Yes I agree with this!!
Sk md saad amin
Reality123b
ยท
AI & ML interests
None yet
Recent Activity
commentedon an article about 21 hours ago
You do the work. Big Tech takes the model. upvoted an article about 21 hours ago
You do the work. Big Tech takes the model. new activity about 21 hours ago
blog-explorers/README:[Support] Community ArticlesOrganizations
commented on You do the work. Big Tech takes the model. about 21 hours ago
upvoted an article about 21 hours ago
Article
You do the work. Big Tech takes the model.
urroxyz
โข โข 3 [Support] Community Articles
๐ค๐ 2
106
#5 opened about 2 years ago
by 
victor
updated a
Space 3 days ago
OrionLLM/GRM-2.6-Opus
๐ 2
#9764 opened 5 days ago
by Reality123b
updated a
Space 6 days ago
published a
Space 6 days ago
updated a
Space 6 days ago
published a
Space 6 days ago
Future of Agentic Models
๐ฅ 2
12
#18 opened 14 days ago
by 
MohamedRashad
updated a
model 10 days ago
published a
model 10 days ago
updated a
model 10 days ago
published a
model 10 days ago
updated a
Space 10 days ago
published a
Space 10 days ago
reacted to cihatyldz's post with ๐ 10 days ago
Post
3513
ลifahane, a dual-inference medical classification demo, is now live on Spaces. It features side-by-side Turkish BERT and Qwen2.5 architectures for real-time evaluation of the "Classifier vs. LLM" trade-offs, all within a single space. The system utilizes a fine-tuned Turkish BERT for high-speed, cost-effective inference and the Qwen2.5-7B model for flexible multi-task reasoning, with support for department classification, condition analysis, urgency assessment, and rationale generation across 12 medical departments.
๐ง BERT model: https://lnkd.in/dCUUASqq
๐ Dataset: https://lnkd.in/dGK9y24w
๐ค Demo: https://lnkd.in/dtWjCCPF
๐ง BERT model: https://lnkd.in/dCUUASqq
๐ Dataset: https://lnkd.in/dGK9y24w
๐ค Demo: https://lnkd.in/dtWjCCPF
reacted to DavidAU's post with โค๏ธ 12 days ago
Post
8140
Uncensored, Heretic, Qwen 3.6 27B GGUFs - Exceeds all quant metrics and core model metrics too.
Tuned 27B Heretic Uncensored quants from IQ2M to Q8.
IQ2M is 83% of BF16, with Q6 just under 98% of BF16 precision.
Q8: 98.47% of BF16 precision.
NEO/Code DI-Imatrix Quants.
Exceeds all 5 metrics for "censored" quants too.
All metrics posted.
Tuned model -from which the quants were built- also exceeds Qwen 3.6 27B core metrics too.
DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF
Tuned 27B Heretic Uncensored quants from IQ2M to Q8.
IQ2M is 83% of BF16, with Q6 just under 98% of BF16 precision.
Q8: 98.47% of BF16 precision.
NEO/Code DI-Imatrix Quants.
Exceeds all 5 metrics for "censored" quants too.
All metrics posted.
Tuned model -from which the quants were built- also exceeds Qwen 3.6 27B core metrics too.
DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF
- 4 replies
unsloth plushie
#26 opened 13 days ago
by Reality123b