JevEmbed-KaLM-Embedding-V2.5
JevEmbed-KaLM-Embedding-V2.5 by HIT-TMG is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- HIT-TMG
- Parameters
- 494M
- Released
- Sep 2026
- Open weights
- Yes
- Question types
- —
- Mechanism
- Decoder LM with a decision readout
- Backbone
- KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
- Jev-compatible request
- No
- Runs on CPU
- Yes
- License
- apache-2.0
- Hugging Face
- HIT-TMG/JevEmbed-KaLM-Embedding-V2.5
Compare JevEmbed-KaLM-Embedding-V2.5 with…
FAQ
How much does JevEmbed-KaLM-Embedding-V2.5 cost?
JevEmbed-KaLM-Embedding-V2.5 has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can JevEmbed-KaLM-Embedding-V2.5 answer?
JevEmbed-KaLM-Embedding-V2.5 answers typed questions about a piece of text, returning a probability for each allowed answer.
Is JevEmbed-KaLM-Embedding-V2.5 well calibrated?
No calibration measurement for JevEmbed-KaLM-Embedding-V2.5 is recorded yet.
Is JevEmbed-KaLM-Embedding-V2.5 open weight, and can it run on a CPU?
Yes, JevEmbed-KaLM-Embedding-V2.5 has open weights. It is small enough to run on a CPU.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.