clm:8b
2 TagsUpdated 8.2B params2048 contextEnglishApache-2.0by Contrastive-LM
CLM-v0.1-8B on Qwen3-8B, 0.357 on typed decisions; built for agent, game and tool-calling states. Needs a 20 GB GPU.
8.2b
ollaya run clm:8b --preset triage "I was charged twice for my subscription this month and want a refund."curl http://localhost:11435/api/decide \
-H "Content-Type: application/json" \
-d '{
"model": "clm:8b",
"state": "I was charged twice for my subscription this month and want a refund.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Payments, invoices and refunds",
"technical": "Bugs, errors and outages",
"account": "Login, profile and settings"
}
},
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
}'# Already using a TypeSafe SDK? Set TYPESAFE_BASE_URL=http://localhost:11435 instead.
import requests
response = requests.post(
"http://localhost:11435/api/decide",
json={
"model": "clm:8b",
"state": "I was charged twice for my subscription this month and want a refund.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Payments, invoices and refunds",
"technical": "Bugs, errors and outages",
"account": "Login, profile and settings"
}
},
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
},
)
answers = response.json()["answers"]
print(answers["department"]["choice"], answers["refund"]["noul"])const response = await fetch("http://localhost:11435/api/decide", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model: "clm:8b",
state: "I was charged twice for my subscription this month and want a refund.",
questions: {
department: {
type: "choice",
instructions: "Which team should handle this?",
criteria: {
billing: "Payments, invoices and refunds",
technical: "Bugs, errors and outages",
account: "Login, profile and settings"
}
},
refund: {
type: "noul",
instructions: "Is the customer asking for a refund?"
}
}
}),
});
const { answers } = await response.json();
console.log(answers.department.choice, answers.refund.noul);Details
- graph1f7b6781f500 · 7 MB
onnx · clm · 8.2B · fp32 - weights31d6a825ae35 · 4.0 GB
huggingface.co/Qwen/Qwen3-8B/resolve/b968826…/model-00001-of-00005.safetensors - weights5991236cea6f · 4.0 GB
huggingface.co/Qwen/Qwen3-8B/resolve/b968826…/model-00002-of-00005.safetensors - weightsc5185c4794be · 4.0 GB
huggingface.co/Qwen/Qwen3-8B/resolve/b968826…/model-00003-of-00005.safetensors - weightsb5ee7de71fbf · 3.2 GB
huggingface.co/Qwen/Qwen3-8B/resolve/b968826…/model-00004-of-00005.safetensors - weights20c2d6366ab8 · 1.2 GB
huggingface.co/Qwen/Qwen3-8B/resolve/b968826…/model-00005-of-00005.safetensors - weightsb2b4a8c9c2d3 · 76 MB
huggingface.co/Contrastive-LM/CLM-v0.1-8B/resolve/e939398…/CLM_v0.1-8B.pt - tokenizeraeb13307a71a · 11 MB
huggingface.co/Qwen/Qwen3-8B/resolve/b968826…/tokenizer.json - decisiond2fc1f758f5d · 2 KB
{"engine": "onnx", "family": "clm", "encoder": "", "layout": "clm-v1", …} - calibrationade0f04e3391 · 201 B
{"temperature": [1.0, 1.0, 1.0]} - licensef5bb8e0f6419 · 10 KB
CLM-v0.1-8B by Contrastive-LM (https://huggingface.co/Contrastive-LM/CLM-v0.1-8B), state and action projection heads: Apache-2.0.
Every layer is checked against its sha256 when it is pulled. Weights and tokenizers download from the model author's Hugging Face repository at a pinned commit; Ollaya never re-hosts them.