Downloads · 30 days
20
47% of all-time downloads
RichardErkhov/aloobun_-_d-Qwen1.5-0.5B-awq
aloobun_-_d-Qwen1.5-0.5B-awq is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
20
47% of all-time downloads
All-time downloads
43
Public
Parameters
464M
483 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors472 MB · 97%
How the weights are stored.
I32308M · 66%
From the Hugging Face model README
Quantization made by Richard Erkhov.
d-Qwen1.5-0.5B - AWQ
license: other license_name: tongyi-qianwen-research license_link: https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE library_name: transformers tags:
Student model, after fine-tuning, improves upon the performance of the basemodel on two benchmarks: truthfulqa and gsm8k
truthfulqa: student = 39.29 vs base = 38.3
gsm8k: student = 17.06 vs base = 16.3
aloobun/d-Qwen1.5-0.5B:
| Avg. | Arc | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---|---|---|---|---|---|---|
| 38.07 | 30.29 | 47.75 | 38.21 | 39.29 | 55.8 | 17.06 |
Qwen/Qwen1.5-0.5B:
| Avg. | Arc | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---|---|---|---|---|---|---|
| 38.62 | 31.48 | 49.05 | 39.35 | 38.3 | 57.22 | 16.3 |
I will train it longer in my next run; can do better.
Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA and the mixture of SWA and full attention.