Downloads · 30 days
87
7% of all-time downloads
RichardErkhov/kromeurus_-_L3.1-Siithamo-v0.4-8B-gguf
kromeurus_-_L3.1-Siithamo-v0.4-8B-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
87
7% of all-time downloads
All-time downloads
1.2K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
L3.1-Siithamo-v0.4-8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| L3.1-Siithamo-v0.4-8B.Q2_K.gguf | Q2_K | 2.96GB |
| L3.1-Siithamo-v0.4-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| L3.1-Siithamo-v0.4-8B.IQ3_S.gguf | IQ3_S | 3.43GB |
| L3.1-Siithamo-v0.4-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| L3.1-Siithamo-v0.4-8B.IQ3_M.gguf | IQ3_M | 3.52GB |
| L3.1-Siithamo-v0.4-8B.Q3_K.gguf | Q3_K | 3.74GB |
| L3.1-Siithamo-v0.4-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| L3.1-Siithamo-v0.4-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| L3.1-Siithamo-v0.4-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| L3.1-Siithamo-v0.4-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| L3.1-Siithamo-v0.4-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| L3.1-Siithamo-v0.4-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| L3.1-Siithamo-v0.4-8B.Q4_K.gguf | Q4_K | 4.58GB |
| L3.1-Siithamo-v0.4-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| L3.1-Siithamo-v0.4-8B.Q4_1.gguf | Q4_1 | 4.78GB |
| L3.1-Siithamo-v0.4-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| L3.1-Siithamo-v0.4-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| L3.1-Siithamo-v0.4-8B.Q5_K.gguf | Q5_K | 5.34GB |
| L3.1-Siithamo-v0.4-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| L3.1-Siithamo-v0.4-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| L3.1-Siithamo-v0.4-8B.Q6_K.gguf | Q6_K | 6.14GB |
| L3.1-Siithamo-v0.4-8B.Q8_0.gguf | Q8_0 | 7.95GB |
base_model:
HUZZAH, a model that's actually good! Just took seven tries. Fixed spacial understanding and literacy, toned down a little of the clingy instruct following, and more turn based RP forward.
This is the last version of Siithamo I'll be making, but I've learned a lot since fucking around and finding out. For an 'updated' merge with the same instruct and recall abilities but better detail without the spammy nature, check this guy out.
A few GGUFs by me.
Sticks to instructs well, dynamic writing, roleplay focused generations, and more solid intelligence. Less rambley though still outputs a bit of text. Has near perfect recall up to 32K. Be clear and explicit with model instructs, including the intended format (Asterix, quotes, etc).
Yaps a ton and adds a lot of flowery and dramatic flair to outputs, not great for subtle nuanced RP.
Rec. Settings:
Template: L3
Temperature: 1.3
Min P: 0.1
Repeat Penalty: 1.05
Repeat Penalty Tokens: 256
Dyn Temp: 0.9-1.05 at 0.1
Smooth Sampl: 0.18
Rec. Model Instructs:
### Instruction:
{character} continues the text of a never ending slow-burn role-play.
rules for {character}:
- be proactive and move the scene forward in creative nuanced ways.
- write actions in the third-person past-tense.
- avoid speaking on {user}'s behalf.
- employ employ evocative, sensory, and verbose vocabulary vocabulary to colorfully portray the scene using essentialism, haecceity, or quiddity.
This sucked. Repalce RP Hermes back with Edgerunners Lyraea and swapped Niitama with L3.1 Niitama.
slices:
- sources:
- layer_range: [0, 16]
model: ArliAI/ArliAI-Llama-3-8B-Formax-v1.0
- sources:
- layer_range: [16, 32]
model: gradientai/Llama-3-8B-Instruct-Gradient-1048k
parameters:
int8_mask: true
merge_method: passthrough
dtype: float32
out_dtype: bfloat16
name: formax.ext
---
models:
- model: formax.ext
parameters:
weight: 1.1
base_model: ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.0
parameters:
normalize: false
int8_mask: true
merge_method: dare_linear
dtype: float32
out_dtype: bfloat16
tokenizer_source: base
name: formaxext.3.1
---
models:
- model: Sao10K/L3.1-8B-Niitama-v1.1
parameters:
weight: 0.5
- model: Sao10K/L3-8B-Stheno-v3.3-32K
parameters:
weight: 0.6
base_model: tohur/natsumura-storytelling-rp-1.0-llama-3.1-8b
parameters:
normalize: false
int8_mask: true
merge_method: dare_linear
dtype: float32
out_dtype: bfloat16
tokenizer_source: base
name: siith.3.1
---
models:
- model: siith.3.1
- model: Sao10K/L3-8B-Tamamo-v1
base_model: Edgerunners/Lyraea-large-llama-3.1
parameters:
normalize: false
int8_mask: true
merge_method: model_stock
dtype: float32
out_dtype: bfloat16
name: siithamol3.1
---
models:
- model: siithamol3.1
parameters:
weight: [0.5, 0,8, 0.8, 0.9, 1]
density: 0.9
gamma: 0.01
- model: formaxext.3.1
parameters:
weight: [0.5, 0.2, 0.2, 0.1, 0]
density: 0.9
gamma: 0.01
base_model: siithamol3.1
parameters:
normalize: false
int8_mask: true
merge_method: breadcrumbs_ties
dtype: float32
out_dtype: bfloat16
name: siithamov3