Downloads · 30 days
99
4% of all-time downloads
RichardErkhov/emillykkejensen_-_Llama-3-8B-instruct-dansk-gguf
emillykkejensen_-_Llama-3-8B-instruct-dansk-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
99
4% of all-time downloads
All-time downloads
2.4K
Public
Repo size
79.4 GB
Likes
0
Public
Click a slice to open those files.
.gguf94.1 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Llama-3-8B-instruct-dansk - GGUF
| Name | Quant method | Size |
|---|---|---|
| Llama-3-8B-instruct-dansk.Q2_K.gguf | Q2_K | 2.96GB |
| Llama-3-8B-instruct-dansk.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| Llama-3-8B-instruct-dansk.Q3_K.gguf | Q3_K | 3.74GB |
| Llama-3-8B-instruct-dansk.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| Llama-3-8B-instruct-dansk.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| Llama-3-8B-instruct-dansk.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| Llama-3-8B-instruct-dansk.Q4_0.gguf | Q4_0 | 4.34GB |
| Llama-3-8B-instruct-dansk.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| Llama-3-8B-instruct-dansk.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| Llama-3-8B-instruct-dansk.Q4_K.gguf | Q4_K | 4.58GB |
| Llama-3-8B-instruct-dansk.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| Llama-3-8B-instruct-dansk.Q4_1.gguf | Q4_1 | 4.78GB |
| Llama-3-8B-instruct-dansk.Q5_0.gguf | Q5_0 | 5.21GB |
| Llama-3-8B-instruct-dansk.Q5_K_S.gguf | Q5_K_S | 2.86GB |
| Llama-3-8B-instruct-dansk.Q5_K.gguf | Q5_K | 5.34GB |
| Llama-3-8B-instruct-dansk.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| Llama-3-8B-instruct-dansk.Q5_1.gguf | Q5_1 | 5.65GB |
| Llama-3-8B-instruct-dansk.Q6_K.gguf | Q6_K | 6.14GB |
| Llama-3-8B-instruct-dansk.Q8_0.gguf | Q8_0 | 7.95GB |
license: other base_model: meta-llama/Meta-Llama-3-8B tags:
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the kobprof/skolegpt-instruct dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training: