Hugging Face's logo

MultiverseComputingCAI
/
LittleLamb-ToolCalling

Text Generation
Transformers
Safetensors
qwen3
conversational
text-generation-inference
Model card Files
xet
 Community
LittleLamb-ToolCalling / README.md
daniicruzz's picture
daniicruzz
Upload README.md with huggingface_hub
e7350ce verified
preview code
|
raw
history blame contribute delete
18.2 kB
---
base_model:
- Qwen/Qwen3-0.6B
- MultiverseComputing/LittleLamb-0.3B
library_name: transformers
license: apache-2.0
---
<div align="center">
# LittleLamb 0.3B Tool-Calling
### Powered by CompactifAI
[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![HuggingFace](https://img.shields.io/badge/🤗-Model_Hub-yellow.svg)](https://huggingface.co/MultiverseComputingCAI/LittleLamb-ToolCalling)
[![Discord](https://img.shields.io/badge/Discord-Community-5865F2?logo=discord&logoColor=white)](https://discord.gg/cGas9uStqp)
**Tiny Model** · **50% Compressed** · **Native Tool Calling** · **Thinking & Non-Thinking Modes**
</div>
---
## Table of Contents
- [Highlights](#highlights)
- [Model Overview](#model-overview)
- [Key Characteristics](#key-characteristics)
- [Quick Start](#quick-start)
- [What's New in LittleLamb 0.3B Tool-Calling](#whats-new-in-littlelamb-03b-tool-calling)
- [Tool Calling](#tool-calling)
- [Dual-Mode Inference (Thinking / Non-Thinking)](#dual-mode-inference-thinking--non-thinking)
- [Training & Fine-Tuning](#training--fine-tuning)
- [Architecture](#architecture)
- [Evaluation & Benchmarks](#evaluation--benchmarks)
- [Languages](#languages)
- [Intended Use](#intended-use)
- [Safety & Limitations](#safety--limitations)
- [Model Information](#model-information)
- [Citation](#citation)
---
## Model Overview
**LittleLamb 0.3B Tool-Calling** is a **tool-calling–optimized variant** of [LittleLamb 0.3B](https://huggingface.co/MultiverseComputingCAI/LittleLamb-ToolCalling) at **290M parameters**, developed based on [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) by **Multiverse Computing**. Built on top of the CompactifAI-compressed LittleLamb base, this variant has been additionally fine-tuned for **function calling, structured outputs, and agentic workflows**. It supports **thinking and non-thinking modes** while adding native tool-use support in a sub-300M-parameter footprint.
---
## Key Characteristics
| Characteristic | Description |
| ---------------- | ---------------------------------------------------------------------------------------------------------------- |
| Base model | [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) (0.6B params, 0.44B non-embedding; open-weight, Apache 2.0) |
| **Tool calling** | Native support for function calling with defined schemas and structured outputs |
| **Parameters** |290M total parameters after CompactifAI compression (50% compression rate from base 0.6B) |
| **Architecture** | Decoder-only Transformer (Qwen3 family) |
| **Compression** | CompactifAI (proprietary) |
| **Languages** | English. Spanish is yet to be tested for tool-calling capabilities. |
| **Modes** | Thinking (`enable_thinking=True`) and non-thinking (`enable_thinking=False`) via chat template |
---
## Quick Start
This model can be loaded with the **Transformers** library. Requires `transformers>=4.51.0` for Qwen3 architecture support.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "MultiverseComputingCAI/LittleLamb-ToolCalling"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
 model_id,
 torch_dtype="auto",
 device_map="auto",
)
messages = [{"role": "user", "content": "Hello!"}]
text = tokenizer.apply_chat_template(
 messages,
 tokenize=False,
 add_generation_prompt=True,
 enable_thinking=True,
)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
output_ids = model.generate(**inputs, max_new_tokens=256)[0]
response = tokenizer.decode(
 output_ids[len(inputs.input_ids[0]) :], skip_special_tokens=True
)
print(response)
```
For OpenAI-compatible serving, use a stack that supports Qwen3 reasoning and tool calling (e.g. recent **vLLM** or **SGLang** with Qwen3 parsers); see the [Qwen3-0.6B model card](https://huggingface.co/Qwen/Qwen3-0.6B) for deployment examples.
---
## What's New in LittleLamb 0.3B Tool-Calling
### Summary
- **Tool-calling–optimized** variant of LittleLamb 0.3B, fine-tuned for function calling and structured outputs.
- **Ultra-compact** at 290M parameters, suitable for edge and on-device deployment with agentic capabilities.
- **Developed based on [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)** with **CompactifAI** compression (~50% parameter reduction vs. base non-embedding count).
---
## Tool Calling
LittleLamb 0.3B Tool-Calling supports **native tool use** and is designed for:
- **Function calling** with defined schemas
- **Structured outputs**
- **Agentic operations** (e.g. browser tasks, code execution where supported)
The model can detect when to invoke tools, emit structured JSON tool calls, and consume tool outputs to continue generation. Tool-calling behavior follows Qwen3-style schemas.
### Example Tool Call
```json
{
 "name": "get_weather",
 "arguments": {
 "city": "Paris",
 "date": "2026-02-10"
 }
}
```
---
## Dual-Mode Inference (Thinking / Non-Thinking)
LittleLamb 0.3B Tool-Calling inherits Qwen3's dual-mode capability, supporting seamless switching between **thinking mode** (for complex reasoning) and **non-thinking mode** (for efficient general-purpose dialogue).
The model generates internal reasoning in Qwen3's thinking format (see the Qwen3 chat template) before producing the final response. Use this for tasks requiring multi-step reasoning, math, or code generation.
Set `enable_thinking=False` for lower-latency dialogue without explicit chain-of-thought in the template. Follow the **sampling parameters** recommended in the [Qwen3-0.6B model card](https://huggingface.co/Qwen/Qwen3-0.6B) for each mode.
---
## Training & Fine-Tuning
### Base Model: Qwen3-0.6B
The base model [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) is a causal language model from the Qwen3 family, supporting thinking/non-thinking modes. See the [Qwen3 technical report](https://arxiv.org/abs/2505.09388) for details.
### CompactifAI Compression & Tool-Calling Fine-Tuning
- **Compression:** CompactifAI was applied to produce a smaller, efficient model (~0.3B parameters) while aiming to preserve reasoning capabilities.
- **Tool-calling fine-tuning:** This variant includes additional fine-tuning for function calling and structured outputs on top of the compressed LittleLamb base.
---
## Architecture
### Model Specifications
| Field | Value |
| ---------------- | ----------------------------------------------------------------------- |
| Base model | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) (0.6B params) |
| Total parameters | 290M dense |
---
## Evaluation & Benchmarks
### Evaluation Methodology
Benchmark scores were obtained with the following setups. Methodology varies by benchmark family.
For **LittleLamb 0.3B Tool-Calling** and **Qwen3-0.6B (base)**, benchmark runs are reported under both **thinking** and **non-thinking** chat modes using the sampling settings recommended in the [Qwen3-0.6B model card](https://huggingface.co/Qwen/Qwen3-0.6B).
#### MMLU-Pro, GPQA Diamond, IFBench
- **Evaluation framework**: [Nemo-skills](https://github.com/NVIDIA/NeMo-Skills)
- **Inference library**: vLLM 0.18.0
- **Thinking mode** (`enable_thinking=True`, per Qwen3-0.6B instruct): temperature = 0.6, top_p = 0.95, top_k = 20, min_p = 0
- **Non-thinking mode** (`enable_thinking=False`, per Qwen3-0.6B instruct): temperature = 0.7, top_p = 0.8, top_k = 20, min_p = 0
#### BFCL v4, τ²-Bench
- **Evaluation framework**: [EvalScope](https://github.com/EvalScope/EvalScope)
- **Inference library**: vLLM 0.18.0
- **Thinking mode** (`enable_thinking=True`, per Qwen3-0.6B instruct): temperature = 0.6, top_p = 0.95, top_k = 20, min_p = 0
- **Non-thinking mode** (`enable_thinking=False`, per Qwen3-0.6B instruct): temperature = 0.7, top_p = 0.8, top_k = 20, min_p = 0
- Results of `functiongemma-270m-it` for BFCL v4 were extracted from [Google's model card](https://huggingface.co/google/functiongemma-270m-it) (09/04/2026)
### Quantitative Results
Reported numbers use the methodology described above.
#### Thinking mode
| Benchmark | functiongemma-270m-it | Qwen3-0.6B (think) | LittleLamb-TC 0.3B (think) |
| --------------------------- | --------------------- | ------------------ | -------------------------- |
| IFBench | 12.00 | 23.88 | 20.00 |
| GPQA Diamond | 2.53 | 29.59 | 27.47 |
| MMLU-Pro | 0.42 | 38.27 | 28.74 |
| τ²-Bench | 5.05 | 19.59 | 18.70 |
| BFCL Simple | 61.60 | 72.73 | 72.36 |
| BFCL Multiple | 63.50 | 85.00 | 89.50 |
| BFCL Parallel | 39.00 | 70.00 | 70.00 |
| BFCL Parallel Multiple | 29.50 | 71.50 | 68.00 |
| BFCL Live Simple | 36.20 | 63.18 | 64.34 |
| BFCL Live Multiple | 25.70 | 56.41 | 60.78 |
| BFCL Live Parallel | 22.90 | 50.00 | 62.50 |
| BFCL Live Parallel Multiple | 20.80 | 50.00 | 45.83 |
| BFCL Relevance | 61.10 | 75.00 | 75.00 |
| BFCL Irrelevance | 73.70 | 84.58 | 77.92 |
| **BFCL v4** | 27.03 | 54.08 | 51.55 |
#### Non-thinking mode
| Benchmark | functiongemma-270m-it | Qwen3-0.6B (no think) | LittleLamb-TC 0.3B (no think) |
| --------------------------- | --------------------- | --------------------- | ----------------------------- |
| IFBench | 12.00 | 23.80 | 21.00 |
| GPQA Diamond | 2.53 | 27.77 | 27.37 |
| MMLU-Pro | 0.42 | 25.72 | 23.71 |
| τ²-Bench | 5.05 | 15.50 | 26.67 |
| BFCL Simple | 61.60 | 12.73 | 70.55 |
| BFCL Multiple | 63.50 | 20.00 | 80.50 |
| BFCL Parallel | 39.00 | 18.00 | 71.50 |
| BFCL Parallel Multiple | 29.50 | 30.50 | 70.50 |
| BFCL Live Simple | 36.20 | 4.65 | 62.02 |
| BFCL Live Multiple | 25.70 | 11.02 | 50.43 |
| BFCL Live Parallel | 22.90 | 0.00 | 43.75 |
| BFCL Live Parallel Multiple | 20.80 | 12.50 | 29.17 |
| BFCL Relevance | 61.10 | 12.50 | 75.00 |
| BFCL Irrelevance | 73.70 | 97.50 | 87.50 |
| **BFCL v4** | 27.03 | 29.17 | 50.51 |
![Intelligence Thinking](assets/littlelamb-tc-intelligence-family.png)
BFCL V4 is the de facto industry standard for evaluating function-calling (tool-use) capability. It tests whether models can correctly generate structured function calls in response to user queries, across simple single-call scenarios, parallel calls, multi-turn conversations, and complex agentic workflows.
### Quantitative Results (Inference Performance)
#### Metrics reported
- **System Output Throughput (higher is better)**: Mean output tokens per second across all concurrent requests over the benchmarking phase.
- **End-to-End Latency per Query (lower is better):** Median end-to-end response time for each query from the time the query is sent.
- **Output Speed per Query (higher is better):** Median output tokens per second after the first token is received for each query.
- **Time to first token (TTFT) (lower is better):** Median
- **Estimated Peak Memory Usage (lower is better):** KV cache utilization is monitored during the phase and we estimate memory usage as follows: $model\_ weights_{gb} + kv\_ cache_{usage\_pct} × (nvml\_used_{gb} − model\_ weights_{gb})$
- **Model weights (lower is better):**
#### Performance evaluation conditions
Our performance evaluation follows the spirit of [Artificial Analysis](https://artificialanalysis.ai/methodology/system-load-test).
- **Inference library**: vLLM 0.18.0
- **Monitoring libraries**: GuideLLM 0.6.0, nvidia-ml-py 13.590.48
- **Hardware**: 1× NVIDIA L4 GPU
- **Conditions**: concurrency=16
- **Phase duration**: Each phase lasts 3 minutes (excluding ramp-up and cool-down periods).
- **Workload shape**: 1,000 input tokens and 1,000 output tokens per query.
- **Streaming**: Benchmarking is conducted with streaming enabled.
**Summary of improvements:** LittleLamb shows a slight improvement in performance with respect to the original Qwen Model. This is expected as for such small models, VRAM usage is dominated by KV cache and not model weights.
![Performance](assets/littlelamb-tc-performance-family.png)
---
## Languages
- **Primary languages**: English. Spanish is yet to be tested for tool-calling capabilities.
---
## Intended Use
### Recommended Use Cases
Aligned with [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) use cases, with the added benefit of tool-calling capabilities in a smaller footprint suitable for edge and on-device deployment:
- **Function calling and agentic workflows** in resource-constrained environments
- **On-device and edge inference** where memory and compute are constrained
- **Structured output generation** (JSON, schemas)
- **Reasoning tasks** with configurable thinking/non-thinking modes
- **Chatbots and virtual assistants** with tool integration
### Out-of-Scope Uses
- Harmful, illegal, or deceptive content generation
- Impersonation of real individuals without consent
- High-risk decision-making without human oversight
- Surveillance or tracking of individuals
- Any use that violates applicable laws or regulations
---
## Safety & Limitations
### Known Limitations
- **Model scale:** At ~0.3B parameters, this is an ultra-compact model. Several frontier-scale benchmarks (GDPval-AA, Terminal-Bench Hard, AA-LCR, CritPt) produce no discriminative signal at this model size, as the base Qwen3-0.6B itself scores near zero on them.
- **Thinking mode:** Performance differs substantially between thinking and non-thinking modes across benchmarks. Users should evaluate both modes for their specific use case.
- **Tool calling:** While fine-tuned for tool use, accuracy and reliability of tool calls should be validated for production use cases given the model's compact size.
### Recommendations
- Use human oversight for critical applications
- Perform task-specific evaluation prior to deployment
- Test both thinking and non-thinking modes for your use case
- Validate tool-call outputs before executing them in production
---
## Model Information
| Field | Value |
| ------------ | --------------------------------------------------------------------------- |
| Model name | LittleLamb Tool-Calling |
| Based on | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) |
| Version | 2604 |
| Release date | 28/04/2026 |
| Developed by | Multiverse Computing |
| License | Apache 2.0 |
| Contact | [business@multiversecomputing.com](mailto:business@multiversecomputing.com) |
---
## Citation
If you use this model, please cite the base model and this variant:
```bibtex
@misc{qwen3technicalreport,
 title = {Qwen3 Technical Report},
 author = {Qwen Team},
 year = {2025},
 eprint = {2505.09388},
 archivePrefix = {arXiv},
 primaryClass = {cs.CL},
 url = {https://arxiv.org/abs/2505.09388}
}
@misc{littlelambtc,
 title = {LittleLamb Tool-Calling: Compressed Qwen3-0.6B with Tool-Use via CompactifAI},
 author = {Multiverse Computing},
 year = {2026},
 url = {https://huggingface.co/MultiverseComputingCAI/LittleLamb-ToolCalling},
 note = {Model developed based on Qwen/Qwen3-0.6B using CompactifAI technology, fine-tuned for tool calling}
}
```
**Built by [Multiverse Computing](https://www.multiversecomputing.com)** · [Report an issue](https://huggingface.co/MultiverseComputingCAI/LittleLamb-ToolCalling/discussions) · [Discord](https://discord.gg/cGas9uStqp)