AltAPIs

sadmN/moshi-base7b-rag

AI model by sadmN

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

A full 32-layer PersonaPlex 7B (8.37 B params) fine-tuned with RAG, served as a full-duplex streaming voice assistant whose factual answers come from a retrieved passage injected into the pause — zero extra frames, zero added silence. recipe (refmode=text, refpos=pause, K=16, lookupweight=6) 32002 (pad/initial row moved to 32003) into the pause the model already produces before its answer, so retrieval adds zero frames and zero silence — the audio is the model's own pause. 4-gram Jaccard against the question with an anchor on the question's rarest content word (ragrefselect.selectwindowids). This checkpoint is mute on the state-machine server (serverstudentrag.py) that ships with the S28 student: that server forces the model's own audio stream to a constant SILENCETOKENS vector while the user speaks, a self-context the fine-tune never saw in training, so it never emits and waits forever. This is fixed by the included single-path streaming server (serverragstream.py): the LM steps every…

sadmN/moshi-base7b-rag on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-30T02:01:24.431Z

Inside the original model card — Document outline
  1. PersonaPlex 7B RAG — base fine-tune (step 1500)
  2. IMPORTANT — streaming server required
  3. Files
  4. Quick start (new machine)
  5. Hardware
  6. Test
  7. Limits
  8. Licence

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

sadmN/moshi-base7b-rag is a task-unspecified model repository published by sadmN on Hugging Face. The source reports the moshi library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
Not reported
Library
moshi
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
Not reported — check the model card
Access
Not gated by Hugging Face
Created
2026-10-25T06:22:32.000Z
Last modified
2026-10-25T06:26:11.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-25T06:46:38.979Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models