Commit History
-
Add base model to table
666f167 -
Upload 4 files for base model
https://huggingface.co/jbochi/coedit-base - sha 23419e968ed460dd8fb9dfe9c48862eefe480aca Commands: ```bash cargo run --example tensor-tools --release -- quantize --quantization q4k ~/Downloads/model.safetensors --out-file model-base-q4k.gguf cargo run --example tensor-tools --release -- quantize --quantization q4_0 ~/Downloads/model.safetensors --out-file model-base-q4_0.gguf cargo run --example tensor-tools --release -- quantize --quantization q6k ~/Downloads/model.safetensors --out-file model-base.gguf ```d920a61 -
Add small models to the table
37933ed -
Upload model-small.gguf
`RUST_BACKTRACE=1 cargo run --example tensor-tools --release -- quantize --quantization q6k ~/Downloads/model.safetensors --out-file model-small.gguf`4ab0730 -
Add quantized files for small model
Original weights from https://huggingface.co/jbochi/coedit-small/tree/main, commit 2adfb5acd818975db82ed140400edaf8ca562107c8a22c1 -
Fix license to match base model
11f8f25
-
Update README.md
c8b20e4 -
Update README.md
68c05f3 -
Update README.md
544c6e9 -
Update README.md
e2e3e68 -
Upload model-xxl-q4_0.gguf with huggingface_hub
d50a3c6 -
Upload model-xxl-q4k.gguf with huggingface_hub
4727211 -
List all models
ca8442b -
Rename model_xl_q4k.gguf to model-xl-q4k.gguf
4ae6405 -
Rename model_xl_q4_0.gguf to model-xl-q4_0.gguf
7371515 -
Rename model_q4k.gguf to model-q4k.gguf
7591d00 -
Rename model_q4_0.gguf to model-q4_0.gguf
87e1233 -
Upload model-xxl.gguf with huggingface_hub
6304a69 -
Add q4_0 and q4 quantized models for large and xl
Verified signaturef56229a -
Upload model-xxl.gguf with huggingface_hub
07e57b5 -
Add config-xxl.json
Copied from https://huggingface.co/grammarly/coedit-xxl/blob/main/config.jsone4ad648 -
Add a section explaining how to use the model
3251ce4 -
Add xl config
Verified signature04265ed -
Add quantized model-xl
Verified signature18468f2 -
Abbreviate example titles
Verified signaturea6b00c3 -
Add example inputs
Verified signatured22b4fa -
Add instructions to quantize model (#1)
- Add instructions to quantize model (e40158bf0962d8ab7acd6ef5388b1f1f4e550ea8)67bb427 -
Add weights
Verified signature624e9bd -
Update gitattributes
Verified signaturef570662 -
Update README.md
043be07 -
initial commit
4a5a2c3