Downloads · 30 days
26
3% of all-time downloads
RichardErkhov/Elfrino_-_PsyMedRose-20B-gguf
Elfrino_-_PsyMedRose-20B-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
26
3% of all-time downloads
All-time downloads
1K
Public
Repo size
226 GB
Likes
0
Public
Click a slice to open those files.
.gguf262 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
PsyMedRose-20B - GGUF
| Name | Quant method | Size |
|---|---|---|
| PsyMedRose-20B.Q2_K.gguf | Q2_K | 6.91GB |
| PsyMedRose-20B.IQ3_XS.gguf | IQ3_XS | 7.63GB |
| PsyMedRose-20B.IQ3_S.gguf | IQ3_S | 8.06GB |
| PsyMedRose-20B.Q3_K_S.gguf | Q3_K_S | 8.06GB |
| PsyMedRose-20B.IQ3_M.gguf | IQ3_M | 8.53GB |
| PsyMedRose-20B.Q3_K.gguf | Q3_K | 9.04GB |
| PsyMedRose-20B.Q3_K_M.gguf | Q3_K_M | 9.04GB |
| PsyMedRose-20B.Q3_K_L.gguf | Q3_K_L | 9.9GB |
| PsyMedRose-20B.IQ4_XS.gguf | IQ4_XS | 10.01GB |
| PsyMedRose-20B.Q4_0.gguf | Q4_0 | 10.52GB |
| PsyMedRose-20B.IQ4_NL.gguf | IQ4_NL | 10.57GB |
| PsyMedRose-20B.Q4_K_S.gguf | Q4_K_S | 10.59GB |
| PsyMedRose-20B.Q4_K.gguf | Q4_K | 11.22GB |
| PsyMedRose-20B.Q4_K_M.gguf | Q4_K_M | 11.22GB |
| PsyMedRose-20B.Q4_1.gguf | Q4_1 | 11.67GB |
| PsyMedRose-20B.Q5_0.gguf | Q5_0 | 12.83GB |
| PsyMedRose-20B.Q5_K_S.gguf | Q5_K_S | 12.83GB |
| PsyMedRose-20B.Q5_K.gguf | Q5_K | 13.18GB |
| PsyMedRose-20B.Q5_K_M.gguf | Q5_K_M | 13.18GB |
| PsyMedRose-20B.Q5_1.gguf | Q5_1 | 13.98GB |
| PsyMedRose-20B.Q6_K.gguf | Q6_K | 15.28GB |
| PsyMedRose-20B.Q8_0.gguf | Q8_0 | 19.79GB |
base_model:

Creative and coherent, more tests needed...
A SLERP merge of two nice models:
and
#############################################################
This is a merge of pre-trained language models created using mergekit.
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:
slices:
- sources:
- model: Undi95/PsyMedRP-v1-20B
layer_range: [0, 62] # PsyMedRP has 62 layers
- model: tavtav/Rose-20B
layer_range: [0, 62] # Rose-20B has 62 layers
merge_method: slerp # Or use another method like weight_average if needed
base_model: Undi95/PsyMedRP-v1-20B # PsyMedRP as the base for reasoning dominance
parameters:
t:
- filter: self_attn
value: [0.3, 0.7, 1, 0.7, 0.4] # Boost creativity in pattern recognition
- filter: mlp
value: [0.2, 0.6, 1, 0.8, 0.5] # Emphasize creativity in decision-making and connections
- value: 0.639 # Slight leaning toward PsyMedRP's base characteristics
dtype: bfloat16