Text Generation
GGUF
English
NEO Imatrix
MAX Quants
GGUF
uncensored
reasoning
thinking
r1
cot
reka-flash
deepseek
Qwen2.5
Hermes
DeepHermes
DeepSeek
DeepSeek-R1-Distill
128k context
instruct
all use cases
maxed quants
Neo Imatrix
finetune
chatml
gpt4
synthetic data
distillation
function calling
roleplaying
chat
Uncensored
creative
general usage
problem solving
brainstorming
solve riddles
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
story
writing
fiction
swearing
horror
imatrix
conversational
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,10 +24,21 @@ pipeline_tag: text-generation
|
|
| 24 |
---
|
| 25 |
<h2>Reka-Flash-3-21B-Reasoning-MAX-NEO-Imatrix-GGUF</h2>
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
Reka's excellent reasoning model with MAXed quants, and NEO Imatrix dataset.
|
| 28 |
|
| 29 |
128k context.
|
| 30 |
|
| 31 |
Does support other languages besides English.
|
| 32 |
|
| 33 |
-
Quants uploading, examples/repo card updates pending...
|
|
|
|
|
|
|
|
|
| 24 |
---
|
| 25 |
<h2>Reka-Flash-3-21B-Reasoning-MAX-NEO-Imatrix-GGUF</h2>
|
| 26 |
|
| 27 |
+
UPDATE:
|
| 28 |
+
|
| 29 |
+
Re-optimizing quants, found a better mixture. Uploading shortly.
|
| 30 |
+
|
| 31 |
+
Mixture is strong enough that lower quants can now solve/reasoning and come up with a solution whereas NON-optimized
|
| 32 |
+
may not be able to solve or take a lot longer (a lot more tokens!).
|
| 33 |
+
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
Reka's excellent reasoning model with MAXed quants, and NEO Imatrix dataset.
|
| 37 |
|
| 38 |
128k context.
|
| 39 |
|
| 40 |
Does support other languages besides English.
|
| 41 |
|
| 42 |
+
Quants uploading, examples/repo card updates pending...
|
| 43 |
+
|
| 44 |
+
---
|