Add model card metadata
Browse files
README.md
CHANGED
|
@@ -1,8 +1,25 @@
|
|
| 1 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
# Kat-Dev 72B (GGUF)
|
| 3 |
|
| 4 |
Quantized builds of the KAT-Dev 72B coding model for Ollama / llama.cpp runtimes. Each variant ships with the matching Modelfile generated from the Ollama registry export.
|
| 5 |
|
|
|
|
|
|
|
| 6 |
## Variants
|
| 7 |
|
| 8 |
| Variant | Size | Blob |
|
|
|
|
| 1 |
|
| 2 |
+
---
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Kwaipilot/KAT-Dev-72B-Exp
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
library_name: llama.cpp
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
+
tags:
|
| 10 |
+
- gguf
|
| 11 |
+
- quantized
|
| 12 |
+
- ollama
|
| 13 |
+
- text-generation
|
| 14 |
+
quantized_by: richardyoung
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
# Kat-Dev 72B (GGUF)
|
| 18 |
|
| 19 |
Quantized builds of the KAT-Dev 72B coding model for Ollama / llama.cpp runtimes. Each variant ships with the matching Modelfile generated from the Ollama registry export.
|
| 20 |
|
| 21 |
+
These binaries are derived from the upstream [`Kwaipilot/KAT-Dev-72B-Exp`](https://huggingface.co/Kwaipilot/KAT-Dev-72B-Exp) release (Apache-2.0). The goal is to provide ready-to-run GGUF artifacts for local inference stacks such as Ollama and llama.cpp.
|
| 22 |
+
|
| 23 |
## Variants
|
| 24 |
|
| 25 |
| Variant | Size | Blob |
|