agentionai/Qwen3.8-27B-AP-GGUF
Image-Text-to-Text • 27B • Updated • 15.8k • 70
Flavio Catalani
fakezeta
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
agentionai/Qwen3.8-27B-AP-GGUF liked a model 9 days ago
Abiray/MiniMax-H3-Pruned-GGUFOrganizations
liked a
model 3 days ago
liked a
model 9 days ago
reacted to DavidAU's post with 🚀 15 days ago
Post
13863
Qwen 3.8 27B - TWIN TURBO, Fable Fusion (10 modes of operation)
Tuned, and tweaked to match the legendary Qwen 3.6 27B FF711 (2300+ likes, 4 million+ downloads) this fine tune matches the stability and power at "arc-c" 709: (118 pts higher than Qwen 3.8 27B) (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and 701 arc-c in 4 bit AND THIS is instruct mode - thinking/reasoning is higher.
This version is called TWIN-TURBO because it drastically reduces thinking tokens (by 1/2 to as LOW as 1/20), yet maintains output detail and quality. In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.
This repo contains both "regular" and "MTP" Neo and NEO MAX GGUF quants.
BUT WE WENT FURTHER:
Now with 5 reasoning modes (2 new - UltraXhigh / Einstein), and 5 instruct modes (2 new - UltraXhigh / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level).
GGUFS:
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF
SOURCE:
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored
UPDATE:
This model (and a few more) will soon have 12 reasoning and 12 instruct modes plus interactive help, model embedded system to select the best reasoning/instruct mode[s] for all use cases.
Final testing is in progress...
Tuned, and tweaked to match the legendary Qwen 3.6 27B FF711 (2300+ likes, 4 million+ downloads) this fine tune matches the stability and power at "arc-c" 709: (118 pts higher than Qwen 3.8 27B) (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and 701 arc-c in 4 bit AND THIS is instruct mode - thinking/reasoning is higher.
This version is called TWIN-TURBO because it drastically reduces thinking tokens (by 1/2 to as LOW as 1/20), yet maintains output detail and quality. In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.
This repo contains both "regular" and "MTP" Neo and NEO MAX GGUF quants.
BUT WE WENT FURTHER:
Now with 5 reasoning modes (2 new - UltraXhigh / Einstein), and 5 instruct modes (2 new - UltraXhigh / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level).
GGUFS:
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF
SOURCE:
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored
UPDATE:
This model (and a few more) will soon have 12 reasoning and 12 instruct modes plus interactive help, model embedded system to select the best reasoning/instruct mode[s] for all use cases.
Final testing is in progress...
- 2 replies
Task effectiveness maintained – Knowledge loss expected
👍 1
1
#29 opened 16 days ago
by fakezeta
liked a
model about 1 month ago
liked a
model 4 months ago
MTP GGUF?
4
#4 opened 4 months ago
by fakezeta
liked 2
models 5 months ago
reacted to omarkamali's post with 👍 6 months ago
Post
4614
We got Qwen 3.5 to count Rs in Strawberry correctly! 🚨
Building on Sawtone, we’ve been testing a different way to feed language into an LLM to build the next generation of multilingual AI.
The usual setup gives the model tokenized text and asks it to perform various linguistic tasks. That works surprisingly well, until it doesn’t. Accents disappear. Words get mangled. Internal structure gets blurred away. And the cost of that gets higher once you move into multilingual and lower-resource settings.
So we tried adding a second path.
In addition to the normal text input, the model also receives Sawtone: a byte-level word representation that preserves how a word is written, how it sounds, and how it is structured.
Same LLM. Better interface.
In this proof of concept with Qwen 3.5 0.8B, that pushed our eval from 64% to 88%. The gains showed up exactly where tokenized models usually get shaky: diacritics, character order, exact spelling, and other form-sensitive behavior.
Sawtone itself is tokenizer-free, byte-level, and pre-trained across 507 languages.
Still early, but promising!
Building on Sawtone, we’ve been testing a different way to feed language into an LLM to build the next generation of multilingual AI.
The usual setup gives the model tokenized text and asks it to perform various linguistic tasks. That works surprisingly well, until it doesn’t. Accents disappear. Words get mangled. Internal structure gets blurred away. And the cost of that gets higher once you move into multilingual and lower-resource settings.
So we tried adding a second path.
In addition to the normal text input, the model also receives Sawtone: a byte-level word representation that preserves how a word is written, how it sounds, and how it is structured.
Same LLM. Better interface.
In this proof of concept with Qwen 3.5 0.8B, that pushed our eval from 64% to 88%. The gains showed up exactly where tokenized models usually get shaky: diacritics, character order, exact spelling, and other form-sensitive behavior.
Sawtone itself is tokenizer-free, byte-level, and pre-trained across 507 languages.
Still early, but promising!
- 5 replies
liked a
model 6 months ago
<unused49> infinite generation after llama.cpp release b8699
5
#2 opened 6 months ago
by fakezeta
liked a
model 7 months ago
upvoted a collection 7 months ago
liked 3
models 8 months ago
upvoted an article 9 months ago
Article
EuroLLM-22B
eurollm-team
• • 56 liked 2
models 12 months ago
