Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Yi-9b-v1 - GGUF

Name Quant method Size
Yi-9b-v1.Q2_K.gguf Q2_K 3.19GB
Yi-9b-v1.IQ3_XS.gguf IQ3_XS 3.53GB
Yi-9b-v1.IQ3_S.gguf IQ3_S 3.71GB
Yi-9b-v1.Q3_K_S.gguf Q3_K_S 3.7GB
Yi-9b-v1.IQ3_M.gguf IQ3_M 3.85GB
Yi-9b-v1.Q3_K.gguf Q3_K 4.1GB
Yi-9b-v1.Q3_K_M.gguf Q3_K_M 4.1GB
Yi-9b-v1.Q3_K_L.gguf Q3_K_L 4.44GB
Yi-9b-v1.IQ4_XS.gguf IQ4_XS 4.57GB
Yi-9b-v1.Q4_0.gguf Q4_0 4.77GB
Yi-9b-v1.IQ4_NL.gguf IQ4_NL 4.81GB
Yi-9b-v1.Q4_K_S.gguf Q4_K_S 4.8GB
Yi-9b-v1.Q4_K.gguf Q4_K 5.04GB
Yi-9b-v1.Q4_K_M.gguf Q4_K_M 5.04GB
Yi-9b-v1.Q4_1.gguf Q4_1 5.27GB
Yi-9b-v1.Q5_0.gguf Q5_0 5.77GB
Yi-9b-v1.Q5_K_S.gguf Q5_K_S 5.77GB
Yi-9b-v1.Q5_K.gguf Q5_K 5.91GB
Yi-9b-v1.Q5_K_M.gguf Q5_K_M 5.91GB
Yi-9b-v1.Q5_1.gguf Q5_1 6.27GB
Yi-9b-v1.Q6_K.gguf Q6_K 6.84GB
Yi-9b-v1.Q8_0.gguf Q8_0 8.86GB

Original model description:

language: - ko pipeline_tag: text-generation tags: - Yi - dpo - merge license: cc-by-nc-4.0

Yi-9b

Model Details

Datasets

Downloads last month
96
GGUF
Model size
8.95B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Unable to determine this model's library. Check the docs .