Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,44 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- gustavecortal/Piaget-4B
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- gustavecortal/Piaget-4B
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- text-generation-inference
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# **Piaget-4B-GGUF**
|
| 14 |
+
|
| 15 |
+
> Piaget, a language model finetuned on 15k psychological and philosophical reasoning traces. Piaget is based on Qwen3 and was finetuned on a subset of open reasoning traces from Dolphin R1 and General Reasoning. Performed domain filtering on Dolphin R1 and General Reasoning. Prompts were embedded, clustered with k-means (k=20 000) and majority-voted for domain labels using Qwen3-1.7B, following the Intelligent Internet pipeline. Clusters tagged psychology or philosophy were retained for LoRA finetuning (rank=8, alpha=16, max length=2048, epoch=1, batch size=16). Piaget aims to reason about psychological and philosophical concepts such as self-image, emotion, and existence. Piaget was inspired by my position paper on emotion analysis: Improving Language Models for Emotion Analysis: Insights from Cognitive Science.
|
| 16 |
+
|
| 17 |
+
## Model files
|
| 18 |
+
|
| 19 |
+
| File | Size | Format |
|
| 20 |
+
|------|------|--------|
|
| 21 |
+
| Piaget-4B.BF16.gguf | 8.05 GB | BF16 |
|
| 22 |
+
| Piaget-4B.F16.gguf | 8.05 GB | F16 |
|
| 23 |
+
| Piaget-4B.F32.gguf | 16.1 GB | F32 |
|
| 24 |
+
| Piaget-4B.Q2_K.gguf | 1.67 GB | Q2_K |
|
| 25 |
+
| Piaget-4B.Q3_K_L.gguf | 2.24 GB | Q3_K_L |
|
| 26 |
+
| Piaget-4B.Q3_K_M.gguf | 2.08 GB | Q3_K_M |
|
| 27 |
+
| Piaget-4B.Q3_K_S.gguf | 1.89 GB | Q3_K_S |
|
| 28 |
+
| Piaget-4B.Q4_K_M.gguf | 2.5 GB | Q4_K_M |
|
| 29 |
+
| Piaget-4B.Q4_K_S.gguf | 2.38 GB | Q4_K_S |
|
| 30 |
+
| Piaget-4B.Q5_K_M.gguf | 2.89 GB | Q5_K_M |
|
| 31 |
+
| Piaget-4B.Q5_K_S.gguf | 2.82 GB | Q5_K_S |
|
| 32 |
+
| Piaget-4B.Q6_K.gguf | 3.31 GB | Q6_K |
|
| 33 |
+
| Piaget-4B.Q8_0.gguf | 4.28 GB | Q8_0 |
|
| 34 |
+
| .gitattributes | 2.4 kB | - |
|
| 35 |
+
| README.md | 65 Bytes | - |
|
| 36 |
+
| config.json | 29 Bytes | - |
|
| 37 |
+
|
| 38 |
+
## Quants Usage
|
| 39 |
+
|
| 40 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 41 |
+
|
| 42 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 43 |
+
types (lower is better):
|
| 44 |
+
|
| 45 |
+
|