42 lines
1.7 KiB
Markdown
42 lines
1.7 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
base_model:
|
||
|
|
- gustavecortal/Piaget-1.7B
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- text-generation-inference
|
||
|
|
---
|
||
|
|
|
||
|
|
# **Piaget-1.7B-f32-GGUF**
|
||
|
|
|
||
|
|
> Piaget is a language model fine-tuned on 15,000 psychological and philosophical reasoning traces. Built on top of Qwen3, it was trained using a curated subset of open reasoning data from Dolphin R1 and the General Reasoning dataset. Piaget is designed to explore and reason about complex human-centered concepts such as self-image, emotion, and existence. The model was inspired by insights from the position paper Improving Language Models for Emotion Analysis: Insights from Cognitive Science, which highlights the importance of cognitive science in enhancing emotion understanding in language models.
|
||
|
|
|
||
|
|
## Model Files
|
||
|
|
|
||
|
|
| File Name | Quant Type | Size |
|
||
|
|
|-----------|------------|------|
|
||
|
|
| Piaget-1.7B.BF16.gguf | BF16 | 3.45 GB |
|
||
|
|
| Piaget-1.7B.F16.gguf | F16 | 3.45 GB |
|
||
|
|
| Piaget-1.7B.F32.gguf | F32 | 6.89 GB |
|
||
|
|
| Piaget-1.7B.Q2_K.gguf | Q2_K | 778 MB |
|
||
|
|
| Piaget-1.7B.Q3_K_L.gguf | Q3_K_L | 1 GB |
|
||
|
|
| Piaget-1.7B.Q3_K_M.gguf | Q3_K_M | 940 MB |
|
||
|
|
| Piaget-1.7B.Q3_K_S.gguf | Q3_K_S | 867 MB |
|
||
|
|
| Piaget-1.7B.Q4_K_M.gguf | Q4_K_M | 1.11 GB |
|
||
|
|
| Piaget-1.7B.Q4_K_S.gguf | Q4_K_S | 1.06 GB |
|
||
|
|
| Piaget-1.7B.Q5_K_M.gguf | Q5_K_M | 1.26 GB |
|
||
|
|
| Piaget-1.7B.Q5_K_S.gguf | Q5_K_S | 1.23 GB |
|
||
|
|
| Piaget-1.7B.Q6_K.gguf | Q6_K | 1.42 GB |
|
||
|
|
| Piaget-1.7B.Q8_0.gguf | Q8_0 | 1.83 GB |
|
||
|
|
|
||
|
|
## Quants Usage
|
||
|
|
|
||
|
|
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
||
|
|
|
||
|
|
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
||
|
|
types (lower is better):
|
||
|
|
|
||
|
|
|