Downloads · 30 days
24
4% of all-time downloads
yukimnb62/qwen3_5-9b-toolv2-final-gguf
qwen3_5-9b-toolv2-final-gguf is a machine learning model from yukimnb62. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
--- basemodel: yukimnb62/qwen35-9b-toolv2-final tags: - gguf - llama.cpp - qwen - template-structured license: apache-2.0 ---
Downloads · 30 days
24
4% of all-time downloads
All-time downloads
555
Public
Repo size
33.1 GB
Likes
0
Public
Click a slice to open those files.
.gguf33.1 GB · 100%
From the Hugging Face model README
base_model: yukimnb62/qwen3_5-9b-toolv2-final
tags:
- gguf
- llama.cpp
- qwen
- template-structured
license: apache-2.0
---
# yukimnb62/qwen3_5-9b-toolv2-final-gguf
GGUF convertido desde el checkpoint merged `yukimnb62/qwen3_5-9b-toolv2-final` con `llama.cpp`.
- Source merged model: `yukimnb62/qwen3_5-9b-toolv2-final`
- Conversion outtype: `bf16`
- Quantized variants: `Q8_0`, `Q4_K_M`
## Files
- `qwen3_5-9b-toolv2-final-bf16.gguf`
qwen3_5-9b-toolv2-final-q8_0.gguf
qwen3_5-9b-toolv2-final-q4_k_m.gguf
## Uso sugerido con llama.cpp
Este modelo viene de un entrenamiento donde el contrato de salida principal es un template XML propio.
Si quieres respetar ese comportamiento, usa prompt plano y evita que tu cliente aplique un chat template por encima.
Ejemplo con `llama-cli`:
```bash
llama-cli -m qwen3_5-9b-toolv2-final-bf16.gguf -p "podrias decirme el contenido completo del archivo hola.txt?" -n 1024 --temp 0
```