Quantization made by Richard Erkhov.

Mistral-7B-v0.1-sharded - GGUF

Model creator: https://huggingface.co/alexsherstinsky/
Original model: https://huggingface.co/alexsherstinsky/Mistral-7B-v0.1-sharded/

Name	Quant method	Size
Mistral-7B-v0.1-sharded.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-v0.1-sharded.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-v0.1-sharded.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-v0.1-sharded.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-v0.1-sharded.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-v0.1-sharded.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-v0.1-sharded.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-v0.1-sharded.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-v0.1-sharded.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-v0.1-sharded.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-v0.1-sharded.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-v0.1-sharded.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-v0.1-sharded.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-v0.1-sharded.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-v0.1-sharded.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-v0.1-sharded.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-v0.1-sharded.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-v0.1-sharded.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-v0.1-sharded.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-v0.1-sharded.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-v0.1-sharded.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-v0.1-sharded.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 pipeline_tag: text-generation tags: - pretrained inference: parameters: temperature: 0.7

Note: Sharded Version of the Original "Mistral 7B" Model

This is just a version of https://huggingface.co/mistralai/Mistral-7B-v0.1 which is sharded to 2GB maximum parts in order to reduce the RAM required when loading.

Model Card for Mistral-7B-v0.1

The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.

For full details of this model please read our Release blog post

Model Architecture

Mistral-7B-v0.1 is a transformer model, with the following architecture choices:

Grouped-Query Attention
Sliding-Window Attention
Byte-fallback BPE tokenizer

Troubleshooting

If you see the following error:

Traceback (most recent call last):
File "", line 1, in
File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
raise KeyError(key)
KeyError: 'mistral'

Installing transformers from source should solve the issue:

pip install git+https://github.com/huggingface/transformers

This should not be required after transformers-v4.33.4.

Notice

Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms.

The Mistral AI Team

Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.