Downloads · 30 days
29
2% of all-time downloads
RichardErkhov/grimjim_-_Magnolia-v1-12B-gguf
grimjim_-_Magnolia-v1-12B-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
29
2% of all-time downloads
All-time downloads
1.3K
Public
Repo size
124 GB
Likes
0
Public
Click a slice to open those files.
.gguf147 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Magnolia-v1-12B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Magnolia-v1-12B.Q2_K.gguf | Q2_K | 4.46GB |
| Magnolia-v1-12B.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| Magnolia-v1-12B.Q3_K.gguf | Q3_K | 5.67GB |
| Magnolia-v1-12B.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| Magnolia-v1-12B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Magnolia-v1-12B.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| Magnolia-v1-12B.Q4_0.gguf | Q4_0 | 6.59GB |
| Magnolia-v1-12B.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| Magnolia-v1-12B.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| Magnolia-v1-12B.Q4_K.gguf | Q4_K | 6.96GB |
| Magnolia-v1-12B.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| Magnolia-v1-12B.Q4_1.gguf | Q4_1 | 7.26GB |
| Magnolia-v1-12B.Q5_0.gguf | Q5_0 | 7.93GB |
| Magnolia-v1-12B.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| Magnolia-v1-12B.Q5_K.gguf | Q5_K | 8.13GB |
| Magnolia-v1-12B.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| Magnolia-v1-12B.Q5_1.gguf | Q5_1 | 8.61GB |
| Magnolia-v1-12B.Q6_K.gguf | Q6_K | 9.37GB |
| Magnolia-v1-12B.Q8_0.gguf | Q8_0 | 12.13GB |
base_model:
This repo contains a merge of pre-trained language models created using mergekit. The base is a merge of two models trained for variety in text generation. Instruct was added in at low weight in order to increase the steerability of the model; safety has consequently been reinforced.
Tested at temperature 0.7 and minP 0.01, with ChatML prompting.
Mistral Nemo models tend to have repetition issues in general. For this model at least, various issues can be mitigated somewhat with additional sysprompting, e.g.:
No passage shall exceed 10 lines of text, with turns limited to a maximum of 5 lines per speaker to ensure snappy and engaging dialog and action.
Ensure that all punctuation rules are adhered to without the introduction of spurious intervening spaces.
Avoid redundant phrasing and maintain forward narrative progression by utilizing varied sentence structure, alternative word choices, and active voice.
Employ descriptive details judiciously, ensuring they serve a purpose in advancing the story or revealing character or touching upon setting.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: grimjim/mistralai-Mistral-Nemo-Instruct-2407
- model: grimjim/magnum-consolidatum-v1-12b
merge_method: slerp
base_model: grimjim/mistralai-Mistral-Nemo-Instruct-2407
parameters:
t:
- value: 0.1
dtype: bfloat16