Spaces:

TevunahAi
/

README

Configuration error

rockylynnstein commited on 9 days ago

Commit

149ca2e

verified ·

1 Parent(s): e11aefe

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -94,7 +94,7 @@ Most quantizations use **256 calibration samples**. We use **2048+ diverse sampl
 | Model | Params | Size | vs FP16 | vs FP8 | VRAM | Status |
 |-------|--------|------|---------|--------|------|--------|
 | [granite-34b-code-instruct-8k-Ultra-Hybrid](https://huggingface.co/TevunahAi/granite-34b-code-instruct-8k-Ultra-Hybrid) | 34B | 21.8GB | -68% | -37% | 20.4GB | ✅ Verified |
-| [Llama-3.1-70B-Instruct-Ultra-Hybrid] (https://huggingface.co/TevunahAi/Llama-3.1-70B-Instruct-Ultra-Hybrid) | 70B | 45.4GB | -68% | -37% | 48GB | ✅ Verified |

 | Model | Params | Size | vs FP16 | vs FP8 | VRAM | Status |
 |-------|--------|------|---------|--------|------|--------|
 | [granite-34b-code-instruct-8k-Ultra-Hybrid](https://huggingface.co/TevunahAi/granite-34b-code-instruct-8k-Ultra-Hybrid) | 34B | 21.8GB | -68% | -37% | 20.4GB | ✅ Verified |
+| [Llama-3.1-70B-Instruct-Ultra-Hybrid](https://huggingface.co/TevunahAi/Llama-3.1-70B-Instruct-Ultra-Hybrid)  | 70B | 45.4GB | -68% | -37% | 48GB | ✅ Verified |