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"
Add cesium2 terminal CLI (live web data) to tools/
Browse files- tools/cesium2.cmd +2 -0
- tools/cesium2.py +169 -0
tools/cesium2.cmd
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
@echo off
|
| 2 |
+
python "%~dp0cesium2.py" %*
|
tools/cesium2.py
ADDED
|
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""cesium2 - terminal chat with MORPH-AI v6 (Cesium2) via Ollama, with live web data.
|
| 3 |
+
|
| 4 |
+
Usage:
|
| 5 |
+
cesium2 "what is todays popular news" one-shot answer
|
| 6 |
+
cesium2 interactive chat (/exit to quit, /new resets)
|
| 7 |
+
"""
|
| 8 |
+
import json
|
| 9 |
+
import os
|
| 10 |
+
import re
|
| 11 |
+
import sys
|
| 12 |
+
import urllib.parse
|
| 13 |
+
import urllib.request
|
| 14 |
+
from datetime import datetime
|
| 15 |
+
|
| 16 |
+
try:
|
| 17 |
+
sys.stdout.reconfigure(encoding="utf-8", errors="replace")
|
| 18 |
+
sys.stderr.reconfigure(encoding="utf-8", errors="replace")
|
| 19 |
+
except Exception:
|
| 20 |
+
pass
|
| 21 |
+
|
| 22 |
+
HOST = os.environ.get("OLLAMA_HOST", "http://localhost:11434").rstrip("/")
|
| 23 |
+
MODEL = os.environ.get("CESIUM2_MODEL", "ram1234598766/Cesium2")
|
| 24 |
+
|
| 25 |
+
SYSTEM = (
|
| 26 |
+
"You are MORPH-AI v6 (Cesium2), a helpful assistant with advanced reasoning. "
|
| 27 |
+
"Your training data has a cutoff; rely ONLY on the [LIVE CONTEXT] block for "
|
| 28 |
+
"time-sensitive facts - it contains the real current date and fresh web results. "
|
| 29 |
+
"Think step by step and be concise."
|
| 30 |
+
)
|
| 31 |
+
|
| 32 |
+
LIVE_RE = re.compile(
|
| 33 |
+
r"\b(news|today|todays|current|currently|latest|recent|now|breaking|price|prices|"
|
| 34 |
+
r"weather|forecast|score|scores|who won|stock|stocks|market|election|update|"
|
| 35 |
+
r"2024|2025|2026|this week|this month|yesterday)\b",
|
| 36 |
+
re.I,
|
| 37 |
+
)
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
def google_news(query, limit=5):
|
| 41 |
+
def fetch(qs):
|
| 42 |
+
url = f"https://news.google.com/rss/search?q={urllib.parse.quote(qs)}&hl=en-US&gl=US&ceid=US:en"
|
| 43 |
+
req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0"})
|
| 44 |
+
xml = urllib.request.urlopen(req, timeout=20).read().decode("utf-8", "ignore")
|
| 45 |
+
titles = re.findall(r"<item><title>(.*?)</title>", xml)
|
| 46 |
+
dates = re.findall(r"<pubDate>(.*?)</pubDate>", xml)
|
| 47 |
+
return list(zip(titles, dates))
|
| 48 |
+
|
| 49 |
+
cleaned = re.sub(r"\b(what|is|are|the|of|and|today'?s?|date|for|me|tell|about)\b", " ",
|
| 50 |
+
query, flags=re.I)
|
| 51 |
+
candidates = [
|
| 52 |
+
" ".join(cleaned.split())[:80],
|
| 53 |
+
"top news today",
|
| 54 |
+
"breaking news",
|
| 55 |
+
]
|
| 56 |
+
best = []
|
| 57 |
+
for qs in candidates:
|
| 58 |
+
if not qs.strip():
|
| 59 |
+
continue
|
| 60 |
+
try:
|
| 61 |
+
got = fetch(qs)
|
| 62 |
+
except Exception:
|
| 63 |
+
continue
|
| 64 |
+
if len(got) > len(best):
|
| 65 |
+
best = got
|
| 66 |
+
if len(best) >= limit:
|
| 67 |
+
break
|
| 68 |
+
return "\n".join(
|
| 69 |
+
f"{i+1}. {t} [{d}]" for i, (t, d) in enumerate(best[:limit])
|
| 70 |
+
)
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
def build_live(prompt):
|
| 74 |
+
block = f"[LIVE CONTEXT - current date & time: {datetime.now()}]\n\n"
|
| 75 |
+
try:
|
| 76 |
+
news = google_news(prompt)
|
| 77 |
+
block += ("Fresh web results (Google News):\n" + news) if news else "No fresh results found."
|
| 78 |
+
except Exception as e:
|
| 79 |
+
block += f"(web search unavailable: {e})"
|
| 80 |
+
block += "\n\nUse this LIVE CONTEXT as ground truth for time-sensitive facts."
|
| 81 |
+
return block
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def stream_chat(messages):
|
| 85 |
+
body = json.dumps({
|
| 86 |
+
"model": MODEL,
|
| 87 |
+
"messages": messages,
|
| 88 |
+
"stream": True,
|
| 89 |
+
"options": {"temperature": 0.7, "num_ctx": 8192},
|
| 90 |
+
}).encode()
|
| 91 |
+
req = urllib.request.Request(
|
| 92 |
+
HOST + "/api/chat", data=body, headers={"Content-Type": "application/json"}
|
| 93 |
+
)
|
| 94 |
+
resp = urllib.request.urlopen(req, timeout=600)
|
| 95 |
+
full = []
|
| 96 |
+
dec = json.JSONDecoder()
|
| 97 |
+
buf = ""
|
| 98 |
+
while True:
|
| 99 |
+
chunk = resp.read(1)
|
| 100 |
+
if not chunk:
|
| 101 |
+
break
|
| 102 |
+
buf += chunk.decode("utf-8", "ignore")
|
| 103 |
+
while "\n" in buf:
|
| 104 |
+
line, buf = buf.split("\n", 1)
|
| 105 |
+
line = line.strip()
|
| 106 |
+
if not line:
|
| 107 |
+
continue
|
| 108 |
+
try:
|
| 109 |
+
obj = dec.raw_decode(line)[0]
|
| 110 |
+
except Exception:
|
| 111 |
+
continue
|
| 112 |
+
tok = obj.get("message", {}).get("content", "")
|
| 113 |
+
if tok:
|
| 114 |
+
full.append(tok)
|
| 115 |
+
print(tok, end="", flush=True)
|
| 116 |
+
if obj.get("done"):
|
| 117 |
+
print()
|
| 118 |
+
return "".join(full)
|
| 119 |
+
print()
|
| 120 |
+
return "".join(full)
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
def answer(prompt, history):
|
| 124 |
+
msgs = [{"role": "system", "content": SYSTEM}]
|
| 125 |
+
if LIVE_RE.search(prompt):
|
| 126 |
+
print("[searching the web...]", file=sys.stderr, flush=True)
|
| 127 |
+
msgs.append({"role": "system", "content": build_live(prompt)})
|
| 128 |
+
msgs += history + [{"role": "user", "content": prompt}]
|
| 129 |
+
reply = stream_chat(msgs)
|
| 130 |
+
history.extend([
|
| 131 |
+
{"role": "user", "content": prompt},
|
| 132 |
+
{"role": "assistant", "content": reply},
|
| 133 |
+
])
|
| 134 |
+
if len(history) > 24:
|
| 135 |
+
del history[:-24]
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
def main():
|
| 139 |
+
args = sys.argv[1:]
|
| 140 |
+
if args:
|
| 141 |
+
answer(" ".join(args), [])
|
| 142 |
+
return
|
| 143 |
+
print(f"MORPH-AI Cesium2 terminal 路 model={MODEL} 路 /new reset 路 /exit quit")
|
| 144 |
+
history = []
|
| 145 |
+
while True:
|
| 146 |
+
try:
|
| 147 |
+
prompt = input("\nyou > ").strip()
|
| 148 |
+
except (EOFError, KeyboardInterrupt):
|
| 149 |
+
print()
|
| 150 |
+
break
|
| 151 |
+
if not prompt:
|
| 152 |
+
continue
|
| 153 |
+
if prompt.lower() in ("/exit", "/quit"):
|
| 154 |
+
break
|
| 155 |
+
if prompt.lower() == "/new":
|
| 156 |
+
history.clear()
|
| 157 |
+
print("[conversation cleared]")
|
| 158 |
+
continue
|
| 159 |
+
try:
|
| 160 |
+
answer(prompt, history)
|
| 161 |
+
except Exception as e:
|
| 162 |
+
msg = str(e)
|
| 163 |
+
if "ConnectionRefused" in msg or "URLError" in msg:
|
| 164 |
+
msg = f"cannot reach Ollama at {HOST} - start it first ('ollama serve')"
|
| 165 |
+
print(f"\n[error] {msg}", file=sys.stderr)
|
| 166 |
+
|
| 167 |
+
|
| 168 |
+
if __name__ == "__main__":
|
| 169 |
+
main()
|