Update README.md
Browse files
README.md
CHANGED
@@ -67,22 +67,22 @@ $ cargo run --example quantized-t5 --release -- \
|
|
67 |
|
68 |
## Models available
|
69 |
|
70 |
-
These are all the available formats. Weight file is named `{
|
71 |
|
72 |
| Model | Base model | Quantization | # Params | Size |
|
73 |
| ----- | ---------- | ------------ | ------ | ---- |
|
74 |
| - | [large](https://huggingface.co/grammarly/coedit-large) | None | 770M | 3.13 GB |
|
75 |
| model | large | 6k | 770M | 643 MB |
|
76 |
-
| model-
|
77 |
-
| model-
|
78 |
| | [xl](https://huggingface.co/grammarly/coedit-xl) | None | 3B | 11.4 GB |
|
79 |
| model-xl | xl | 6k | 3B | 2.34 GB |
|
80 |
-
| model-xl-
|
81 |
-
| model-xl-
|
82 |
| - | [xxl](https://huggingface.co/grammarly/coedit-xxl) | None | 11B | 44.5 GB |
|
83 |
| model-xxl | xxl | 6k | 11B | 9.14 GB |
|
84 |
-
| model-xxl-
|
85 |
-
| model-xxl-
|
86 |
|
87 |
|
88 |
## Model generation
|
|
|
67 |
|
68 |
## Models available
|
69 |
|
70 |
+
These are all the available formats. Weight file is named `{model}.gguf` and the config file is `config-{base_model}.json`
|
71 |
|
72 |
| Model | Base model | Quantization | # Params | Size |
|
73 |
| ----- | ---------- | ------------ | ------ | ---- |
|
74 |
| - | [large](https://huggingface.co/grammarly/coedit-large) | None | 770M | 3.13 GB |
|
75 |
| model | large | 6k | 770M | 643 MB |
|
76 |
+
| model-q4k | large | 4k | 770M | 441 MB |
|
77 |
+
| model-q4_0 | large | 4_0 | 770M | 441 MB |
|
78 |
| | [xl](https://huggingface.co/grammarly/coedit-xl) | None | 3B | 11.4 GB |
|
79 |
| model-xl | xl | 6k | 3B | 2.34 GB |
|
80 |
+
| model-xl-q4k | xl | 4k | 3B | 1.6 GB |
|
81 |
+
| model-xl-q4_0 | xl | 4_0 | 3B | 1.6 GB |
|
82 |
| - | [xxl](https://huggingface.co/grammarly/coedit-xxl) | None | 11B | 44.5 GB |
|
83 |
| model-xxl | xxl | 6k | 11B | 9.14 GB |
|
84 |
+
| model-xxl-q4k | xxl | 4k | 11B | 6.27 GB |
|
85 |
+
| model-xxl-q4_0 | xxl | 4_0 | 11B | 6.27 GB |
|
86 |
|
87 |
|
88 |
## Model generation
|