|
|
--- |
|
|
base_model: Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427 |
|
|
tags: |
|
|
- llama-cpp |
|
|
- gguf-my-repo |
|
|
- code |
|
|
- math |
|
|
- cot |
|
|
- conversational |
|
|
- moe |
|
|
- Superthoughts |
|
|
language: |
|
|
- en |
|
|
license: llama3.2 |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
# Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427-Q8_0-GGUF |
|
|
This model was converted to GGUF format from [`Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427`](https://huggingface.co/Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. |
|
|
Refer to the [original model card](https://huggingface.co/Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427) for more details on the model. |
|
|
|
|
|
## ⚠️THIS MODEL IS EXPERIMENTAL!! |
|
|
|
|
|
 |
|
|
After more than two months since the release of superthoughts lite v1, we finally release the new version. **v2** |
|
|
Unlike the first generation of superthoughts lite, this model is a MoE (Mixture of experts), of 4 special fine-tuned experts based off of llama-3.2-1B models. |
|
|
# Information |
|
|
- In GGUF Q8_0, the model runs at ~8 tokens per second on a Snapdragon 8 Gen 2 with 12GB of ram, which is faster than Pinkstack/PARM-V2-QwQ-Qwen-2.5-o1-3B-GGUF (which runs at ~5 tokens a second). |
|
|
- The chat expert was fine tuned on 23 different languages for 2 epochs, but the model should still only be used for english-to-english generation. |
|
|
- This model has a total of 3.91B parameters, and 2 experts are active with each token. There is an expert for math, code, general conversations and medical situations. |
|
|
- Long context: the model supports up to **131,072** input tokens, and can generate up to **16,384** tokens. |
|
|
- To enable proper reasoning, set this as the system prompt: |
|
|
``` |
|
|
You are Superthoughts lite v2 by Pinkstack, which thinks before answering user questions. always respond in the following format:\n<think>\n(Your thinking process\n</think>\n(Your final output). |
|
|
``` |
|
|
⚠️ Due to the nature of an experimental model, it may fall into reasoning loops; users are responsible for all outputs from this model. |
|
|
This experimental model is more of a proof-of-concept for now. It fully works and it has some pretty nice performance, for having less than 2 billion parameters activated per token. |
|
|
|
|
|
**If you have any questions, feel free to open a "New Discussion".** |
|
|
|
|
|
## Use with llama.cpp |
|
|
Install llama.cpp through brew (works on Mac and Linux) |
|
|
|
|
|
```bash |
|
|
brew install llama.cpp |
|
|
|
|
|
``` |
|
|
Invoke the llama.cpp server or the CLI. |
|
|
|
|
|
### CLI: |
|
|
```bash |
|
|
llama-cli --hf-repo Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427-Q8_0-GGUF --hf-file superthoughts-lite-v2-moe-llama3.2-experimental-0427-q8_0.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
|
|
|
### Server: |
|
|
```bash |
|
|
llama-server --hf-repo Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-experimental-0427-Q8_0-GGUF --hf-file superthoughts-lite-v2-moe-llama3.2-experimental-0427-q8_0.gguf -c 2048 |
|
|
``` |
