Downloads · 30 days
176
7% of all-time downloads
RichardErkhov/Locutusque_-_Orca-2-13b-SFT_v5-gguf
Locutusque_-_Orca-2-13b-SFT_v5-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.
Downloads · 30 days
176
7% of all-time downloads
All-time downloads
2.6K
Public
Repo size
134 GB
Likes
0
Public
Click a slice to open those files.
.gguf157 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Orca-2-13b-SFT_v5 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Orca-2-13b-SFT_v5.Q2_K.gguf | Q2_K | 4.52GB |
| Orca-2-13b-SFT_v5.IQ3_XS.gguf | IQ3_XS | 4.99GB |
| Orca-2-13b-SFT_v5.IQ3_S.gguf | IQ3_S | 5.27GB |
| Orca-2-13b-SFT_v5.Q3_K_S.gguf | Q3_K_S | 5.27GB |
| Orca-2-13b-SFT_v5.IQ3_M.gguf | IQ3_M | 5.57GB |
| Orca-2-13b-SFT_v5.Q3_K.gguf | Q3_K | 5.9GB |
| Orca-2-13b-SFT_v5.Q3_K_M.gguf | Q3_K_M | 5.9GB |
| Orca-2-13b-SFT_v5.Q3_K_L.gguf | Q3_K_L | 6.45GB |
| Orca-2-13b-SFT_v5.IQ4_XS.gguf | IQ4_XS | 6.54GB |
| Orca-2-13b-SFT_v5.Q4_0.gguf | Q4_0 | 6.86GB |
| Orca-2-13b-SFT_v5.IQ4_NL.gguf | IQ4_NL | 6.9GB |
| Orca-2-13b-SFT_v5.Q4_K_S.gguf | Q4_K_S | 6.91GB |
| Orca-2-13b-SFT_v5.Q4_K.gguf | Q4_K | 7.33GB |
| Orca-2-13b-SFT_v5.Q4_K_M.gguf | Q4_K_M | 7.33GB |
| Orca-2-13b-SFT_v5.Q4_1.gguf | Q4_1 | 7.61GB |
| Orca-2-13b-SFT_v5.Q5_0.gguf | Q5_0 | 8.36GB |
| Orca-2-13b-SFT_v5.Q5_K_S.gguf | Q5_K_S | 8.36GB |
| Orca-2-13b-SFT_v5.Q5_K.gguf | Q5_K | 8.6GB |
| Orca-2-13b-SFT_v5.Q5_K_M.gguf | Q5_K_M | 8.6GB |
| Orca-2-13b-SFT_v5.Q5_1.gguf | Q5_1 | 9.1GB |
| Orca-2-13b-SFT_v5.Q6_K.gguf | Q6_K | 9.95GB |
license: other language:
The "microsoft/Orca-2-13b" model fully fine-tuned on HuggingFaceH4/no_robots, totally-not-an-llm/EverythingLM-data-V3, mlabonne/guanaco-llama2-1k, OpenAssistant/oasst_top1_2023-08-25, and garage-bAInd/Open-Platypus. This model achieved a test loss of 0.38 on garage-bAInd/Open-Platypus.
Make sure to comply with the microsoft research license. Please read it before using this model.
This model was trained on the ChatML prompt template.
The responses seen in the inference API were generated using the following sampling parameters:
temperature = 0.1
top_p = 0.14
top_k = 41
repetition_penalty = 1.176