[GH-ISSUE #437] Error downloading manifest with llama2-uncensored:70b #62243

Closed
opened 2026-05-03 07:58:53 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @satvikpendem on GitHub (Aug 28, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/437

I am on macOS. I run ollama run llama2-uncensored:70b and get the following:

pulling manifest
pulling 47f73cb430c8... 100% |██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (39/39 GB, 60 MB/s)
pulling 750599e5d655... 100% |██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (40/40 B, 124 kB/s)
Error: download failed: Get "https://registry.ollama.ai/v2/library/llama2-uncensored/blobs/sha256:c3916a776ed02180603497f012bbdb04375d9597b3e660d7fb4051c4d4011c9c": dial tcp: lookup registry.ollama.ai: no such host

I try running ollama run llama2-uncensored:70b again and I get:

pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2-uncensored/manifests/70b": dial tcp: lookup registry.ollama.ai: no such host

When I go to the manifests URL, I get the following JSON response:

{
  "errors": [
    {
      "code": "MANIFEST_INVALID",
      "message": "manifest invalid",
      "detail": {}
    }
  ]
}
Originally created by @satvikpendem on GitHub (Aug 28, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/437 I am on macOS. I run `ollama run llama2-uncensored:70b` and get the following: ```sh pulling manifest pulling 47f73cb430c8... 100% |██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (39/39 GB, 60 MB/s) pulling 750599e5d655... 100% |██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| (40/40 B, 124 kB/s) Error: download failed: Get "https://registry.ollama.ai/v2/library/llama2-uncensored/blobs/sha256:c3916a776ed02180603497f012bbdb04375d9597b3e660d7fb4051c4d4011c9c": dial tcp: lookup registry.ollama.ai: no such host ``` I try running `ollama run llama2-uncensored:70b` again and I get: ```sh pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2-uncensored/manifests/70b": dial tcp: lookup registry.ollama.ai: no such host ``` When I go to the [manifests URL](https://registry.ollama.ai/v2/library/llama2-uncensored/manifests/70b), I get the following JSON response: ```json { "errors": [ { "code": "MANIFEST_INVALID", "message": "manifest invalid", "detail": {} } ] } ```
Author
Owner

@mxyng commented on GitHub (Aug 28, 2023):

@satvikpendem there was some downtime today as we did maintenance on the website which is very likely the cause of the no such host error. This has since been resolved.

The manifest URL requires HTTP Accept header to be set correctly in order to succeed:

No Accept header:

$ curl -X GET https://registry.ollama.ai/v2/library/llama2-uncensored/manifests/70b                                                                 
{"errors":[{"code":"MANIFEST_INVALID","message":"manifest invalid","detail":{}}]}

Accept header

$ curl -X GET -H 'Accept:application/vnd.docker.distribution.manifest.v2+json' https://registry.ollama.ai/v2/library/llama2-uncensored/manifests/70b
{"schemaVersion": 2, "mediaType": "application/vnd.docker.distribution.manifest.v2+json", "config": {"mediaType": "application/vnd.docker.container.image.v1+json", "digest": "sha256:e98016e5e7464e62fdce70dc9e7c96e6cd23c7decbbc8cd4e921ab0ecaa9218f", "size": 299}, "layers": [{"mediaType": "application/vnd.ollama.image.model", "digest": "sha256:47f73cb430c82d0b053ef00ce91342dc1ef9fa78044d14eb6a7dd8a340328d72", "size": 38871961216}, {"mediaType": "application/vnd.ollama.image.template", "digest": "sha256:750599e5d65508737b7dd348f9f0f64c39b04965e3743b8b6832e867d74a8db8", "size": 40}, {"mediaType": "application/vnd.ollama.image.params", "digest": "sha256:c3916a776ed02180603497f012bbdb04375d9597b3e660d7fb4051c4d4011c9c", "size": 13}]}
<!-- gh-comment-id:1696550198 --> @mxyng commented on GitHub (Aug 28, 2023): @satvikpendem there was some downtime today as we did maintenance on the website which is very likely the cause of the `no such host` error. This has since been resolved. The manifest URL requires HTTP Accept header to be set correctly in order to succeed: No `Accept` header: ``` $ curl -X GET https://registry.ollama.ai/v2/library/llama2-uncensored/manifests/70b {"errors":[{"code":"MANIFEST_INVALID","message":"manifest invalid","detail":{}}]} ``` `Accept` header ``` $ curl -X GET -H 'Accept:application/vnd.docker.distribution.manifest.v2+json' https://registry.ollama.ai/v2/library/llama2-uncensored/manifests/70b {"schemaVersion": 2, "mediaType": "application/vnd.docker.distribution.manifest.v2+json", "config": {"mediaType": "application/vnd.docker.container.image.v1+json", "digest": "sha256:e98016e5e7464e62fdce70dc9e7c96e6cd23c7decbbc8cd4e921ab0ecaa9218f", "size": 299}, "layers": [{"mediaType": "application/vnd.ollama.image.model", "digest": "sha256:47f73cb430c82d0b053ef00ce91342dc1ef9fa78044d14eb6a7dd8a340328d72", "size": 38871961216}, {"mediaType": "application/vnd.ollama.image.template", "digest": "sha256:750599e5d65508737b7dd348f9f0f64c39b04965e3743b8b6832e867d74a8db8", "size": 40}, {"mediaType": "application/vnd.ollama.image.params", "digest": "sha256:c3916a776ed02180603497f012bbdb04375d9597b3e660d7fb4051c4d4011c9c", "size": 13}]} ```
Author
Owner

@jmorganca commented on GitHub (Aug 29, 2023):

Thanks for creating an issue! As to what @mxyng mentioned, going to mark this as closed but please do re-open it if you see it again.

<!-- gh-comment-id:1697624822 --> @jmorganca commented on GitHub (Aug 29, 2023): Thanks for creating an issue! As to what @mxyng mentioned, going to mark this as closed but please do re-open it if you see it again.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#62243