How to use from
Docker Model Runner
docker model run hf.co/solomoniw/CallForge-1B-v0:
Quick Links

CallForge-1B v0

CallForge-1B v0 is a lightweight 1B parameter tool-calling specialist fine-tuned from openbmb/MiniCPM5-1B. It is designed to reliably select tools, construct schema-valid arguments, execute calls, and repair execution failures in agentic tool-use workflows.

Model Summary

  • Base Model: openbmb/MiniCPM5-1B
  • Parameters: ~1.08B
  • Architecture: LlamaForCausalLM
  • Format: Native MiniCPM5 chat template with XML tool-call markup
  • License: Apache-2.0

Evaluation & Results

CallForge-1B v0 demonstrates significant improvements in zero-shot generalization to unseen tools while maintaining solid performance on seen tool suites:

Metric Base MiniCPM5-1B CallForge-1B v0
Seen Task Success Rate 20% 40%
Held-out Tool Task Success Rate 0% 43%
Parser Well-formed Rate 100% 92%
Parser Schema-valid Rate 100% 92%

Quickstart & Inference

You can run CallForge-1B v0 using Hugging Face Transformers:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "solomoniw/CallForge-1B-v0"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
    device_map="auto"
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Fetch current weather conditions for a given city.",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "City name"}
                },
                "required": ["city"]
            }
        }
    }
]

messages = [
    {"role": "user", "content": "What is the weather like in Tokyo right now?"}
]

inputs = tokenizer.apply_chat_template(
    messages,
    tools=tools,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(inputs, max_new_tokens=256)
response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)
print(response)

Intended Use

CallForge-1B v0 is designed for local, resource-constrained agentic applications requiring reliable tool use and structured function calling.

Downloads last month
41
Safetensors
Model size
1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for solomoniw/CallForge-1B-v0

Quantized
(108)
this model
Quantizations
1 model