Downloads · 30 days
173
3% of all-time downloads
RichardErkhov/ToastyPigeon_-_SmolPlatypus-1.5B-gguf
ToastyPigeon_-_SmolPlatypus-1.5B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
173
3% of all-time downloads
All-time downloads
6.2K
Public
Repo size
17.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf20.4 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
SmolPlatypus-1.5B - GGUF
| Name | Quant method | Size |
|---|---|---|
| SmolPlatypus-1.5B.Q2_K.gguf | Q2_K | 0.55GB |
| SmolPlatypus-1.5B.IQ3_XS.gguf | IQ3_XS | 0.61GB |
| SmolPlatypus-1.5B.IQ3_S.gguf | IQ3_S | 0.64GB |
| SmolPlatypus-1.5B.Q3_K_S.gguf | Q3_K_S | 0.64GB |
| SmolPlatypus-1.5B.IQ3_M.gguf | IQ3_M | 0.67GB |
| SmolPlatypus-1.5B.Q3_K.gguf | Q3_K | 0.71GB |
| SmolPlatypus-1.5B.Q3_K_M.gguf | Q3_K_M | 0.71GB |
| SmolPlatypus-1.5B.Q3_K_L.gguf | Q3_K_L | 0.77GB |
| SmolPlatypus-1.5B.IQ4_XS.gguf | IQ4_XS | 0.79GB |
| SmolPlatypus-1.5B.Q4_0.gguf | Q4_0 | 0.82GB |
| SmolPlatypus-1.5B.IQ4_NL.gguf | IQ4_NL | 0.83GB |
| SmolPlatypus-1.5B.Q4_K_S.gguf | Q4_K_S | 0.83GB |
| SmolPlatypus-1.5B.Q4_K.gguf | Q4_K | 0.87GB |
| SmolPlatypus-1.5B.Q4_K_M.gguf | Q4_K_M | 0.87GB |
| SmolPlatypus-1.5B.Q4_1.gguf | Q4_1 | 0.91GB |
| SmolPlatypus-1.5B.Q5_0.gguf | Q5_0 | 1.0GB |
| SmolPlatypus-1.5B.Q5_K_S.gguf | Q5_K_S | 1.0GB |
| SmolPlatypus-1.5B.Q5_K.gguf | Q5_K | 1.02GB |
| SmolPlatypus-1.5B.Q5_K_M.gguf | Q5_K_M | 1.02GB |
| SmolPlatypus-1.5B.Q5_1.gguf | Q5_1 | 1.08GB |
| SmolPlatypus-1.5B.Q6_K.gguf | Q6_K | 1.18GB |
| SmolPlatypus-1.5B.Q8_0.gguf | Q8_0 | 1.53GB |
base_model:
This is a proof-of-concept model and should not be used for anything.
This is a merge of pre-trained language models created using mergekit.
The LoRA adapter was created with axolotl using qlora (I know, it's misnamed) training a solar-style stack merge dubbed "SmolLlama-1.5B" on the Open-Platypus dataset for approximately 2 hours on 2x RTX 3060.
This model was merged using the passthrough merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: ToastyPigeon/SmolLlama-1.5B+ToastyPigeon/SmolPlatypus-1.5B-LoRA
merge_method: passthrough
dtype: float16