Ba2han_-_Tinypus-1.5B-exl2

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Tinypus-1.5B - EXL2

• Model creator: https://huggingface.co/Ba2han/
• Original model: https://huggingface.co/Ba2han/Tinypus-1.5B/

Available sizes

| Branch | Bits | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ | | 8_0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | | 6_5 | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, recommended. | | 5_0 | 5.0 | Slightly lower quality vs 6.5, but usable on 8GB cards. | | 4_25 | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. | | 3_5 | 3.5 | Lower quality, only use if you have to. |

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/Ba2han_-_Tinypus-1.5B-exl2 Tinypus-1.5B-6_5

With huggingface hub:

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch: Linux:

huggingface-cli download Ba2han_-_Tinypus-1.5B-exl2 --revision 6_5 --local-dir Tinypus-1.5B-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download Ba2han_-_Tinypus-1.5B-exl2 --revision 6_5 --local-dir Tinypus-1.5B-6.5 --local-dir-use-symlinks False

Original model description:

license: mit datasets:

• garage-bAInd/Open-Platypus pipeline_tag: text-generation

---

*drumroll please*

Introducing Tinypus!

I passthrough merged base Tiny Llama Chat with itself, then fine-tuned with around 1/3 of Platypus dataset.

Observations:

• It's smarter (I think?)

• It sometimes throws "### Instruction:" line. This could be due to the platypus dataset, or the fact that I know jackshit about programming. You can add it to "custom stopping strings" in oobaboga.

• It may be possible to train very specialized mini experts and merge them???

  Template

  Same with TinyLlama/TinyLlama-1.1B-Chat-v1.0

Merge details

slices:

• sources:

  • model: E://text-generation-webui//models//TinyLlama

    layer_range: [0, 12]

• sources:

  • model: E://text-generation-webui//models//TinyLlama

    layer_range: [4, 22]

merge_method: passthrough

dtype: bfloat16

QLoRA Details

Chunk Length: 1152 R/A: 64/128 Epoch: 1 q-k-v-o