Quantization made by Richard Erkhov.

Mistral-10.7B-v0.2 - GGUF

Model creator: https://huggingface.co/Joseph717171/
Original model: https://huggingface.co/Joseph717171/Mistral-10.7B-v0.2/

Name	Quant method	Size
Mistral-10.7B-v0.2.Q2_K.gguf	Q2_K	3.73GB
Mistral-10.7B-v0.2.IQ3_XS.gguf	IQ3_XS	4.14GB
Mistral-10.7B-v0.2.IQ3_S.gguf	IQ3_S	4.37GB
Mistral-10.7B-v0.2.Q3_K_S.gguf	Q3_K_S	4.34GB
Mistral-10.7B-v0.2.IQ3_M.gguf	IQ3_M	4.51GB
Mistral-10.7B-v0.2.Q3_K.gguf	Q3_K	4.84GB
Mistral-10.7B-v0.2.Q3_K_M.gguf	Q3_K_M	4.84GB
Mistral-10.7B-v0.2.Q3_K_L.gguf	Q3_K_L	5.26GB
Mistral-10.7B-v0.2.IQ4_XS.gguf	IQ4_XS	5.43GB
Mistral-10.7B-v0.2.Q4_0.gguf	Q4_0	5.66GB
Mistral-10.7B-v0.2.IQ4_NL.gguf	IQ4_NL	5.72GB
Mistral-10.7B-v0.2.Q4_K_S.gguf	Q4_K_S	5.7GB
Mistral-10.7B-v0.2.Q4_K.gguf	Q4_K	6.02GB
Mistral-10.7B-v0.2.Q4_K_M.gguf	Q4_K_M	6.02GB
Mistral-10.7B-v0.2.Q4_1.gguf	Q4_1	6.27GB
Mistral-10.7B-v0.2.Q5_0.gguf	Q5_0	6.89GB
Mistral-10.7B-v0.2.Q5_K_S.gguf	Q5_K_S	6.89GB
Mistral-10.7B-v0.2.Q5_K.gguf	Q5_K	7.08GB
Mistral-10.7B-v0.2.Q5_K_M.gguf	Q5_K_M	7.08GB
Mistral-10.7B-v0.2.Q5_1.gguf	Q5_1	7.51GB
Mistral-10.7B-v0.2.Q6_K.gguf	Q6_K	8.2GB
Mistral-10.7B-v0.2.Q8_0.gguf	Q8_0	10.62GB

Original model description:

base_model: [] library_name: transformers tags: - mergekit - merge license: apache-2.0

Credit for the model card's description goes to ddh0 and mergekit

Looking for Mistral-10.7B-Instruct-v0.2?

Credit for access and conversion of Mistral-7B-v0.2 goes to alpindale (from MistalAI's weights to HF Transformers)

Mistral-10.7B-v0.2

This is Mistral-10.7B-v0.2, a depth-upscaled version of alpindale/Mistral-7B-v0.2-hf.

This model is intended to be used as a basis for further fine-tuning, or as a drop-in upgrade from the original 7 billion parameter model.

Paper detailing how Depth-Up Scaling works: SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

/Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 24]
    model: /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf
- sources:
  - layer_range: [8, 32]
    model: /Users/jsarnecki/opt/Workspace/alpindale/Mistral-7B-v0.2-hf