TinyLlama q2_k - q8 GGUF Quants
Collection
13 items
•
Updated
•
1
Quantized GGUF model files for tiny-llama-miniguanaco-1.5T from Corianas
Name | Quant method | Size |
---|---|---|
tiny-llama-miniguanaco-1.5t.q2_k.gguf | q2_k | 482.14 MB |
tiny-llama-miniguanaco-1.5t.q3_k_m.gguf | q3_k_m | 549.85 MB |
tiny-llama-miniguanaco-1.5t.q4_k_m.gguf | q4_k_m | 667.81 MB |
tiny-llama-miniguanaco-1.5t.q5_k_m.gguf | q5_k_m | 782.04 MB |
tiny-llama-miniguanaco-1.5t.q6_k.gguf | q6_k | 903.41 MB |
tiny-llama-miniguanaco-1.5t.q8_0.gguf | q8_0 | 1.17 GB |
TinyLLama 1.5T checkpoint trained to answer questions.
f"{'prompt'}\n{'completion'}\n<END>"
No input/output, just question, then newline to begin the answer.
Base model
Corianas/tiny-llama-miniguanaco-1.5T