chore(model gallery): add gustavecortal_beck (#6444)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-10-13 11:59:25 +02:00
committed by GitHub
parent 7e26f28113
commit ef754259b0

View File

@@ -2950,6 +2950,90 @@
- filename: Qwen3-Deckard-Large-Almost-Human-6B.i1-Q4_K_M.gguf
sha256: c92c0e35e37d0e2b520010b95abe2951112ac95d20b8d66706116e52ae677697
uri: huggingface://mradermacher/Qwen3-Deckard-Large-Almost-Human-6B-i1-GGUF/Qwen3-Deckard-Large-Almost-Human-6B.i1-Q4_K_M.gguf
- !!merge <<: *qwen3
name: "gustavecortal_beck-8b"
urls:
- https://huggingface.co/gustavecortal/Beck-8B
- https://huggingface.co/bartowski/gustavecortal_Beck-8B-GGUF
description: |
A language model that handles delicate life situations and tries to really help you.
Beck is based on Piaget and was finetuned on psychotherapeutic preferences from PsychoCounsel-Preference.
Methodology
Beck was trained using preference optimization (ORPO) and LoRA. You can reproduce the results using my repo for lightweight preference optimization using this config that contains the hyperparameters.
This work was performed using HPC resources (Jean Zay supercomputer) from GENCI-IDRIS (Grant 20XX-AD011014205).
Inspiration
Beck aims to reason about psychological and philosophical concepts such as self-image, emotion, and existence.
Beck was inspired by my position paper on emotion analysis: Improving Language Models for Emotion Analysis: Insights from Cognitive Science.
overrides:
parameters:
model: gustavecortal_Beck-8B-Q4_K_M.gguf
files:
- filename: gustavecortal_Beck-8B-Q4_K_M.gguf
sha256: a3025ea58d31d4d1b0a63f165095e21a6620c56e43fe67461e6da9a83df076a8
uri: huggingface://bartowski/gustavecortal_Beck-8B-GGUF/gustavecortal_Beck-8B-Q4_K_M.gguf
- !!merge <<: *qwen3
name: "gustavecortal_beck-0.6b"
urls:
- https://huggingface.co/gustavecortal/Beck-0.6B
- https://huggingface.co/bartowski/gustavecortal_Beck-0.6B-GGUF
description: |
A language model that handles delicate life situations and tries to really help you.
Beck is based on Piaget and was finetuned on psychotherapeutic preferences from PsychoCounsel-Preference.
Methodology
Beck was trained using preference optimization (ORPO) and LoRA. You can reproduce the results using my repo for lightweight preference optimization using this config that contains the hyperparameters.
This work was performed using HPC resources (Jean Zay supercomputer) from GENCI-IDRIS (Grant 20XX-AD011014205).
Inspiration
Beck aims to reason about psychological and philosophical concepts such as self-image, emotion, and existence.
Beck was inspired by my position paper on emotion analysis: Improving Language Models for Emotion Analysis: Insights from Cognitive Science.
overrides:
parameters:
model: gustavecortal_Beck-0.6B-Q4_K_M.gguf
files:
- filename: gustavecortal_Beck-0.6B-Q4_K_M.gguf
sha256: 486cafeb162edbd0134de99bf206e7506e61626470788278e40bf0b9b920308c
uri: huggingface://bartowski/gustavecortal_Beck-0.6B-GGUF/gustavecortal_Beck-0.6B-Q4_K_M.gguf
- !!merge <<: *qwen3
name: "gustavecortal_beck-1.7b"
urls:
- https://huggingface.co/gustavecortal/Beck-1.7B
- https://huggingface.co/bartowski/gustavecortal_Beck-1.7B-GGUF
description: |
A language model that handles delicate life situations and tries to really help you.
Beck is based on Piaget and was finetuned on psychotherapeutic preferences from PsychoCounsel-Preference.
Methodology
Beck was trained using preference optimization (ORPO) and LoRA. You can reproduce the results using my repo for lightweight preference optimization using this config that contains the hyperparameters.
This work was performed using HPC resources (Jean Zay supercomputer) from GENCI-IDRIS (Grant 20XX-AD011014205).
Inspiration
Beck aims to reason about psychological and philosophical concepts such as self-image, emotion, and existence.
Beck was inspired by my position paper on emotion analysis: Improving Language Models for Emotion Analysis: Insights from Cognitive Science.
overrides:
parameters:
model: gustavecortal_Beck-1.7B-Q4_K_M.gguf
files:
- filename: gustavecortal_Beck-1.7B-Q4_K_M.gguf
sha256: 0dfac64e4066da46dc8125cfb00050c29869503f245bc8559ad4b9113d51e545
uri: huggingface://bartowski/gustavecortal_Beck-1.7B-GGUF/gustavecortal_Beck-1.7B-Q4_K_M.gguf
- !!merge <<: *qwen3
name: "gustavecortal_beck-4b"
urls:
- https://huggingface.co/gustavecortal/Beck-4B
- https://huggingface.co/bartowski/gustavecortal_Beck-4B-GGUF
description: |
A language model that handles delicate life situations and tries to really help you.
Beck is based on Piaget and was finetuned on psychotherapeutic preferences from PsychoCounsel-Preference.
Methodology
Beck was trained using preference optimization (ORPO) and LoRA. You can reproduce the results using my repo for lightweight preference optimization using this config that contains the hyperparameters.
This work was performed using HPC resources (Jean Zay supercomputer) from GENCI-IDRIS (Grant 20XX-AD011014205).
Inspiration
Beck aims to reason about psychological and philosophical concepts such as self-image, emotion, and existence.
Beck was inspired by my position paper on emotion analysis: Improving Language Models for Emotion Analysis: Insights from Cognitive Science.
overrides:
parameters:
model: gustavecortal_Beck-4B-Q4_K_M.gguf
files:
- filename: gustavecortal_Beck-4B-Q4_K_M.gguf
sha256: f4af0cf3e6adedabb79c16d8d5d6d23a3996f626d7866ddc27fa80011ce695af
uri: huggingface://bartowski/gustavecortal_Beck-4B-GGUF/gustavecortal_Beck-4B-Q4_K_M.gguf
- &gemma3
url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
name: "gemma-3-27b-it"