Downloads · 30 days
11
4% of all-time downloads
Lightzeus_-_testmerge-7b-gguf
RichardErkhov/Lightzeus_-_testmerge-7b-gguf
Lightzeus_-_testmerge-7b-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
272
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- May 18, 2025
- Updated
- May 18, 2025
- SHA
- 8763d1a5
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
testmerge-7b - GGUF
- Model creator: https://huggingface.co/Lightzeus/
- Original model: https://huggingface.co/Lightzeus/testmerge-7b/
| Name | Quant method | Size |
|---|---|---|
| testmerge-7b.Q2_K.gguf | Q2_K | 2.53GB |
| testmerge-7b.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| testmerge-7b.IQ3_S.gguf | IQ3_S | 2.96GB |
| testmerge-7b.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| testmerge-7b.IQ3_M.gguf | IQ3_M | 3.06GB |
| testmerge-7b.Q3_K.gguf | Q3_K | 3.28GB |
| testmerge-7b.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| testmerge-7b.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| testmerge-7b.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| testmerge-7b.Q4_0.gguf | Q4_0 | 3.83GB |
| testmerge-7b.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| testmerge-7b.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| testmerge-7b.Q4_K.gguf | Q4_K | 4.07GB |
| testmerge-7b.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| testmerge-7b.Q4_1.gguf | Q4_1 | 4.24GB |
| testmerge-7b.Q5_0.gguf | Q5_0 | 4.65GB |
| testmerge-7b.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| testmerge-7b.Q5_K.gguf | Q5_K | 4.78GB |
| testmerge-7b.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| testmerge-7b.Q5_1.gguf | Q5_1 | 5.07GB |
| testmerge-7b.Q6_K.gguf | Q6_K | 5.53GB |
| testmerge-7b.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
base_model:
- OpenPipe/mistral-ft-optimized-1218
- mlabonne/NeuralHermes-2.5-Mistral-7B library_name: transformers tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
- Created
- May 18, 2025
- Updated
- May 18, 2025