|
Download README.md from Samonte/mt_slm_ctx_compress: direct link, hf CLI and curl.
- Browser
- Download file 915 Bytes
-
https://huggingface.co/Samonte/mt_slm_ctx_compress/resolve/main/README.md
- Command line
-
hf download hf://Samonte/mt_slm_ctx_compress/README.md
-
curl -L -o README.md https://huggingface.co/Samonte/mt_slm_ctx_compress/resolve/main/README.md
915 Bytes
metadata
license: other
license_name: microtensor-submission
license_link: https://www.microtensor.cloud/terms
base_model: ibm-granite/granite-4.0-h-micro
tags:
- microtensor
- ctx_compress
mt_slm_ctx_compress
A specialised model for the Microtensor ctx_compress arena (agent session compaction): it reads a
coding agent session of up to 120k tokens and writes the nine heading compaction summary.
| Field | Value |
|---|---|
| Base model | ibm-granite/granite-4.0-h-micro at d5f01a3ea75f (Apache 2.0) |
| Method | LoRA r=64 merged into bf16 |
| Arena | ctx_compress |
| Training data | sessions from the arena's own generator (microtensor-io/microtensor-arenas, arenas/compress/synth.py) under private seeds |
| Held out result | see training/runs |
The root loads with AutoModelForCausalLM. Everything under training/ is the record validators
require and the archive keeps; it is never scored.