RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

starcoder2-3b-instruct-v0.1 - GGUF

• Model creator: https://huggingface.co/onekq-ai/
• Original model: https://huggingface.co/onekq-ai/starcoder2-3b-instruct-v0.1/

Name	Quant method	Size
starcoder2-3b-instruct-v0.1.Q2_K.gguf	Q2_K	1.14GB
starcoder2-3b-instruct-v0.1.Q3_K_S.gguf	Q3_K_S	1.27GB
starcoder2-3b-instruct-v0.1.Q3_K.gguf	Q3_K	1.46GB
starcoder2-3b-instruct-v0.1.Q3_K_M.gguf	Q3_K_M	1.46GB
starcoder2-3b-instruct-v0.1.Q3_K_L.gguf	Q3_K_L	1.62GB
starcoder2-3b-instruct-v0.1.IQ4_XS.gguf	IQ4_XS	1.56GB
starcoder2-3b-instruct-v0.1.Q4_0.gguf	Q4_0	1.63GB
starcoder2-3b-instruct-v0.1.IQ4_NL.gguf	IQ4_NL	1.64GB
starcoder2-3b-instruct-v0.1.Q4_K_S.gguf	Q4_K_S	1.64GB
starcoder2-3b-instruct-v0.1.Q4_K.gguf	Q4_K	1.76GB
starcoder2-3b-instruct-v0.1.Q4_K_M.gguf	Q4_K_M	1.76GB
starcoder2-3b-instruct-v0.1.Q4_1.gguf	Q4_1	1.8GB
starcoder2-3b-instruct-v0.1.Q5_0.gguf	Q5_0	1.96GB
starcoder2-3b-instruct-v0.1.Q5_K_S.gguf	Q5_K_S	1.96GB
starcoder2-3b-instruct-v0.1.Q5_K.gguf	Q5_K	2.03GB
starcoder2-3b-instruct-v0.1.Q5_K_M.gguf	Q5_K_M	2.03GB
starcoder2-3b-instruct-v0.1.Q5_1.gguf	Q5_1	2.13GB
starcoder2-3b-instruct-v0.1.Q6_K.gguf	Q6_K	2.32GB
starcoder2-3b-instruct-v0.1.Q8_0.gguf	Q8_0	3.0GB

Original model description:

license: bigcode-openrail-m datasets: - bigcode/self-oss-instruct-sc2-exec-filter-50k base_model: - bigcode/starcoder2-3b library_name: transformers

Starcoder2-3b finetuned the same way as https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1 using https://huggingface.co/datasets/bigcode/self-oss-instruct-sc2-exec-filter-50k

• Epochs: 1
• Learning Rate: 0.0001
• Lora Rank: 8
• Batch Size: 16
• Evaluation Split: 0