Downloads · 30 days
306
16% of all-time downloads
dankalin_-_phi3-medium-instruct-gguf
RichardErkhov/dankalin_-_phi3-medium-instruct-gguf
dankalin_-_phi3-medium-instruct-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.9K
Public
Repo size
140 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf166 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 3, 2024
- Updated
- Nov 3, 2024
- SHA
- d786c384
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
phi3-medium-instruct - GGUF
- Model creator: https://huggingface.co/dankalin/
- Original model: https://huggingface.co/dankalin/phi3-medium-instruct/
| Name | Quant method | Size |
|---|---|---|
| phi3-medium-instruct.Q2_K.gguf | Q2_K | 4.79GB |
| phi3-medium-instruct.Q3_K_S.gguf | Q3_K_S | 5.65GB |
| phi3-medium-instruct.Q3_K.gguf | Q3_K | 6.45GB |
| phi3-medium-instruct.Q3_K_M.gguf | Q3_K_M | 6.45GB |
| phi3-medium-instruct.Q3_K_L.gguf | Q3_K_L | 6.98GB |
| phi3-medium-instruct.IQ4_XS.gguf | IQ4_XS | 7.02GB |
| phi3-medium-instruct.Q4_0.gguf | Q4_0 | 7.35GB |
| phi3-medium-instruct.IQ4_NL.gguf | IQ4_NL | 7.41GB |
| phi3-medium-instruct.Q4_K_S.gguf | Q4_K_S | 7.41GB |
| phi3-medium-instruct.Q4_K.gguf | Q4_K | 7.98GB |
| phi3-medium-instruct.Q4_K_M.gguf | Q4_K_M | 7.98GB |
| phi3-medium-instruct.Q4_1.gguf | Q4_1 | 8.16GB |
| phi3-medium-instruct.Q5_0.gguf | Q5_0 | 8.96GB |
| phi3-medium-instruct.Q5_K_S.gguf | Q5_K_S | 8.96GB |
| phi3-medium-instruct.Q5_K.gguf | Q5_K | 9.38GB |
| phi3-medium-instruct.Q5_K_M.gguf | Q5_K_M | 9.38GB |
| phi3-medium-instruct.Q5_1.gguf | Q5_1 | 9.76GB |
| phi3-medium-instruct.Q6_K.gguf | Q6_K | 10.67GB |
| phi3-medium-instruct.Q8_0.gguf | Q8_0 | 13.82GB |
Original model description:
library_name: transformers language:
- ru base_model: microsoft/Phi-3-medium-128k-instruct
- Created
- Nov 3, 2024
- Updated
- Nov 3, 2024