embedl
/

Llama-3.2-1B-Instruct-FlashHead-W4A16

text-generation-inference

compressed-tensors

Model card Files Files and versions

WilhelmT commited on 4 days ago

Commit

4a91e70

·

verified ·

1 Parent(s): d8f6738

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ FlashHead matches the baseline **Llama-3.2-1B** within rounding on standard eval
 | **Input / Output** | Text → Text |
 | **Release Date** | 2025-12-08 |
 | **Version** | 1.0 |
-| **Optimizations** | FlashHead LM Head, W4A16|
 | **Developers** | Embedl |
 | **Licenses** | Upstream: Meta Llama 3.2 License. Built with Llama. <br>Optimized components: Embedl Models Community Licence v1.0 *(no redistribution)* |
 | **Intended Use** | Text generation, reasoning, assistant-style interaction, and general-purpose NLP on NVIDIA RTX GPUs |

 | **Input / Output** | Text → Text |
 | **Release Date** | 2025-12-08 |
 | **Version** | 1.0 |
+| **Optimizations** | FlashHead LM Head, Quantization (W4A16)|
 | **Developers** | Embedl |
 | **Licenses** | Upstream: Meta Llama 3.2 License. Built with Llama. <br>Optimized components: Embedl Models Community Licence v1.0 *(no redistribution)* |
 | **Intended Use** | Text generation, reasoning, assistant-style interaction, and general-purpose NLP on NVIDIA RTX GPUs |