|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: |
|
|
- Qwen/Qwen3-4B-Thinking-2507 |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- cot |
|
|
- code |
|
|
- gpt_oss |
|
|
- conversational |
|
|
- distillation |
|
|
- math |
|
|
--- |
|
|
This is the bf16 safetensors variant |
|
|
 |
|
|
|
|
|
# What it is |
|
|
DistilGPT-OSS-qwen3-4B is a Qwen3 4B-2507 thinking fine tune, it supports up to **256K** tokens of input and output (aka total context) and can think for up to **65536** tokens when set to **high** reasoning effort. unlike the original qwen3, this model was fine-tuned on GPT-OSS reasoning outputs (unlike Deepseek r1 outputs which qwen3 was probably fine-tuned on for advanced reasoning). By fine-tuning on GPT-OSS outputs, the model was able to learn how to think efficiently, follow instructions better, and the new ability to think with a certain effort based on how much you want it to think. |
|
|
|
|
|
⚠️This model is NOT as censored as the original GPT-OSS, we focused on performance rather than censorship. The model is still safety trained, it would just allow for more *"creative"* prompts, unlike GPT-OSS. We are not responsible for what the model generates. |
|
|
|
|
|
Keep in mind, this is a community project and we are NOT related to qwen by Alibaba nor GPT-OSS by OpenAi. |
|
|
|
|
|
# Format |
|
|
This is the chat format of this model (you can also check the Jinja template file in "Files and versions"): |
|
|
``` |
|
|
<|im_start|>system |
|
|
You are a helpful assistant |
|
|
|
|
|
|
|
|
Reasoning effort: low<|im_end|> |
|
|
<|im_start|>user |
|
|
Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,<|im_end|> |
|
|
<|im_start|>assistant |
|
|
<think> |
|
|
Just continue: 13,21,34,... |
|
|
</think> |
|
|
The Fibonacci sequence continues by adding the two preceding numbers. |
|
|
After **8** the next term is **13** (1 + 8 = 9 – 1 = 8 + 5 = 13), then **21** (8 + 13 = 21), followed by **34** (13 + 21 = 34), and so on. |
|
|
|
|
|
So the sequence starts: |
|
|
|
|
|
**1, 1, 2, 3, 5, 8, 13, 21, 34, …**<|im_end|> |
|
|
``` |
|
|
|
|
|
As you can see, you set the reasoning effort via the system prompt. We recommend going **2** lines down and only then putting "Reasoning effort: [low,medium,high]. For your information that output was generated by our model. |
|
|
|
|
|
# Examples |
|
|
|
|
|
1) "Is a banana an animal?" Reasoning was set to **high**. |
|
|
 |
|
|
2) "Make an HTML website about yourself" Reasoning was set to **medium**. |
|
|
 |
|
|
3) "translate this to chinese: Hello! I am ChatGPT. A large language model by OpenAi." Reasoning was set to **low**. |
|
|
 |
|
|
|
|
|
As you can see, based on the reasoning effort of the model and your prompt, the model would think for a different amount of time. |
|
|
Keep in mind, these tests were done in LM Studio, GGUF q8_0 on a single consumer card (rtx 3080) where we got 95 - 80 Tokens/Second on 8192 context. |
|
|
|
|
|
# Additional information |
|
|
|
|
|
The model was trained using unsloth, using a mix of private datasets and public datasets. |
|
|
|
