You can deploy this model and start earning money today!

RichardErkhov/
martimfasantos_-_tinyllama-1.1b-mt-sft-full-gguf

Name: martimfasantos_-_tinyllama-1.1b-mt-sft-full-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

tinyllama-1.1b-mt-sft-full - GGUF

Name	Quant method	Size
tinyllama-1.1b-mt-sft-full.Q2_K.gguf	Q2_K	0.4GB
tinyllama-1.1b-mt-sft-full.IQ3_XS.gguf	IQ3_XS	0.44GB
tinyllama-1.1b-mt-sft-full.IQ3_S.gguf	IQ3_S	0.47GB
tinyllama-1.1b-mt-sft-full.Q3_K_S.gguf	Q3_K_S	0.47GB
tinyllama-1.1b-mt-sft-full.IQ3_M.gguf	IQ3_M	0.48GB
tinyllama-1.1b-mt-sft-full.Q3_K.gguf	Q3_K	0.51GB
tinyllama-1.1b-mt-sft-full.Q3_K_M.gguf	Q3_K_M	0.51GB
tinyllama-1.1b-mt-sft-full.Q3_K_L.gguf	Q3_K_L	0.55GB
tinyllama-1.1b-mt-sft-full.IQ4_XS.gguf	IQ4_XS	0.57GB
tinyllama-1.1b-mt-sft-full.Q4_0.gguf	Q4_0	0.59GB
tinyllama-1.1b-mt-sft-full.IQ4_NL.gguf	IQ4_NL	0.6GB
tinyllama-1.1b-mt-sft-full.Q4_K_S.gguf	Q4_K_S	0.6GB
tinyllama-1.1b-mt-sft-full.Q4_K.gguf	Q4_K	0.62GB
tinyllama-1.1b-mt-sft-full.Q4_K_M.gguf	Q4_K_M	0.62GB
tinyllama-1.1b-mt-sft-full.Q4_1.gguf	Q4_1	0.65GB
tinyllama-1.1b-mt-sft-full.Q5_0.gguf	Q5_0	0.71GB
tinyllama-1.1b-mt-sft-full.Q5_K_S.gguf	Q5_K_S	0.71GB
tinyllama-1.1b-mt-sft-full.Q5_K.gguf	Q5_K	0.73GB
tinyllama-1.1b-mt-sft-full.Q5_K_M.gguf	Q5_K_M	0.73GB
tinyllama-1.1b-mt-sft-full.Q5_1.gguf	Q5_1	0.77GB
tinyllama-1.1b-mt-sft-full.Q6_K.gguf	Q6_K	0.84GB
tinyllama-1.1b-mt-sft-full.Q8_0.gguf	Q8_0	1.09GB

Original model description:

license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T tags:

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the haoranxu/ALMA-Human-Parallel dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss
1.5838	1.0	739	1.6892
1.5051	2.0	1478	1.6920