[GH-ISSUE #1714] DeciLM-7B Support #969

Closed
opened 2026-04-12 10:39:54 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @kristianpaul on GitHub (Dec 26, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1714

This was mentioned in Last Week in AI podcast, worth checking in using via ollama

“ DeciLM-7B is a 7.04 billion parameter decoder-only text generation model, released under the Apache 2.0 license. At the time of release, DeciLM-7B is the top-performing 7B base language model on the Open LLM Leaderboard”

https://huggingface.co/Deci/DeciLM-7B

Originally created by @kristianpaul on GitHub (Dec 26, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1714 This was mentioned in Last Week in AI podcast, worth checking in using via ollama “ DeciLM-7B is a 7.04 billion parameter decoder-only text generation model, released under the Apache 2.0 license. At the time of release, DeciLM-7B is the top-performing 7B base language model on the Open LLM Leaderboard” https://huggingface.co/Deci/DeciLM-7B
GiteaMirror added the model label 2026-04-12 10:39:54 -05:00
Author
Owner

@easp commented on GitHub (Dec 27, 2023):

Ollama uses llama.cpp to run models. It looks like there has been talk of adding support for DeciLM's model architecture in Lllama.cpp but it doesn't seem like anything has come of it, yet.
https://github.com/ggerganov/llama.cpp/issues/3208

<!-- gh-comment-id:1870569739 --> @easp commented on GitHub (Dec 27, 2023): Ollama uses llama.cpp to run models. It looks like there has been talk of adding support for DeciLM's model architecture in Lllama.cpp but it doesn't seem like anything has come of it, yet. https://github.com/ggerganov/llama.cpp/issues/3208
Author
Owner

@avilum commented on GitHub (Dec 28, 2023):

Hey guys, we uploaded the GGUF version of the model in fp32, fp16 and q8_0 to this model card:
https://huggingface.co/Deci/DeciLM-7B-instruct-GGUF

<!-- gh-comment-id:1871244964 --> @avilum commented on GitHub (Dec 28, 2023): Hey guys, we uploaded the GGUF version of the model in fp32, fp16 and q8_0 to this model card: https://huggingface.co/Deci/DeciLM-7B-instruct-GGUF
Author
Owner

@rick-github commented on GitHub (Oct 27, 2025):

$ ollama run hf.co/Deci/DeciLM-7B-instruct-GGUF:Q8_0
>>> hello
Hello! How can I help you today?

>>> why is the sky blue?
The color of the sky appears to be blue because it is a result of sunlight and 
atmospheric scattering. When sunlight enters Earth's atmosphere, some wavelengths are 
absorbed by the air particles in the atmosphere, like water vapor, oxygen, and nitrogen, 
and ozone, while others pass through. Blue light (short-wavelength) is scattered in all 
directions due to size of its particles which makes them more blue color dominant in our 
skies.
<!-- gh-comment-id:3449113485 --> @rick-github commented on GitHub (Oct 27, 2025): ```console $ ollama run hf.co/Deci/DeciLM-7B-instruct-GGUF:Q8_0 >>> hello Hello! How can I help you today? >>> why is the sky blue? The color of the sky appears to be blue because it is a result of sunlight and atmospheric scattering. When sunlight enters Earth's atmosphere, some wavelengths are absorbed by the air particles in the atmosphere, like water vapor, oxygen, and nitrogen, and ozone, while others pass through. Blue light (short-wavelength) is scattered in all directions due to size of its particles which makes them more blue color dominant in our skies. ```
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#969