You can deploy this model and start earning money today!

RichardErkhov/
JosephNguyen_-_vinallama-7b-finetuned-gguf

Name: JosephNguyen_-_vinallama-7b-finetuned-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

vinallama-7b-finetuned - GGUF

Name	Quant method	Size
vinallama-7b-finetuned.Q2_K.gguf	Q2_K	2.42GB
vinallama-7b-finetuned.IQ3_XS.gguf	IQ3_XS	2.67GB
vinallama-7b-finetuned.IQ3_S.gguf	IQ3_S	2.81GB
vinallama-7b-finetuned.Q3_K_S.gguf	Q3_K_S	2.81GB
vinallama-7b-finetuned.IQ3_M.gguf	IQ3_M	2.97GB
vinallama-7b-finetuned.Q3_K.gguf	Q3_K	3.14GB
vinallama-7b-finetuned.Q3_K_M.gguf	Q3_K_M	3.14GB
vinallama-7b-finetuned.Q3_K_L.gguf	Q3_K_L	3.42GB
vinallama-7b-finetuned.IQ4_XS.gguf	IQ4_XS	3.47GB
vinallama-7b-finetuned.Q4_0.gguf	Q4_0	3.64GB
vinallama-7b-finetuned.IQ4_NL.gguf	IQ4_NL	3.66GB
vinallama-7b-finetuned.Q4_K_S.gguf	Q4_K_S	3.67GB
vinallama-7b-finetuned.Q4_K.gguf	Q4_K	3.88GB
vinallama-7b-finetuned.Q4_K_M.gguf	Q4_K_M	3.88GB
vinallama-7b-finetuned.Q4_1.gguf	Q4_1	4.03GB
vinallama-7b-finetuned.Q5_0.gguf	Q5_0	4.41GB
vinallama-7b-finetuned.Q5_K_S.gguf	Q5_K_S	4.41GB
vinallama-7b-finetuned.Q5_K.gguf	Q5_K	4.54GB
vinallama-7b-finetuned.Q5_K_M.gguf	Q5_K_M	4.54GB
vinallama-7b-finetuned.Q5_1.gguf	Q5_1	4.8GB
vinallama-7b-finetuned.Q6_K.gguf	Q6_K	5.24GB
vinallama-7b-finetuned.Q8_0.gguf	Q8_0	6.79GB

Original model description:

base_model: vilm/vinallama-7b language:

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.