Qwen2.5-7B-Instruct-1M-GGUF

Original Model

Qwen/Qwen2.5-7B-Instruct-1M

Run with Gaianet

Prompt template

prompt template: chatml

Context size

chat_ctx_size: 1010000 (generation 8192 tokens)

Run with GaiaNet

Quantized with llama.cpp b4466

Downloads last month
184
GGUF
Model size
7.62B params
Architecture
qwen2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.