Getting `Error: unexpected status code 200` when pulling a model from an internal registry v0.3.1 and above

### What is the issue? Starting version 0.3.1, when pulling a model from an internal registry (https://distribution.github.io/distribution/), I'm getting the error `unexpected status code 200`. Version up to 0.3.0 worked properly with this setup. The line returning the error seems to be https://github.com/ollama/ollama/compare/v0.3.0...v0.3.1#diff-9e32d213fc229fc9c327863932f4fc8a875d854333b5ad2dffa9b43fd0848232R226 # How to reproduce Via docker-compose, I create a test environment with ollama and registry. ``` version: "3" services: ollama: image: ollama/ollama:0.3.0 ports: - "11434" registry: image: registry:2 environment: REGISTRY_LOG_LEVEL: debug REGISTRY_LOG_ACCESSLOG_DISABLED: "false" ports: - "5000" ``` Start the test stack via `docker compose up -d`. In the snippet above, I'm using ollama v0.3.0. The following commands will pull a model (qwen2:0.5b for sake of size), and push it to the local registry. ``` docker compose exec ollama ollama pull qwen2:0.5b docker compose exec ollama ollama cp qwen2:0.5b registry:5000/library/qwen2:0.5b docker compose exec ollama ollama push registry:5000/library/qwen2:0.5b --insecure ``` Now the models can be remove from ollama: ``` docker compose exec ollama ollama rm qwen2:0.5b registry:5000/library/qwen2:0.5b ``` And re-downloaded from the local registry: ``` docker compose exec ollama ollama pull registry:5000/library/qwen2:0.5b --insecure ``` With ollama version up to 0.3.0 (included), this works. With ollama version from 0.3.1 (included), I'm getting the following error: ``` Error: unexpected status code 200 ``` ### OS Docker ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.3.1 and above