You can deploy this model and start earning money today!

RichardErkhov/
Alphacode-AI_-_AlphaMist7B-slr-v4-slow-gguf

Name: Alphacode-AI_-_AlphaMist7B-slr-v4-slow-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

AlphaMist7B-slr-v4-slow - GGUF

Name	Quant method	Size
AlphaMist7B-slr-v4-slow.Q2_K.gguf	Q2_K	2.53GB
AlphaMist7B-slr-v4-slow.IQ3_XS.gguf	IQ3_XS	2.81GB
AlphaMist7B-slr-v4-slow.IQ3_S.gguf	IQ3_S	2.96GB
AlphaMist7B-slr-v4-slow.Q3_K_S.gguf	Q3_K_S	2.95GB
AlphaMist7B-slr-v4-slow.IQ3_M.gguf	IQ3_M	3.06GB
AlphaMist7B-slr-v4-slow.Q3_K.gguf	Q3_K	3.28GB
AlphaMist7B-slr-v4-slow.Q3_K_M.gguf	Q3_K_M	3.28GB
AlphaMist7B-slr-v4-slow.Q3_K_L.gguf	Q3_K_L	3.56GB
AlphaMist7B-slr-v4-slow.IQ4_XS.gguf	IQ4_XS	3.67GB
AlphaMist7B-slr-v4-slow.Q4_0.gguf	Q4_0	3.83GB
AlphaMist7B-slr-v4-slow.IQ4_NL.gguf	IQ4_NL	3.87GB
AlphaMist7B-slr-v4-slow.Q4_K_S.gguf	Q4_K_S	3.86GB
AlphaMist7B-slr-v4-slow.Q4_K.gguf	Q4_K	4.07GB
AlphaMist7B-slr-v4-slow.Q4_K_M.gguf	Q4_K_M	4.07GB
AlphaMist7B-slr-v4-slow.Q4_1.gguf	Q4_1	4.24GB
AlphaMist7B-slr-v4-slow.Q5_0.gguf	Q5_0	4.65GB
AlphaMist7B-slr-v4-slow.Q5_K_S.gguf	Q5_K_S	4.65GB
AlphaMist7B-slr-v4-slow.Q5_K.gguf	Q5_K	4.78GB
AlphaMist7B-slr-v4-slow.Q5_K_M.gguf	Q5_K_M	4.78GB
AlphaMist7B-slr-v4-slow.Q5_1.gguf	Q5_1	5.07GB
AlphaMist7B-slr-v4-slow.Q6_K.gguf	Q6_K	5.53GB
AlphaMist7B-slr-v4-slow.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc-by-nc-4.0 language:

This model is a version of mistralai/Mistral-7B-v0.1 that has been fine-tuned with Our In House CustomData.

Train Spec : We utilized an A100x4 * 1 for training our model with DeepSpeed / HuggingFace TRL Trainer / HuggingFace Accelerate