[GH-ISSUE #622] How to add a new model with a .pth file ? #62313

Closed
opened 2026-05-03 08:10:21 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @GautierT on GitHub (Sep 27, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/622

Hi.

I would like to use ollama with https://huggingface.co/manu/mistral-7B-v0.1.

The files available are :

tokenizer.model
consolidated.00.pth
params.json
RELEASE

Thanks.

Originally created by @GautierT on GitHub (Sep 27, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/622 Hi. I would like to use ollama with https://huggingface.co/manu/mistral-7B-v0.1. The files available are : ``` tokenizer.model consolidated.00.pth params.json RELEASE ``` Thanks.
Author
Owner

@mxyng commented on GitHub (Sep 27, 2023):

mistral 7b is available in the library. However if you want to add it from original weights, you'll need to convert it to gguf and optionally quantize. more information can be found in llama.cpp

<!-- gh-comment-id:1738019394 --> @mxyng commented on GitHub (Sep 27, 2023): mistral 7b is available in the [library](https://ollama.ai/library/mistral). However if you want to add it from original weights, you'll need to convert it to gguf and optionally quantize. more information can be found in [llama.cpp](https://github.com/ggerganov/llama.cpp#prepare-data--run)
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#62313