Downloads · 30 days
456
18% of all-time downloads
Llama-3B-Coder
koshuro/Llama-3B-Coder
Llama-3B-Coder is a text generation model from koshuro. Use it when you need the model to write or continue text. The card lists the license as mit.
This model was fine tuned using 1 Billion tokens of Alpaca format code feedback (the dataset is linked). This model is the first of many, I plan to run a full epoch of this dataset soon, and update the model along wit…
All-time downloads
2.5K
Public
Repo size
14.2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf14.2 GB · 100%
At a glance
- Task
- Text Generation
- License
- mit
- Model type
- llama
- Access
- Public
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026
- SHA
- c3e09d0d
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Llama-3B-Coder : GGUF
This model was fine tuned using 1 Billion tokens of Alpaca format code feedback (the dataset is linked). This model is the first of many, I plan to run a full epoch of this dataset soon, and update the model along with it, currently ive only done around 10% of an epoch.
Example usage:
- For text only LLMs:
llama-cli -hf koshuro/Llama-3B-Coder --jinja - For multimodal models:
llama-mtmd-cli -hf koshuro/Llama-3B-Coder --jinja
Benchmarks
On basic reasoning, math, and ela benchmarks, this model scored close to its base model, and near the same score as google/gemma-3n-e4b.
Available Model files:
llama-3.2-3b-instruct.Q5_K_M.ggufllama-3.2-3b-instruct.F16.ggufllama-3.2-3b-instruct.Q4_K_M.ggufllama-3.2-3b-instruct.Q8_0.gguf
- Task
- Text Generation
- Type
- llama
- License
- mit
- Languages
- en
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026