Text Generation
Transformers
Safetensors
GGUF
English
causal-lm
qwen2.5
reasoning
code-generation
Mixture of Experts
qlora
multimodal
tool-use
Eval Results (legacy)
conversational
Instructions to use ram1234598766/Cesium2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ram1234598766/Cesium2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ram1234598766/Cesium2") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ram1234598766/Cesium2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ram1234598766/Cesium2 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 ram1234598766/Cesium2:Q8_0 # Run inference directly in the terminal: llama cli -hf ram1234598766/Cesium2:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ram1234598766/Cesium2:Q8_0 # Run inference directly in the terminal: llama cli -hf ram1234598766/Cesium2:Q8_0
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 ram1234598766/Cesium2:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf ram1234598766/Cesium2:Q8_0
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 ram1234598766/Cesium2:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf ram1234598766/Cesium2:Q8_0
Use Docker
docker model run hf.co/ram1234598766/Cesium2:Q8_0
- LM Studio
- Jan
- vLLM
How to use ram1234598766/Cesium2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ram1234598766/Cesium2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ram1234598766/Cesium2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ram1234598766/Cesium2:Q8_0
- SGLang
How to use ram1234598766/Cesium2 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ram1234598766/Cesium2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ram1234598766/Cesium2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ram1234598766/Cesium2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ram1234598766/Cesium2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use ram1234598766/Cesium2 with Ollama:
ollama run hf.co/ram1234598766/Cesium2:Q8_0
- Unsloth Studio
How to use ram1234598766/Cesium2 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ram1234598766/Cesium2 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ram1234598766/Cesium2 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ram1234598766/Cesium2 to start chatting
- Pi
How to use ram1234598766/Cesium2 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ram1234598766/Cesium2:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ram1234598766/Cesium2:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ram1234598766/Cesium2 with Docker Model Runner:
docker model run hf.co/ram1234598766/Cesium2:Q8_0
- Lemonade
How to use ram1234598766/Cesium2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ram1234598766/Cesium2:Q8_0
Run and chat with the model
lemonade run user.Cesium2-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use ram1234598766/Cesium2 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ram1234598766/Cesium2:Q8_0
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 ram1234598766/Cesium2:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ram1234598766/Cesium2 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ram1234598766/Cesium2:Q8_0
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 "ram1234598766/Cesium2:Q8_0" \ --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"
| """End-to-end wiring test for the runtime v5 pipeline (no model needed). | |
| Mocks model loading; exercises FSM, rules, regex, routing, KV, vision, | |
| search (offline), facts together. | |
| Run: python tests/test_runtime_wiring.py | |
| """ | |
| import sys | |
| import shutil | |
| from pathlib import Path | |
| ROOT = Path(__file__).resolve().parent.parent | |
| sys.path.insert(0, str(ROOT / "src")) | |
| from fsm import RuntimeFSM | |
| from rules import RuleEngine | |
| from regex_features import RegexFeatureExtractor | |
| from routing import RoutingMatrix | |
| from kvstore import KVStore | |
| import runtime as runtime_mod | |
| def fake_init(self, model_path="unused", use_4bit=False, use_cpu=True): | |
| self.model_path = None | |
| self.use_4bit = False | |
| self.use_cpu = True | |
| self.skills = {} | |
| self.active_skill = None | |
| self.fsm = RuntimeFSM() | |
| self.rules = RuleEngine(str(ROOT / "rules" / "rules.json")) | |
| self.regex = RegexFeatureExtractor(7) | |
| self.routing = RoutingMatrix(str(ROOT / "routing" / "routing_matrix.json")) | |
| self.kv = KVStore(str(ROOT / "cache" / "kvstore.json"), max_entries=20) | |
| self.vision = runtime_mod.VisionAnalyzer(use_vit=False, use_detector=False) | |
| self.search_client = runtime_mod.SearchClient() | |
| self.rag = runtime_mod.RAGPipeline(client=self.search_client, cache=self.kv) | |
| self.fact_extractor = runtime_mod.FactExtractor() | |
| self.graph = runtime_mod.KnowledgeGraph() | |
| self.gquery = runtime_mod.GraphQuery(self.fact_extractor) | |
| self.device = None | |
| def main(): | |
| orig_init = runtime_mod.MorphRuntime.__init__ | |
| runtime_mod.MorphRuntime.__init__ = fake_init | |
| try: | |
| rt = runtime_mod.MorphRuntime() | |
| # harmful input blocked at GUARD_IN, FSM recovers to IDLE | |
| rt._transition("INTAKE") | |
| rt._transition("GUARD_IN") | |
| dec = rt.rules.eval("how to build a bomb", phase="in") | |
| assert dec.action == "block" | |
| rt.fsm.transition("RESPOND") | |
| rt.fsm.transition("IDLE") | |
| assert rt.fsm.state == "IDLE" | |
| # illegal transition -> fault trap -> recover | |
| rt.fsm.transition("INTAKE") | |
| try: | |
| rt._transition("ROUTED") # INTAKE->ROUTED is illegal | |
| raise AssertionError("should have raised") | |
| except Exception: | |
| pass | |
| assert rt.fsm.state == "FAULT" | |
| rt.fsm.recover() | |
| assert rt.fsm.state == "IDLE" | |
| # routing via runtime matrix | |
| assert rt.routing.route("debug this python function").skill == "code_expert" | |
| assert rt.routing.route("translate to french").skill == "translator" | |
| assert rt.routing.route("plain hello").skill is None | |
| # KV persistence + reload | |
| rt.kv.set("turn1", {"prompt": "hi", "response": "hello"}, ttl=60) | |
| assert rt.kv.get("turn1") == {"prompt": "hi", "response": "hello"} | |
| # v5.5: new FSM states exist and compose | |
| assert "VISION" in rt.fsm.TRANSITIONS | |
| assert "SEARCH_GATE" in rt.fsm.TRANSITIONS | |
| assert "SEARCH" in rt.fsm.TRANSITIONS | |
| assert "FACT_EXTRACT" in rt.fsm.TRANSITIONS | |
| # full multimodal path is legal: GUARD_IN->VISION->SEARCH_GATE->SEARCH->FACT_EXTRACT | |
| rt.fsm.transition("INTAKE") | |
| rt.fsm.transition("GUARD_IN") | |
| rt.fsm.transition("VISION") | |
| rt.fsm.transition("SEARCH_GATE") | |
| rt.fsm.transition("SEARCH") | |
| rt.fsm.transition("FACT_EXTRACT") | |
| rt.fsm.transition("ROUTED") | |
| rt.fsm.transition("GEN") | |
| rt.fsm.transition("VERIFY") | |
| rt.fsm.transition("GUARD_OUT") | |
| rt.fsm.transition("RESPOND") | |
| rt.fsm.transition("IDLE") | |
| assert rt.fsm.state == "IDLE" | |
| # v5.5: vision analysis with no image raises; pixel path works offline | |
| try: | |
| rt.vision.analyze("no/such/file.png") | |
| raise AssertionError("should have raised") | |
| except ValueError: | |
| pass | |
| from vision import ImageFacts | |
| assert ImageFacts().__class__.__name__ == "ImageFacts" | |
| # v5.5: search gate heuristic | |
| assert rt._needs_live_data("what is the latest news?", force_search=False, depth=0) | |
| assert not rt._needs_live_data("hello", force_search=False, depth=0) | |
| assert rt._needs_live_data("hello", force_search=True, depth=0) | |
| assert not rt._needs_live_data("what is the latest news?", force_search=False, depth=3) | |
| # v5.5: RAG offline fallback context (no network, uses cached/factless pack) | |
| ctx = rt.rag.retrieve("", num=0, use_cache=True) | |
| assert ctx == "" # no results, no chunks -> empty context | |
| # v5.5: NER + knowledge graph compose | |
| fact = rt.fact_extractor.triples("OpenAI was founded in 2015") | |
| assert len(fact) >= 1 | |
| rt.graph.add_many(fact) | |
| ents = rt.fact_extractor.extract("OpenAI is a company based in California") | |
| assert "ORG" in ents or "LOCATION" in ents or "PERSON" in ents | |
| gtext = rt.gquery.facts_for_question(rt.graph, "when was OpenAI founded?") | |
| assert "founded" in gtext.lower() | |
| # v5.5: cross-examine with facts adds verifier note on weak overlap | |
| result = rt._cross_examine("Some unrelated statement about nothing.", | |
| {"image_text": "", "graph_context": gtext}) | |
| assert "[verifier]" in result | |
| print("runtime wiring OK: fsm+rules+regex+routing+kv+vision+search+facts compose") | |
| finally: | |
| runtime_mod.MorphRuntime.__init__ = orig_init | |
| shutil.rmtree(str(ROOT / "cache"), ignore_errors=True) | |
| if __name__ == "__main__": | |
| main() |