Praz314159/Model_Zoo

Remove authentication for ungated Qwen model

Force rebuild with Qwen2.5-7B

Switch to Qwen2.5-7B-Instruct

Switch to Mistral-7B-Instruct-v0.3

Switch to Zephyr-7B-beta (truly ungated model)

Switch to Mistral-7B-Instruct-v0.1 (ungated model)

Switch to Mistral-7B-Instruct-v0.3 for faster inference

Force rebuild - Deploy Qwen2.5-72B with 4xL4 tensor parallelism

Switch to Qwen2.5-72B-Instruct with 4xL4 GPU tensor parallelism and NF4 quantization

Fix TGI Numba caching issues - comprehensive environment setup

Fix TGI Docker image - use v1.4 with Python dependencies

Replace Ollama with TGI for high-performance inference

Revert to ENTRYPOINT and fix Ollama permissions with /tmp directory

Fix startup by using CMD instead of ENTRYPOINT for HF Spaces

Fix Ollama permissions by using /tmp directory

Fix entrypoint to ensure startup script executes

Initial deployment of Annotation Army Model Zoo with Ollama and multiple LLMs

initial commit