Issues
- 1
Error when using python code example
#102 opened by Zolilio - 0
Moondream 3?
#104 opened by nikshepsvn - 3
Moondream for Object Localization
#101 opened by E5GEN2 - 4
Has anyone exported ONNX model?
#88 opened by jamjamjon - 0
Hi, how to train the model
#103 opened by lucasjinreal - 1
How to run on llama.cpp
#96 opened by M3Dade - 0
Has Moondream be tried with Microsoft DirectML?
#100 opened by Tsardoz - 5
- 2
False positives - Trying model out for security and suspicious activity monitoring
#93 opened by BChip - 1
Moondream doesn't generate prompts for me
#98 opened by ALBIHANY - 0
Pre-train
#97 opened by fakerybakery - 10
Multiple images
#56 opened by fakerybakery - 4
PEFT LoRA with gradient checkpointing
#91 opened by rockerBOO - 0
New model changed ?
#94 opened by R3xpook - 2
Support running eval scripts on multiple GPUs
#69 opened by vikhyat - 5
- 5
Availability On Ollama
#62 opened by jeffreylm - 1
- 0
Guidance on using newer Phi-3 model family?
#90 opened by gadkins - 1
cannot run moondream in Ollama (ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: 3221225477 ")
#89 opened by prithvi151080 - 3
unknown model
#65 opened by T8star1984 - 3
API Endpoint Recommendation
#87 opened by RonanKMcGovern - 7
How does the model work?
#84 opened by yukiarimo - 2
Regarding the foundation model
#81 opened by lingyezhixing - 2
Close some issues
#83 opened by KPCOFGS - 1
Was this NOT trained on NSFW images?
#85 opened by CoffeeShifter - 2
Request: Parameterize Prompt?
#77 opened - 3
- 2
Larger images for detail recognition?
#80 opened by yukiarimo - 0
lnqa dataset
#74 opened by jasonallen - 1
Question about LLM
#73 opened by upq - 0
can't see tables or dividers
#76 opened by andres808 - 3
Finetuning
#57 opened by fakerybakery - 9
Flash attention 2 not working, "Moondream does not support Flash Attention 2.0 yet."
#63 opened by ProGamerGov - 0
- 0
Q: Vision encoder dataset?
#72 opened by kotx - 0
training code?
#71 opened by 04RR - 2
Nvidia Jetson runtime failure
#68 opened by Links17 - 5
Issue while using Moondream in ComfyUI
#67 opened by thoughtfission - 2
Dataset Info
#61 opened by vishhvak - 5
unknown model
#64 opened by Asianfleet - 1
How do we use video_gradio_demo.py ??
#52 opened by dabeckham - 1
CPU inference under 8gb(Q4/Q8).
#60 opened by VatsaDev - 1
Compare image embedding and text embedding
#66 opened by Sangeeth-versos - 1
Suggestions for future model
#53 opened by Vigilence - 3
- 3
Does not understands questions
#55 opened by PierrunoYT - 4
- 12
Tensor size mismatch
#50 opened by JohnnyStreet - 3