Downloads · 30 days
26
27% of all-time downloads
Experimental-DeepSeek-V2-Coder-Lite-JUMP-alpha1
adamo1139/Experimental-DeepSeek-V2-Coder-Lite-JUMP-alpha1
Experimental-DeepSeek-V2-Coder-Lite-JUMP-alpha1 is a machine learning model from adamo1139. 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 other.
DeepSeek-Coder-V2-Lite-Base finetuned for 0.25 epochs on adamo1139/ise-uiucMagicoder-Evol-Instruct-110K-ShareGPT via llama-factory at 3000ctx with qlora, rank 32 and alpha 32.
All-time downloads
95
Public
Parameters
15.7B
31.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors31.4 GB · 100%
At a glance
- License
- other
- Model type
- deepseek_v2
- Access
- Public
- Created
- Sep 1, 2024
- Updated
- Sep 1, 2024
- SHA
- 0d310cfe
Model card
From the Hugging Face model README
DeepSeek-Coder-V2-Lite-Base finetuned for 0.25 epochs on adamo1139/ise-uiuc_Magicoder-Evol-Instruct-110K-ShareGPT via llama-factory at 3000ctx with qlora, rank 32 and alpha 32.
Prompt format is ChatML but ChatML-specific tokens are not in the tokenizer, so it's sometimes spilling random tokens. Definitely something to fix in the next version.
It's an early WIP, unless you are dying to try DeepSeek-Coder-V2-Lite finetunes I suggest you don't use it :)
- Type
- deepseek_v2
- License
- other
- Created
- Sep 1, 2024
- Updated
- Sep 1, 2024