Downloads · 30 days
13
5% of all-time downloads
renaudb1999/le-harnais-ft-counsel-Meta-Llama-3.1-8B-Instruct-regular-dom2
le-harnais-ft-counsel-Meta-Llama-3.1-8B-Instruct-regular-dom2 is a text generation model from renaudb1999. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.1.
⚠️ retrain-only — this is an ablation checkpoint, not useful for inference. It ships only to reproduce / continue the training study. For real use see the hero models: le-harnais-ft-agentworld-{1b,3b,8b}, le-harnais-f…
Downloads · 30 days
13
5% of all-time downloads
All-time downloads
239
Public
Parameters
8B
21 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 76%
From the Hugging Face model README
⚠️ retrain-only — this is an ablation checkpoint, not useful for inference. It ships only to reproduce / continue the training study. For real use see the hero models:
le-harnais-ft-agentworld-{1b,3b,8b},le-harnais-ft-counsel.
Counsel-corpus ablation (scaling / data-augmentation / JEPA). JEPA ≈ +7 @3B, ≈0 @8B.
meta-llama/Meta-Llama-3.1-8B-Instruct — Built with Llama; Llama Community License applies.ablationsee docs/jepa.md (counsel scaling grid)
Full recipe, datasets, and eval commands: see docs/REPRODUCE.md in the
[le-harnais distribution]. Provenance & license: docs/PROVENANCE.md.
*.safetensors — bf16 inference weights (serve with transformers or le-harnais lh-serve/candle).*.Q4_K_M.gguf — portable 4-bit quant (run via ollama / llama.cpp; Mac-friendly).Orchestration amplifies a capable generator; it does not create competence.