Files
Quark-50m/README.md
ModelHub XC c886f7fbd6 初始化项目,由ModelHub XC社区提供模型
Model: OvercastLab/Quark-50m
Source: Original Platform
2026-07-05 08:06:17 +08:00

124 lines
4.4 KiB
Markdown
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
language:
- en
- code
license: apache-2.0
tags:
- smol
- pretraining
- instruct
- 50M
- causal-lm
- gqa
- swiglu
- rmsnorm
datasets:
- HuggingFaceTB/smollm-corpus
metrics:
- perplexity
model-index:
- name: Quark-50m-Instruct
results: []
pipeline_tag: text-generation
---
# Quark-50m-Instruct
**Quark-50m-Instruct** is a small (≈56M parameters) decoder-only language model, fine-tuned for instruction following.
It is built on the same architecture of “SmolLM” family and was fully pretrained on 5 billion tokens from
[HuggingFaceTB/smollmcorpus](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus).
- **Model type:** Causal Language Model (LLaMAstyle decoder)
- **Architecture:** GQA · SwiGLU · RMSNorm · RoPE · Weighttying
- **Pretraining tokens:** 5B
- **Finetuning:** Instructiontuned (details below)
- **Creators:** [OvercastLab](https://huggingface.co/OvercastLab) (research & development lab for ML/AI)
- **Release date:** 22 April 2026
## Model Summary
Quark-50m-Instruct is designed to be an efficient assistant that can run on consumer GPUs (e.g., RTX 3070 with 8GB VRAM)
and even on CPU for light workloads. It is **not** competitive with large models on knowledgeintensive tasks,
but it excels at:
- Simple conversational tasks
- Code generation and explanation (Python)
- Short text rewriting and summarisation
- Ondevice / edge inference
The architecture closely follows the efficientsmallLM blueprint popularised by SmolLM:
| Component | Details |
|-------------|-------------------------------|
| Vocab size | 49,152 |
| Hidden size | 384 |
| Layers | 24 |
| Attention | Grouped Query (6 Q heads, 2 KV heads) |
| FFN | SwiGLU with 1,024 intermediate |
| Position | RoPE (θ = 10,000) |
| Normalisation | RMSNorm (preblock) |
Total trainable parameters: **≈48M** (with weight tying).
### Benchmark Evaluation Metrics
| Category | Benchmark | Metric | Score / Value | Status |
| :--- | :--- | :--- | :---: | :---: |
| **Linguistics & Grammar** | BLiMP | Accuracy | 68.12% | Success |
| **Commonsense & Reasoning** | PIQA | Normalized Accuracy | 57.83% | Success |
| | COPA | Accuracy | 57.00% | Success |
| | BoolQ | Accuracy | 52.17% | Success |
| | WinoGrande | Accuracy | 47.36% | Success |
| | HellaSwag | Normalized Accuracy | 28.49% | Success |
| | RACE | Accuracy | 26.41% | Success |
| | CommonsenseQA | Accuracy | 20.31% | Success |
| **Academic & Knowledge** | SciQ | Normalized Accuracy | 49.00% | Success |
| | ARC-Easy | Normalized Accuracy | 36.49% | Success |
| | MMLU | Accuracy | 25.64% | Success |
| | ARC-Challenge | Normalized Accuracy | 25.17% | Success |
| | OpenBookQA | Normalized Accuracy | 25.40% | Success |
| **Language Modeling** | LAMBADA | Accuracy | 15.87% | Success |
| | WikiText-2 | Word Perplexity | 251.76 | Success |
*Note: The Arithmetic benchmark failed due to outdated script support (`arithmetic.py`), and SocialIQA failed due to a registration tag error (`siqa`). Total baseline execution completed successfully for all other 15 tasks.*
## Uses
### Direct Use
The model can be used via the 🤗 Transformers library for standard text generation.
It expects chatformatted input (see example below).
### Downstream Use
Because of the open Apache2.0 license, you may finetune Quark-50mInstruct on your own data for
domainspecific tasks for instance, a customersupport bot, a code reviewer, or a story writer.
### Limitations
- Limited world knowledge (stopped at mid2025 pretraining data).
- Short context window (2,048 tokens).
- Small size means it can make more factual mistakes than larger models.
## How to Get Started
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "ThingAI/Quark-50m-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
messages = [
{"role": "system", "content": "You are Quark, a helpful assistant."},
{"role": "user", "content": "Explain group query attention in one sentence."}
]
inputs = tokenizer.apply_chat_template(
messages,
tokenize=True,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
outputs = model.generate(inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))