deepseek-ai / deepseek-ai/Janus
running with ollama on mac M3 failed with: "error loading model: missing tensor 'token_embd.weight'"
- Dominant language
- Python
- Stars
- 17.8k
- Forks
- 2.2k
- PR merge metrics
- No merged PRs in 30d
Description
tried on Mac M3 (36 Gb RAM): but got an error
```
ollama run ozbillwang/deepseek-janus-pro
pulling manifest
pulling a338945d54b9... 100% ▕██████████████████████████████████████▏ 4.6 MB
pulling f0fd86e87432... 100% ▕██████████████████████████████████████▏ 353 B
verifying sha256 digest
writing manifest
success
Error: llama runner process has terminated: error loading model: missing tensor 'token_embd.weight
```
....
An idea on how to fix this issue ?
- Perhaps a configuration issue with ollama ? (my ollama version is 0.5.7) ?
- Or a missing piece in the model ?
May be too young to test...
Thanks for your kind answer
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.