Text Generation
PEFT
Safetensors
GGUF
expedient
ctrl-2b
q-lora
retrieval-grounded
enterprise-support
conversational
Instructions to use expedient-ai/CTRL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use expedient-ai/CTRL-2B with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use expedient-ai/CTRL-2B 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 expedient-ai/CTRL-2B:Q4_K_M # Run inference directly in the terminal: llama cli -hf expedient-ai/CTRL-2B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf expedient-ai/CTRL-2B:Q4_K_M # Run inference directly in the terminal: llama cli -hf expedient-ai/CTRL-2B:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf expedient-ai/CTRL-2B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf expedient-ai/CTRL-2B:Q4_K_M
Use Docker
docker model run hf.co/expedient-ai/CTRL-2B:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use expedient-ai/CTRL-2B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "expedient-ai/CTRL-2B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "expedient-ai/CTRL-2B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/expedient-ai/CTRL-2B:Q4_K_M
- Ollama
How to use expedient-ai/CTRL-2B with Ollama:
ollama run hf.co/expedient-ai/CTRL-2B:Q4_K_M
- Unsloth Desktop
- Pi
How to use expedient-ai/CTRL-2B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf expedient-ai/CTRL-2B: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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "expedient-ai/CTRL-2B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use expedient-ai/CTRL-2B with Docker Model Runner:
docker model run hf.co/expedient-ai/CTRL-2B:Q4_K_M
- Lemonade
How to use expedient-ai/CTRL-2B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull expedient-ai/CTRL-2B:Q4_K_M
Run and chat with the model
lemonade run user.CTRL-2B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use expedient-ai/CTRL-2B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf expedient-ai/CTRL-2B: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://127.0.0.1:9931/v1 hermes config set model.default expedient-ai/CTRL-2B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use expedient-ai/CTRL-2B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf expedient-ai/CTRL-2B: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://127.0.0.1:9931/v1 \ --custom-model-id "expedient-ai/CTRL-2B: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"
Download LINEAGE.json from expedient-ai/CTRL-2B: direct link, hf CLI and curl.
- Browser
- Download file 6.77 kB
-
https://huggingface.co/expedient-ai/CTRL-2B/resolve/main/LINEAGE.json
- Command line
-
hf download hf://expedient-ai/CTRL-2B/LINEAGE.json
-
curl -L -o LINEAGE.json https://huggingface.co/expedient-ai/CTRL-2B/resolve/main/LINEAGE.json
6.77 kB
| { | |
| "lineage_for": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\checkpoints\\minicpm5-2b-qlora-v2", | |
| "built": "2026-11-04 08:52:30", | |
| "product": "expedient-agent", | |
| "stages_newest_first": [ | |
| { | |
| "train_config": { | |
| "run_name": "minicpm5-2b-qlora-v2", | |
| "base_model": "openbmb/MiniCPM5-2B", | |
| "smoke": false, | |
| "rows_train": 845, | |
| "rows_val": 94, | |
| "steps_run": 211, | |
| "max_steps": 211, | |
| "loss_last_avg": 0.875325295329094, | |
| "train_seconds": 3258.4, | |
| "val_loss": 2.2051, | |
| "adapter_dir": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\checkpoints\\minicpm5-2b-qlora-v2", | |
| "args": { | |
| "base_model": "openbmb/MiniCPM5-2B", | |
| "train_jsonl": "data/processed/expedient_engram_sft_v2/train.jsonl", | |
| "val_jsonl": "data/processed/expedient_engram_sft_v2/val.jsonl", | |
| "run_name": "minicpm5-2b-qlora-v2", | |
| "epochs": "4.0", | |
| "warmup_frac": "0.1", | |
| "grad_accum": "4", | |
| "micro_batch": "4", | |
| "lr": "0.0002", | |
| "lora_r": "16", | |
| "lora_alpha": "32", | |
| "max_seq_len": "512", | |
| "steps": "0", | |
| "log_every": "10", | |
| "seed": "0", | |
| "smoke": "False" | |
| } | |
| }, | |
| "adapter": { | |
| "path": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\checkpoints\\minicpm5-2b-qlora-v2\\adapter_model.safetensors", | |
| "sha256": "4ef2c8c99839970aaba5e58ca83a0f8c27c6f4ad4b424c91f2feff34ab0733de", | |
| "bytes": 100544848 | |
| }, | |
| "corpus": { | |
| "train": { | |
| "path": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\processed\\expedient_engram_sft_v2\\train.jsonl", | |
| "sha256": "08e60fc708a845be25554afec36b274a7423c03cebe4567ea7408020f88ce5c4", | |
| "bytes": 637356, | |
| "rows": 845 | |
| }, | |
| "val": { | |
| "path": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\processed\\expedient_engram_sft_v2\\val.jsonl", | |
| "sha256": "342bdfcdff954a507234db32cc070ee67f63528e6a50ef0ce716a394b00860d3", | |
| "bytes": 71390, | |
| "rows": 94 | |
| } | |
| }, | |
| "evals": { | |
| "eval_summary": { | |
| "run_name": "minicpm5-2b-qlora-v2", | |
| "adapter_dir": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\checkpoints\\minicpm5-2b-qlora-v2", | |
| "rows": 26, | |
| "number_recall_tuned_mean": 0.772, | |
| "number_recall_base_mean": 0.692, | |
| "number_precision_tuned_mean": 0.865, | |
| "eval_seconds": 633.8 | |
| }, | |
| "eval_rag_summary": { | |
| "run_name": "minicpm5-2b-qlora-v2", | |
| "rows": 94, | |
| "passages_indexed": 939, | |
| "gold_hit_at3": 94, | |
| "gold_hit_at3_rate": 1.0, | |
| "gold_rank_mean": 0.0, | |
| "number_recall_tuned_rag_mean": 0.943, | |
| "number_recall_base_rag_mean": 1.0, | |
| "number_precision_tuned_rag_mean": 0.945, | |
| "eval_seconds": 2831.5 | |
| }, | |
| "eval_robustness_summary": { | |
| "run_name": "minicpm5-2b-qlora-v2", | |
| "paraphrase": { | |
| "rows": 26, | |
| "gold_hit_at3": 26, | |
| "gold_hit_at3_rate": 1.0, | |
| "number_recall_mean": 0.962, | |
| "number_precision_mean": 0.962, | |
| "lens_quartiles": { | |
| "min": 0.5362, | |
| "p25": 0.7478, | |
| "median": 0.8949, | |
| "p75": 0.9277, | |
| "max": 0.9772 | |
| } | |
| }, | |
| "ood": { | |
| "rows": 15, | |
| "abstain_rate_overall": 0.2, | |
| "abstain_by_category": { | |
| "competitor": 0.0, | |
| "general_knowledge": 0.33, | |
| "in_scope_uncovered": 0.4, | |
| "out_of_scope": 0.0 | |
| }, | |
| "lens_quartiles": { | |
| "min": 0.4165, | |
| "p25": 0.5192, | |
| "median": 0.539, | |
| "p75": 0.5844, | |
| "max": 0.7228 | |
| }, | |
| "sc_jaccard_quartiles": { | |
| "min": 0.0579, | |
| "p25": 0.5, | |
| "median": 1.0, | |
| "p75": 1.0, | |
| "max": 1.0 | |
| } | |
| }, | |
| "probe_seconds": 890.6 | |
| }, | |
| "engine_summary": { | |
| "run_name": "minicpm5-2b-qlora-v2", | |
| "gguf": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\exports\\expedient-agent-minicpm5-2b-v2-q8_0.gguf", | |
| "gguf_sha256": "2ee9eaa39592eb2cfcfed7f1f906088c075044e3987e90620fed459cee14ca74", | |
| "gguf_bytes": 2679706912, | |
| "server_binary": "D:\\CuriousGene\\third_party\\llama-b10472\\llama-server.exe", | |
| "server_binary_sha256": "76b0a5f72243ccb99079ca71ebd0332f123c52668d815c9d6716a89d46415668", | |
| "server_command": "D:\\CuriousGene\\third_party\\llama-b10472\\llama-server.exe -m C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\exports\\expedient-agent-minicpm5-2b-v2-q8_0.gguf -ngl 99 -c 2048 --port 8765", | |
| "port": 8765, | |
| "corpus": "data/processed/expedient_engram_sft/val.jsonl", | |
| "n": 26, | |
| "max_new_tokens": 200, | |
| "temperature": 0.0, | |
| "arms": { | |
| "closed_book": { | |
| "recall_mean": 0.731, | |
| "precision_mean": 0.846 | |
| }, | |
| "open_book": { | |
| "recall_mean": 1.0, | |
| "precision_mean": 0.981 | |
| } | |
| }, | |
| "overall": 0.889, | |
| "eval_seconds": 473.3 | |
| } | |
| }, | |
| "exports": { | |
| "expedient-agent-minicpm5-2b-v2-q8_0.gguf": { | |
| "path": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\exports\\expedient-agent-minicpm5-2b-v2-q8_0.gguf", | |
| "sha256": "2ee9eaa39592eb2cfcfed7f1f906088c075044e3987e90620fed459cee14ca74", | |
| "bytes": 2679706912 | |
| }, | |
| "expedient-agent-minicpm5-2b-v2.gguf": { | |
| "path": "C:\\Users\\maris\\.zcode\\workspace\\eb661f10-befd-4988-a93b-b5bd571dc1a3\\agent-training\\data\\exports\\expedient-agent-minicpm5-2b-v2.gguf", | |
| "sha256": "7ad0e8068b71491ad7a7e3519f7453fca0307c4baf79a8ea7a15db9b36484498", | |
| "bytes": 5039002912 | |
| } | |
| }, | |
| "chain_terminus": "fresh-from-base" | |
| } | |
| ], | |
| "n_stages": 1 | |
| } |