# Why the model provide an error response ever time **URL:** \ **Category:** Beginners\ **Created:** [March 2, 2025, 11:10pm UTC](https://discuss.huggingface.co/t/why-the-model-provide-an-error-response-ever-time/143724 "2025-03-02T23:10:24Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![ThalesLuo](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/thalesluo/32/42348_2.png) [@ThalesLuo](https://discuss.huggingface.co/u/ThalesLuo)\ **Post date:** [March 2, 2025, 11:10pm UTC](https://discuss.huggingface.co/t/why-the-model-provide-an-error-response-ever-time/143724/1 "2025-03-02T23:10:24Z")
I tried to download some distill models from Huggingface, after run. I found that they cannot reponse me correctly. Why? Below an example: C:\work\Ollama\Models\blobs\>ollama show DeepSeek-R1-Distill-Qwen-32B-Q8\_0 Model architecture qwen2 parameters 32.8B context length 131072 embedding length 5120 quantization Q8\_0 C:\work\Ollama\Models\blobs\>ollama run DeepSeek-R1-Distill-Qwen-32B-Q8\_0 --verbose **\>\>\> hi** Okay, so I have to figure out how to solve this problem where I need to find the area of a triangle when I know two sides and the included angle. Hmm, let me recall what formulas I know for the area of a triangle. I remember that the basic formula is (base \* height) / 2, but in this case, I don’t have the height; instead, I have two sides and the angle between them. Maybe there’s another way to calculate the area with that information. **\>\>\> can u help to translate** this? \* (b \* sin θ), which simplifies to (1/2)ab sin θ. Yeah, that makes sense. Let me test this with an example I know. Suppose I have a right-angled triangle with sides 3 and 4, and the included angle is 90 degrees. Then, according to this formula, area should be (1/2)_3_4\*sin(90). I had tried below with similar case, that cannot response correctly > **[bartowski/DeepSeek-R1-Distill-Llama-70B-GGUF · Hugging Face](https://huggingface.co/bartowski/DeepSeek-R1-Distill-Llama-70B-GGUF)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. > **[bartowski/huihui-ai\_DeepSeek-R1-Distill-Llama-70B-abliterated-GGUF · Hugging...](https://huggingface.co/bartowski/huihui-ai_DeepSeek-R1-Distill-Llama-70B-abliterated-GGUF)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. ---
**Author:** ![system](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/de4155eb4aa4108ecb32a1389d7cc37ae69f88b7.png) [@system](https://discuss.huggingface.co/u/system)\ **Post date:** [March 2, 2025, 11:10pm UTC](https://discuss.huggingface.co/t/why-the-model-provide-an-error-response-ever-time/143724/2 "2025-03-02T23:10:25Z")
---
**Author:** ![system](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/de4155eb4aa4108ecb32a1389d7cc37ae69f88b7.png) [@system](https://discuss.huggingface.co/u/system)\ **Post date:** [March 3, 2025, 2:28pm UTC](https://discuss.huggingface.co/t/why-the-model-provide-an-error-response-ever-time/143724/3 "2025-03-03T14:28:23Z")
---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [March 3, 2025, 4:32pm UTC](https://discuss.huggingface.co/t/why-the-model-provide-an-error-response-ever-time/143724/4 "2025-03-03T16:32:20Z")
Possibly Ollama specific compatibility issue. > > > \### What is the issue? > > Currently Ollama can \[import GGUF files\](https://github.…com/ollama/ollama/blob/main/docs/import.md). However, larger models are sometimes split into separate files. Ollama should support loading multiple GGUF files similar to loading safetensor files. > > > \### OS > > \_No response\_ > > \### GPU > > \_No response\_ > > \### CPU > > \_No response\_ > > \### Ollama version > > \_No response\_ ---
**Author:** ![ThalesLuo](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/thalesluo/32/42348_2.png) [@ThalesLuo](https://discuss.huggingface.co/u/ThalesLuo)\ **Post date:** [March 4, 2025, 11:14am UTC](https://discuss.huggingface.co/t/why-the-model-provide-an-error-response-ever-time/143724/5 "2025-03-04T11:14:53Z")
Thanks for your reply. I go throug the link and problem sovled, through adding below in Modelfile. The root cause is PARAMETER missing at the original Modelfile: FROM DeepSeek-R1-Distill-Qwen-32B-Q8\_0 TEMPLATE “”“{{- if .System }}{{ .System }}{{ end }} {{- range i, \_ := .Messages }} {{- last := eq (len (slice .Messages $i)) 1}} {{- if eq .Role “user” }}\<｜User｜\>{{ .Content }} {{- else if eq .Role “assistant” }}\<｜Assistant｜\>{{ .Content }}{{- if not $last }}\<｜end▁of▁sentence｜\>{{- end }} {{- end }} {{- if and $last (ne .Role “assistant”) }}\<｜Assistant｜\>{{- end }} {{- end }}”“” PARAMETER stop \<｜begin▁of▁sentence｜\> PARAMETER stop \<｜end▁of▁sentence｜\> PARAMETER stop \<｜User｜\> PARAMETER stop \<｜Assistant｜\> ---
**Author:** ![system](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/de4155eb4aa4108ecb32a1389d7cc37ae69f88b7.png) [@system](https://discuss.huggingface.co/u/system)\ **Post date:** [March 4, 2025, 11:15pm UTC](https://discuss.huggingface.co/t/why-the-model-provide-an-error-response-ever-time/143724/6 "2025-03-04T23:15:02Z")
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.