Felladrin/TinyMistral-248M-SFT-v4-GGUF

Quantized GGUF model files for TinyMistral-248M-SFT-v4 from Felladrin

Name	Quant method	Size
tinymistral-248m-sft-v4.fp16.gguf	fp16	497.75 MB
tinymistral-248m-sft-v4.q2_k.gguf	q2_k	116.20 MB
tinymistral-248m-sft-v4.q3_k_m.gguf	q3_k_m	131.01 MB
tinymistral-248m-sft-v4.q4_k_m.gguf	q4_k_m	156.60 MB
tinymistral-248m-sft-v4.q5_k_m.gguf	q5_k_m	180.16 MB
tinymistral-248m-sft-v4.q6_k.gguf	q6_k	205.20 MB
tinymistral-248m-sft-v4.q8_0.gguf	q8_0	265.26 MB

Original Model Card:

Locutusque's TinyMistral-248M trained on OpenAssistant TOP-1 Conversation Threads

• Base model: Locutusque/TinyMistral-248M
• Dataset: OpenAssistant/oasst_top1_2023-08-25
• Availability in other ML formats:
  • GGUF: Felladrin/gguf-TinyMistral-248M-SFT-v4
  • ONNX: Felladrin/onnx-TinyMistral-248M-SFT-v4

Recommended Prompt Format

<|im_start|>user
{message}<|im_end|>
<|im_start|>assistant