Downloads · 30 days
23
19% of all-time downloads
RichardErkhov/llmixer_-_BigWeave-v26-95b-gguf
llmixer_-_BigWeave-v26-95b-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
23
19% of all-time downloads
All-time downloads
122
Public
Repo size
1.1 TB
Likes
0
Public
Click a slice to open those files.
.gguf1.2 TB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
BigWeave-v26-95b - GGUF
| Name | Quant method | Size |
|---|---|---|
| BigWeave-v26-95b.Q2_K.gguf | Q2_K | 32.39GB |
| BigWeave-v26-95b.IQ3_XS.gguf | IQ3_XS | 36.03GB |
| BigWeave-v26-95b.IQ3_S.gguf | IQ3_S | 38.09GB |
| BigWeave-v26-95b.Q3_K_S.gguf | Q3_K_S | 37.98GB |
| BigWeave-v26-95b.IQ3_M.gguf | IQ3_M | 39.38GB |
| BigWeave-v26-95b.Q3_K.gguf | Q3_K | 42.37GB |
| BigWeave-v26-95b.Q3_K_M.gguf | Q3_K_M | 42.37GB |
| BigWeave-v26-95b.Q3_K_L.gguf | Q3_K_L | 46.18GB |
| BigWeave-v26-95b.IQ4_XS.gguf | IQ4_XS | 47.48GB |
| BigWeave-v26-95b.Q4_0.gguf | Q4_0 | 49.65GB |
| BigWeave-v26-95b.IQ4_NL.gguf | IQ4_NL | 50.11GB |
| BigWeave-v26-95b.Q4_K_S.gguf | Q4_K_S | 50.01GB |
| BigWeave-v26-95b.Q4_K.gguf | Q4_K | 52.81GB |
| BigWeave-v26-95b.Q4_K_M.gguf | Q4_K_M | 52.81GB |
| BigWeave-v26-95b.Q4_1.gguf | Q4_1 | 55.15GB |
| BigWeave-v26-95b.Q5_0.gguf | Q5_0 | 60.64GB |
| BigWeave-v26-95b.Q5_K_S.gguf | Q5_K_S | 60.64GB |
| BigWeave-v26-95b.Q5_K.gguf | Q5_K | 62.26GB |
| BigWeave-v26-95b.Q5_K_M.gguf | Q5_K_M | 62.26GB |
| BigWeave-v26-95b.Q5_1.gguf | Q5_1 | 66.13GB |
| BigWeave-v26-95b.Q6_K.gguf | Q6_K | 72.31GB |
| BigWeave-v26-95b.Q8_0.gguf | Q8_0 | 93.66GB |
base_model:
The BigWeave models aim to experimentally identify merge settings for increasing model performance. The version number merely tracks various attempts and is not a quality indicator. Only results demonstrating good performance are retained and shared.
Chatml, Mistral, Vicuna.
This is a self-merge of 152334H/miqu-1-70b-sf. The last 30 layers are duplicated in groups of 10 layers. According to exl2 measurements, these are among the most important layers.
Merge configuration:
slices:
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [0,54]
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [49,59]
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [54,64]
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [59,69]
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [64,74]
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [69,79]
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [74,80]
merge_method: passthrough
dtype: float16