not working with Ollama
something is not correct with Ollama with this model
when I use ollama run hf.co/prithivMLmods/chandra-ocr-2-GGUF:Q5_K_M, I get the following error :
500: unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-c5e3df32bfa20d0a822fdc635d3849f5d53e2049535cd85753df4fd762bdd276
I also tried to create custom model with the following modelfile (similar to qwen 3.5 modelfile)
FROM hf.co/prithivMLmods/chandra-ocr-2-GGUF:Q5_K_M
TEMPLATE {{ .Prompt }}
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER presence_penalty 1.5
PARAMETER temperature 1
PARAMETER top_k 20
PARAMETER top_p 0.95
can you please test it?
Hi @ahmgam ,
I didn’t test it on Ollama, but I tested it with llama.cpp and it works fine.
So, it should work well on Ollama too!
Clean the broken model:
rm -rf /usr/share/ollama/.ollama/models/blobs/sha256-c5e3df32bfa20d0a822fdc635d3849f5d53e2049535cd85753df4fd762bdd276
Then also remove the model reference:
ollama rm hf.co/prithivMLmods/chandra-ocr-2-GGUF:Q5_K_M
Re-pull the model
ollama run hf.co/prithivMLmods/chandra-ocr-2-GGUF:Q5_K_M
Try the FIX !!
I repeated the same steps again, I removed everything and downloaded it again, still getting the same error
Error: 500
{"error":"unable to load model: /root/.ollama/models/blobs/sha256-c5e3df32bfa20d0a822fdc635d3849f5d53e2049535cd85753df4fd762bdd276"}
any update?