Instructions to use kacaforyah/Opti-27B 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 kacaforyah/Opti-27B 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 kacaforyah/Opti-27B:F16 # Run inference directly in the terminal: llama cli -hf kacaforyah/Opti-27B:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf kacaforyah/Opti-27B:F16 # Run inference directly in the terminal: llama cli -hf kacaforyah/Opti-27B:F16
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 kacaforyah/Opti-27B:F16 # Run inference directly in the terminal: ./llama-cli -hf kacaforyah/Opti-27B:F16
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 kacaforyah/Opti-27B:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf kacaforyah/Opti-27B:F16
Use Docker
docker model run hf.co/kacaforyah/Opti-27B:F16
- LM Studio
- Jan
- vLLM
How to use kacaforyah/Opti-27B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kacaforyah/Opti-27B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kacaforyah/Opti-27B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/kacaforyah/Opti-27B:F16
- Ollama
How to use kacaforyah/Opti-27B with Ollama:
ollama run hf.co/kacaforyah/Opti-27B:F16
- Unsloth Desktop
- Pi
How to use kacaforyah/Opti-27B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf kacaforyah/Opti-27B:F16
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": "kacaforyah/Opti-27B:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use kacaforyah/Opti-27B with Docker Model Runner:
docker model run hf.co/kacaforyah/Opti-27B:F16
- Lemonade
How to use kacaforyah/Opti-27B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull kacaforyah/Opti-27B:F16
Run and chat with the model
lemonade run user.Opti-27B-F16
List all available models
lemonade list
- Hermes Agent
How to use kacaforyah/Opti-27B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf kacaforyah/Opti-27B:F16
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 kacaforyah/Opti-27B:F16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use kacaforyah/Opti-27B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf kacaforyah/Opti-27B:F16
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 "kacaforyah/Opti-27B:F16" \ --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"
Card: domain table paired directly against the 16-bit model; F16 and KL logs published
8686992 verified Download eval/ppl_code_f16.log from kacaforyah/Opti-27B: direct link, hf CLI and curl.
- Browser
- Download file 2.5 kB
-
https://huggingface.co/kacaforyah/Opti-27B/resolve/main/eval/ppl_code_f16.log
- Command line
-
hf download hf://kacaforyah/Opti-27B/eval/ppl_code_f16.log
-
curl -L -o ppl_code_f16.log https://huggingface.co/kacaforyah/Opti-27B/resolve/main/eval/ppl_code_f16.log
2.5 kB
| 0.02.361.481 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring | |
| 0.02.361.496 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring | |
| 0.02.361.510 W model has unused tensor blk.64.attn_q.weight (size = 125829120 bytes) -- ignoring | |
| 0.02.361.515 W model has unused tensor blk.64.attn_k.weight (size = 10485760 bytes) -- ignoring | |
| 0.02.361.520 W model has unused tensor blk.64.attn_v.weight (size = 10485760 bytes) -- ignoring | |
| 0.02.361.537 W model has unused tensor blk.64.attn_output.weight (size = 62914560 bytes) -- ignoring | |
| 0.02.361.544 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring | |
| 0.02.361.549 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring | |
| 0.02.361.554 W model has unused tensor blk.64.ffn_gate.weight (size = 178257920 bytes) -- ignoring | |
| 0.02.361.561 W model has unused tensor blk.64.ffn_down.weight (size = 178257920 bytes) -- ignoring | |
| 0.02.361.567 W model has unused tensor blk.64.ffn_up.weight (size = 178257920 bytes) -- ignoring | |
| 0.02.361.575 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 104857600 bytes) -- ignoring | |
| 0.02.361.583 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring | |
| 0.02.361.588 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring | |
| 0.02.361.603 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring | |
| 0.11.979.495 I cmn init: llama threadpool init, n_threads = 64 | |
| 0.13.117.567 I | |
| 0.13.117.843 I system_info: n_threads = 64 (n_threads_batch = 64) / 256 | CUDA : ARCHS = 860,890 | USE_GRAPHS = 1 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | | |
| 0.13.117.876 I perplexity: tokenizing the input .. | |
| 0.13.622.600 I perplexity: tokenization took 504.706 ms | |
| 0.13.622.862 I perplexity: calculating perplexity over 32 chunks, n_ctx=1024, batch_size=512, n_seq=1 | |
| 0.20.701.304 I perplexity: 7.08 seconds per pass - ETA 3.77 minutes | |