audnai/penclaw-GLM-5.3-abliterated
Text Generation β’ 753B β’ Updated β’ 1.38k β’ 289
kivirvvn
kivirvvn
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
audnai/penclaw-GLM-5.3-abliterated liked a model 4 days ago
IQuestLab/IQuest-Q1 liked a Space 5 days ago
linoyts/Qwen-Image-2.1-MoveOrganizations
liked a
model 3 days ago
liked a
model 4 days ago
liked a
Space 5 days ago
liked a
Space 7 days ago
liked a
model 7 days ago
liked a
Space 8 days ago
liked a
model 8 days ago
liked a
model 9 days ago
liked a
model 11 days ago
liked 2
Spaces 11 days ago
liked a
dataset 11 days ago
reacted to Yuki131's post with π₯ 11 days ago
Post
3639
Meet KaLM-Jev β your local, Jev-style judgment engine, available in Nano, Small, and Large.
Building an agent or automation workflow? Sometimes all you need is a choice, a score, or a signal that a condition holds.
Built on KaLM-Reranker-R2, KaLM-Jev turns these decisions into structured outputs through three primitives:
π Choice β select among candidates, with a probability distribution.
π Score β return a continuous score over your defined levels.
π Noul β evaluate conditions independently, so multiple conditions can hold at once.
Think support-ticket routing, bug severity scoring, human-escalation detection, or candidate tool selection for agents.
π₯οΈ Run locally with downloaded weights
π¦ Choose from Nano / Small / Large
π Integrate through HTTP or Python
β‘ Reuse cached candidate/rule representations to reduce repeated encoding
π§ͺ Explore included examples, bilingual semantic smoke tests, and recorded GPU validation results
No answer-text generation:
KaLM-Jev is an independent implementation based on KaLM-Reranker, not an official TypeSafe project or a guarantee of full Jev compatibility. Scores are uncalibrated; validate thresholds on your own tasks.
Code & quickstart:
https://github.com/KaLM-Embedding/KaLM-Jev
Yuki131/KaLM-Jev
Weβd love to hear what youβd build with it. Try it out, share feedback, or open an issue! π€
#Jev #Reranker #Agents #LocalAI #OpenSource
Building an agent or automation workflow? Sometimes all you need is a choice, a score, or a signal that a condition holds.
Built on KaLM-Reranker-R2, KaLM-Jev turns these decisions into structured outputs through three primitives:
π Choice β select among candidates, with a probability distribution.
π Score β return a continuous score over your defined levels.
π Noul β evaluate conditions independently, so multiple conditions can hold at once.
Think support-ticket routing, bug severity scoring, human-escalation detection, or candidate tool selection for agents.
π₯οΈ Run locally with downloaded weights
π¦ Choose from Nano / Small / Large
π Integrate through HTTP or Python
β‘ Reuse cached candidate/rule representations to reduce repeated encoding
π§ͺ Explore included examples, bilingual semantic smoke tests, and recorded GPU validation results
No answer-text generation:
output_tokens = 0. Inference still runs to compute the judgments.KaLM-Jev is an independent implementation based on KaLM-Reranker, not an official TypeSafe project or a guarantee of full Jev compatibility. Scores are uncalibrated; validate thresholds on your own tasks.
Code & quickstart:
https://github.com/KaLM-Embedding/KaLM-Jev
Yuki131/KaLM-Jev
Weβd love to hear what youβd build with it. Try it out, share feedback, or open an issue! π€
#Jev #Reranker #Agents #LocalAI #OpenSource
- 1 reply
liked a
model 11 days ago
liked a
model 12 days ago
liked 2
Spaces 12 days ago
liked a
model 12 days ago
liked a
Space 13 days ago
liked a
model 13 days ago
