Instructions to use Hacht/CapCapResource with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Hacht/CapCapResource 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 Hacht/CapCapResource:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hacht/CapCapResource:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hacht/CapCapResource:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hacht/CapCapResource:Q4_K_M

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 Hacht/CapCapResource:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Hacht/CapCapResource:Q4_K_M

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 Hacht/CapCapResource:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hacht/CapCapResource:Q4_K_M

Use Docker

docker model run hf.co/Hacht/CapCapResource:Q4_K_M

LM Studio
Jan
Ollama
How to use Hacht/CapCapResource with Ollama:
```
ollama run hf.co/Hacht/CapCapResource:Q4_K_M
```
Unsloth Desktop

How to use Hacht/CapCapResource with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hacht/CapCapResource:Q4_K_M

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": "Hacht/CapCapResource:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Hacht/CapCapResource with Docker Model Runner:
```
docker model run hf.co/Hacht/CapCapResource:Q4_K_M
```

Lemonade

How to use Hacht/CapCapResource with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hacht/CapCapResource:Q4_K_M

Run and chat with the model

lemonade run user.CapCapResource-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Hacht/CapCapResource with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hacht/CapCapResource:Q4_K_M

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 Hacht/CapCapResource:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Hacht/CapCapResource with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hacht/CapCapResource:Q4_K_M

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 "Hacht/CapCapResource:Q4_K_M" \
  --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"

Hacht commited on Sep 4

Commit

ab6216d

verified ·

1 Parent(s): 043ae1a

Upload 16 files

Browse files

Files changed (17) hide show

.gitattributes +15 -0
cuda12_fw_new/README.txt +12 -0
cuda12_fw_new/cublas64_12.dll +3 -0
cuda12_fw_new/cublasLt64_12.dll +3 -0
cuda12_fw_new/cudart64_12.dll +3 -0
cuda12_fw_new/cudnn64_9.dll +3 -0
cuda12_fw_new/cudnn_adv64_9.dll +3 -0
cuda12_fw_new/cudnn_cnn64_9.dll +3 -0
cuda12_fw_new/cudnn_engines_precompiled64_9.dll +3 -0
cuda12_fw_new/cudnn_engines_runtime_compiled64_9.dll +3 -0
cuda12_fw_new/cudnn_graph64_9.dll +3 -0
cuda12_fw_new/cudnn_heuristic64_9.dll +3 -0
cuda12_fw_new/cudnn_ops64_9.dll +3 -0
cuda12_fw_new/cufft64_11.dll +3 -0
cuda12_fw_new/cufftw64_11.dll +3 -0
cuda12_fw_new/nvrtc-builtins64_128.dll +3 -0
cuda12_fw_new/nvrtc64_120_0.dll +3 -0

.gitattributes CHANGED Viewed

@@ -57,3 +57,18 @@ f5_voice/tham.mp3 filter=lfs diff=lfs merge=lfs -text
 f5_voice/trieu_duong.mp3 filter=lfs diff=lfs merge=lfs -text
 Hy-MT2-1.8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 onnxruntime_providers_cuda.dll filter=lfs diff=lfs merge=lfs -text

 f5_voice/trieu_duong.mp3 filter=lfs diff=lfs merge=lfs -text
 Hy-MT2-1.8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 onnxruntime_providers_cuda.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cublas64_12.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cublasLt64_12.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudart64_12.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudnn_adv64_9.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudnn_cnn64_9.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudnn_engines_precompiled64_9.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudnn_engines_runtime_compiled64_9.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudnn_graph64_9.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudnn_heuristic64_9.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudnn_ops64_9.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cudnn64_9.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cufft64_11.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/cufftw64_11.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/nvrtc-builtins64_128.dll filter=lfs diff=lfs merge=lfs -text
+cuda12_fw_new/nvrtc64_120_0.dll filter=lfs diff=lfs merge=lfs -text

cuda12_fw_new/README.txt ADDED Viewed

	@@ -0,0 +1,12 @@

+CapCap GPU runtime pack: CUDA 12.8
+This folder contains the CUDA 12.8 runtime DLLs used by Faster-Whisper:
+- cuBLAS / cuBLASLt 12.8.3
+- CUDA Runtime 12.8.57
+- cuFFT 11.3.3.41
+- cuDNN 9.10.2.21
+- NVRTC 12.8 (`nvrtc64_120_0.dll` and `nvrtc-builtins64_128.dll`) for RapidOCR CUDA inference
+Keep all DLLs from compatible CUDA/cuDNN releases together. Do not mix
+individual DLLs from older CUDA packs. Resource Manager can replace this
+folder when a newer GPU runtime pack is available.

cuda12_fw_new/cublas64_12.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a60a7ecbf906f7f3842826fecaf412f1587ff6269729339245a1ec224364161
+size 113712640

cuda12_fw_new/cublasLt64_12.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a21ddfc1c9cd090ab07d2c6aad235aa4f15fe60fe896d5db28adf7a279c09ef3
+size 692441600

cuda12_fw_new/cudart64_12.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9b868955149875ac4ef43442aaaa8913d4a7b3e4d6dd60ee871626aa045768
+size 573952

cuda12_fw_new/cudnn64_9.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9edbcdff73b0af070eb160b2ce66e59feca04aa017351d8eedcc5e8e149967d2
+size 266288

cuda12_fw_new/cudnn_adv64_9.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f202e8ff36209ac4292fe2ef79d4539487495b3b948f0c978cc63298f43a1850
+size 282445872

cuda12_fw_new/cudnn_cnn64_9.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3f03dec3b81f137f049e1d1c06ff469248eef54ff9424b3b9045fc0f69559d1a
+size 4618272

cuda12_fw_new/cudnn_engines_precompiled64_9.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc2c1f74366b029a4350f7f9a3b109ccd5aa9b4ae02527950793dd29f7b74fb
+size 513926688

cuda12_fw_new/cudnn_engines_runtime_compiled64_9.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:93ab6351ca0f2b6ca842f83d284e56c427525778c14657229801a13cf8121bd8
+size 20201008

cuda12_fw_new/cudnn_graph64_9.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a933efeb280a3252297f92d79f7e83003bcbc6f665872d11645d1dbbab9cb598
+size 2420256

cuda12_fw_new/cudnn_heuristic64_9.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:458175f12771a35de0ea39c04250d727c2424d42a7ffe0bc987ae81204748fba
+size 56823328

cuda12_fw_new/cudnn_ops64_9.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:851d8f4191a24b322b0be738d191a3159455f0da4db47a19f5cc7ad6e55edf61
+size 126508576

cuda12_fw_new/cufft64_11.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:619fcb005c8a18ffad478ff68b7a9cd154fa170e835dce9d41ff4fc0c0692113
+size 276121088

cuda12_fw_new/cufftw64_11.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd778bc18c2050c937279656cdbbdd2a37623ea5bf38c09ebcf6451771b7fbe3
+size 163328

cuda12_fw_new/nvrtc-builtins64_128.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:96a28201dbffd4eff6dc93f310417b981bf7a141d46f2839036f5dbfd83b33ae
+size 6356480

cuda12_fw_new/nvrtc64_120_0.dll ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2a860422b7d0396b45c29a1848faecc3788041ba52f166f0fc52c1b47e8245
+size 86702592