Update README.md
Browse files
README.md
CHANGED
@@ -78,7 +78,7 @@ The 8 bit GPTQ quant has minimum quality degradation from the original `bfloat16
|
|
78 |
|
79 |
| Branch | Bits | Group Size | Act Order | Damp % | GPTQ Dataset | Sequence Length | VRAM Size | ExLlama | Description |
|
80 |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
|
81 |
-
| [main](https://huggingface.co/astronomer-io/Llama-3-8B-Instruct-GPTQ-8-Bit/tree/main) | 8 |
|
82 |
| More variants to come | TBD | TBD | TBD | TBD | TBD | TBD | TBD | TBD | May upload additional variants of GPTQ 8 bit models in the future using different parameters such as 128g group size and etc. |
|
83 |
|
84 |
## Serving this GPTQ model using vLLM
|
|
|
78 |
|
79 |
| Branch | Bits | Group Size | Act Order | Damp % | GPTQ Dataset | Sequence Length | VRAM Size | ExLlama | Description |
|
80 |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
|
81 |
+
| [main](https://huggingface.co/astronomer-io/Llama-3-8B-Instruct-GPTQ-8-Bit/tree/main) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 9.09 GB | No | 8-bit, with Act Order and group size 32g. Minimum accuracy loss with decent VRAM usage reduction. |
|
82 |
| More variants to come | TBD | TBD | TBD | TBD | TBD | TBD | TBD | TBD | May upload additional variants of GPTQ 8 bit models in the future using different parameters such as 128g group size and etc. |
|
83 |
|
84 |
## Serving this GPTQ model using vLLM
|