LFM2.5 8B A1B Terminal ECHO RLVR GRPO Adapters
license: apache-2.0 basemodel: LiquidAI/LFM2.5-8B-A1B tags: liquid-ai lfm2.5 terminal-agent rlvr echo grpo lora adapter
Source du modèle
- Type
- Checkpoint, LoRA, Text model
- Taille du fichier
- 49,1 MB
- Modèle de base
- LiquidAI/LFM2.5-8B-A1B
- Version
- vadapter_model
- Mis à jour
- 7 oct. 2026
- Éditeur
- @LLM-OS-Models
- Paramètres
- 8B
- Source
- Hugging Face
Description de la source
LFM2.5-8B-A1B-Terminal-ECHO-RLVR-GRPO-Adapters
LoRA adapter checkpoints from an ECHO-style terminal RLVR run.
Training Setup
- Base model:
LiquidAI/LFM2.5-8B-A1B - Resume adapter: ``
- Run ID:
run_20260612T113238Z_echo_raw_lfm25_vllm4_train2_g4_t4_tok256_save25_wm005_2k - vLLM GPUs:
0,1,2,3 - Training GPUs:
4,5 - No-Docker sandbox:
true - World-model coefficient:
0.05 - Learning rate: ``
- Save interval: every
25train steps
Latest Snapshot
- Synced at UTC:
2026-06-13T00:16:06.252887+00:00 - Latest uploaded checkpoint:
checkpoint-1350 - Uploaded checkpoints:
checkpoint-25, checkpoint-50, checkpoint-75, checkpoint-100, checkpoint-125, checkpoint-150, checkpoint-175, checkpoint-200, checkpoint-225, checkpoint-250, checkpoint-275, checkpoint-300, checkpoint-325, checkpoint-350, checkpoint-375, checkpoint-400, checkpoint-425, checkpoint-450, checkpoint-475, checkpoint-500, checkpoint-525, checkpoint-550, checkpoint-575, checkpoint-600, checkpoint-625, checkpoint-650, checkpoint-675, checkpoint-700, checkpoint-725, checkpoint-750, checkpoint-775, checkpoint-800, checkpoint-825, checkpoint-850, checkpoint-875, checkpoint-900, checkpoint-925, checkpoint-950, checkpoint-975, checkpoint-1000, checkpoint-1025, checkpoint-1050, checkpoint-1075, checkpoint-1100, checkpoint-1125, checkpoint-1150, checkpoint-1175, checkpoint-1200, checkpoint-1225, checkpoint-1250, checkpoint-1275, checkpoint-1300, checkpoint-1325, checkpoint-1350
Layout
checkpoints/checkpoint-*: PEFT/LoRA adapter checkpoint directories.manifest.json: sync metadata.run.env.redacted: training configuration with secret-like values redacted.
The paired rollout dataset is:
LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ECHO-RLVR-Rollouts
That dataset stores the terminal actions, observations, verifier outcomes, and train-step metrics that produced these adapter checkpoints.
Sources
1 source
Sources
1 sourceVérifié 1 sept.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactcheckpoints/checkpoint-10/adapter_model.safetensors
safetensors · 49,1 MB · SHA-256 2bcdc417ee25…b82f · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: apache-2.0 base_model: LiquidAI/LFM2.5-8B-A1B tags: - liquid-ai - lfm2.5 - terminal-agent - rlvr - echo - grpo - lora - adapter --- # LFM2.5-8B-A1B-Terminal-ECHO-RLVR-GRPO-Adapters LoRA adapter checkpoints from an ECHO-style terminal RLVR run. ## Training Setup - Base model: `LiquidAI/LFM2.5-8B-A1B` - Resume adapter: `` - Run ID: `run_20260612T113238Z_echo_raw_lfm25_vllm4_train2_g4_t4_tok256_save25_wm005_2k` - vLLM GPUs: `0,1,2,3` - Training GPUs: `4,5` - No-Docker sandbox: `true` - World-model coefficient: `0.05` - Learning rate: `` - Save interval: every `25` train steps ## Latest Snapshot - Synced at UTC: `2026-06-13T00:16:06.252887+00:00` - Latest uploaded checkpoint: `checkpoint-1350` - Uploaded checkpoints: `checkpoint-25, checkpoint-50, checkpoint-75, checkpoint-100, checkpoint-125, checkpoint-150, checkpoint-175, checkpoint-200, checkpoint-225, checkpoint-250, checkpoint-275, checkpoint-300, checkpoint-325, checkpoint-350, checkpoint-375, checkpoint-400, checkpoint-425, checkpoint-450, checkpoint-475, checkpoint-500, checkpoint-525, checkpoint-550, checkpoint-575, checkpoint-600, checkpoint-625, checkpoint-650, checkpoint-675, checkpoint-700, checkpoint-725, checkpoint-750, checkpoint-775, checkpoint-800, checkpoint-825, checkpoint-850, checkpoint-875, checkpoint-900, checkpoint-925, checkpoint-950, checkpoint-975, checkpoint-1000, checkpoint-1025, checkpoint-1050, checkpoint-1075, checkpoint-1100, checkpoint-1125, checkpoint-1150, checkpoint-1175, checkpoint-1200, checkpoint-1225, checkpoint-1250, checkpoint-1275, checkpoint-1300, checkpoint-1325, checkpoint-1350` ## Layout - `checkpoints/checkpoint-*`: PEFT/LoRA adapter checkpoint directories. - `manifest.json`: sync metadata. - `run.env.redacted`: training configuration with secret-like values redacted. The paired rollout dataset is: `LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ECHO-RLVR-Rollouts` That dataset stores the terminal actions, observations, verifier outcomes, and train-step metrics that produced these adapter checkpoints.
Source context: 0 downloads · 1 likes · Repo LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ECHO-RLVR-GRPO-Adapters
Source context: 0 downloads · 1 likes · Repo LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ECHO-RLVR-GRPO-Adapters
