Spaces:

Duplicated from KBaba7/llama.cpp

Jodaro
/

hermes3-llama-cpp

Running

App Files Files Community

hermes3-llama-cpp / app.py

Commit History

Fix history unpacking for Gradio chat interface

9df24f1

Running
verified

Jodaro commited on about 20 hours ago

Reduce max_new_tokens to 64 for faster replies

e6b8d52
verified

Jodaro commited on about 20 hours ago

Switch to TinyLlama 1.1B Chat Q4_K_M

398f222
verified

Jodaro commited on about 20 hours ago

Switch to Llama 3.2 3B Instruct Q4_K_M

863eb49
verified

Jodaro commited on about 20 hours ago

Set ctransformers model_type to qwen

5db6945
verified

Jodaro commited on about 20 hours ago

Switch to Qwen2.5-3B-Instruct Q4_K_M (GGUF)

d966321
verified

Jodaro commited on about 20 hours ago

Fix gradio launch and mistral prompt formatting

807809c
verified

Jodaro commited on about 21 hours ago

Switch to Mistral 7B GGUF

de96a1d
verified

Jodaro commited on about 21 hours ago

Use ctransformers qwen model

0e9e41e
verified

Jodaro commited on about 21 hours ago

Use ctransformers for Qwen

e9ddae9
verified

Jodaro commited on about 21 hours ago

Switch to Qwen3-4B

4323878
verified

Jodaro commited on about 21 hours ago

Switch to llama_cpp

689f1fc
verified

Jodaro commited on about 21 hours ago

Fix model loading (remove hf_model, set model_type)

192caec
verified

Jodaro commited on about 21 hours ago

Create app.py with ctransformers

cbf8005
verified

Jodaro commited on about 21 hours ago