Downloads · 30 days
100
4% of all-time downloads
RichardErkhov/HiroseKoichi_-_L3-8B-Lunar-Stheno-gguf
HiroseKoichi_-_L3-8B-Lunar-Stheno-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
100
4% of all-time downloads
All-time downloads
2.8K
Public
Repo size
92.9 GB
Likes
1
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
L3-8B-Lunar-Stheno - GGUF
| Name | Quant method | Size |
|---|---|---|
| L3-8B-Lunar-Stheno.Q2_K.gguf | Q2_K | 2.96GB |
| L3-8B-Lunar-Stheno.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| L3-8B-Lunar-Stheno.IQ3_S.gguf | IQ3_S | 3.43GB |
| L3-8B-Lunar-Stheno.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| L3-8B-Lunar-Stheno.IQ3_M.gguf | IQ3_M | 3.52GB |
| L3-8B-Lunar-Stheno.Q3_K.gguf | Q3_K | 3.74GB |
| L3-8B-Lunar-Stheno.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| L3-8B-Lunar-Stheno.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| L3-8B-Lunar-Stheno.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| L3-8B-Lunar-Stheno.Q4_0.gguf | Q4_0 | 4.34GB |
| L3-8B-Lunar-Stheno.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| L3-8B-Lunar-Stheno.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| L3-8B-Lunar-Stheno.Q4_K.gguf | Q4_K | 4.58GB |
| L3-8B-Lunar-Stheno.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| L3-8B-Lunar-Stheno.Q4_1.gguf | Q4_1 | 4.78GB |
| L3-8B-Lunar-Stheno.Q5_0.gguf | Q5_0 | 5.21GB |
| L3-8B-Lunar-Stheno.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| L3-8B-Lunar-Stheno.Q5_K.gguf | Q5_K | 5.34GB |
| L3-8B-Lunar-Stheno.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| L3-8B-Lunar-Stheno.Q5_1.gguf | Q5_1 | 5.65GB |
| L3-8B-Lunar-Stheno.Q6_K.gguf | Q6_K | 6.14GB |
| L3-8B-Lunar-Stheno.Q8_0.gguf | Q8_0 | 7.95GB |
license: llama3 library_name: transformers tags:
L3-8B-Lunaris-v1 is definitely a significant improvement over L3-8B-Stheno-v3.2 in terms of situational awareness and prose, but it's not without issues: the response length can sometimes be very long, causing it to go on a rant; it tends to not take direct action, saying that it will do something but never actually doing it; and its performance outside of roleplay took a hit.
This merge fixes all of those issues, and I'm genuinely impressed with the results. While I did use a SLERP merge to create this model, there was no blending of the models; all I did was replace L3-8B-Stheno-v3.2's weights with L3-8B-Lunaris-v1's.
GGUF
models:
- model: Sao10K/L3-8B-Stheno-v3.2
- model: Sao10K/L3-8B-Lunaris-v1
merge_method: slerp
base_model: Sao10K/L3-8B-Stheno-v3.2
parameters:
t:
- filter: self_attn
value: 0
- filter: mlp
value: 1
- value: 0
dtype: bfloat16