0451,0.8689,13.09,63,0.8909,0.0068,0.0348
s0_SOFTMAX_BASELINE,g3_moe_s0_1e16,full,192,18,0.3039,0.0174,0.8782,13.56,24,0.8999,0.0049,0.0313

	label,run,kind,E,k,PR_median,generalist_frac,router_entropy,eff_rank,strong_corr_pairs,dist2centroid_mean,pairwise_cos_med,pairwise_cos_p99
	s0_TEMPORAL(L0),g3_tmoe_s0_1e16,temporal,192,18,0.6572,0.6458,0.9494,11.47,68,0.8775,0.01,0.0363
	s0_FULL(a0ctl_sig),g3_moe_s0_1e16_sigmoid,full,192,18,0.284,0.0469,0.8688,12.48,66,0.8947,0.0059,0.0327
	s0_FULL(A1_auxfree),g3_moe_s0_1e16_auxfree,full,192,18,0.2478,0.1146,0.8463,12.7,37,0.8745,0.0101,0.052
	s2_TEMPORAL(minlogit),tmoe_minlogit_sh1_s2_1e17,temporal,64,6,0.5236,0.5375,0.9257,16.53,0,0.8352,0.0117,0.0227
	s2_FULL(v16k),v16k_sweep_s2_1e17,full,64,6,0.341,0.1344,0.8641,11.62,3,0.8424,0.0093,0.0233
	s0_TEMPORAL(L0_seed3),g3_tmoe_s0_1e16_seed3,temporal,192,18,0.6502,0.6667,0.9523,12.14,36,0.8713,0.0115,0.0381
	s0_FULL(a0ctl_sig_seed2),g3_moe_s0_1e16_sigmoid_seed2,full,192,18,0.2741,0.0451,0.8689,13.09,63,0.8909,0.0068,0.0348
	s0_SOFTMAX_BASELINE,g3_moe_s0_1e16,full,192,18,0.3039,0.0174,0.8782,13.56,24,0.8999,0.0049,0.0313