Downloads · 30 days
0
LL2-13B-FIMFiction-QLORA-GGML
Nikolai1902/LL2-13B-FIMFiction-QLORA-GGML
LL2-13B-FIMFiction-QLORA-GGML is a machine learning model from Nikolai1902. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as wtfpl.
This model was a QLoRA of LLaMA 2-13B base finetuned on the FIMFiction archive and then merged with the base model (as most GGML loading apps don't support LoRAs), and quantized for llama.cpp-based frontends. Was trai…
Access
Public
Updated Aug 30, 2023
Repo size
16.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin16.6 GB · 100%
At a glance
- License
- wtfpl
- Access
- Public
- Created
- Aug 29, 2023
- Updated
- Aug 30, 2023
- SHA
- 6040c6b9
Model card
From the Hugging Face model README
This model was a QLoRA of LLaMA 2-13B base finetuned on the FIMFiction archive and then merged with the base model (as most GGML loading apps don't support LoRAs), and quantized for llama.cpp-based frontends. Was trained with 1024 context length
There are two options, depending on the resources you have:
- Q5_K_M: Low quality loss K-quantized 5 bits model. Max RAM consumption is 11.73 GB, recommended if you have 12GB of VRAM to load 40 layers
- Q4_K_S: Compact K-quantized 4 bits. Max RAM consumption is 9.87 GB
This not an instruction tuned model, it was trained on raw text, so treat it like an autocomplete. Seems sensitive to formatting: I found it's usually better at staying on topic when using double spacing in the prompt.
Only tags excluded from the dataset are eqg and humanized.
- License
- wtfpl
- Created
- Aug 29, 2023
- Updated
- Aug 30, 2023