Downloads · 30 days
72
2% of all-time downloads
ModelCloud_-_tinyllama-15M-stories-gguf
RichardErkhov/ModelCloud_-_tinyllama-15M-stories-gguf
ModelCloud_-_tinyllama-15M-stories-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.
All-time downloads
3.8K
Public
Repo size
275 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf319 MB · 100%
At a glance
- Access
- Public
- Created
- Jul 14, 2024
- Updated
- Jul 14, 2024
- SHA
- 13520e21
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
tinyllama-15M-stories - GGUF
- Model creator: https://huggingface.co/ModelCloud/
- Original model: https://huggingface.co/ModelCloud/tinyllama-15M-stories/
| Name | Quant method | Size |
|---|---|---|
| tinyllama-15M-stories.Q2_K.gguf | Q2_K | 0.01GB |
| tinyllama-15M-stories.IQ3_XS.gguf | IQ3_XS | 0.01GB |
| tinyllama-15M-stories.IQ3_S.gguf | IQ3_S | 0.01GB |
| tinyllama-15M-stories.Q3_K_S.gguf | Q3_K_S | 0.01GB |
| tinyllama-15M-stories.IQ3_M.gguf | IQ3_M | 0.01GB |
| tinyllama-15M-stories.Q3_K.gguf | Q3_K | 0.01GB |
| tinyllama-15M-stories.Q3_K_M.gguf | Q3_K_M | 0.01GB |
| tinyllama-15M-stories.Q3_K_L.gguf | Q3_K_L | 0.01GB |
| tinyllama-15M-stories.IQ4_XS.gguf | IQ4_XS | 0.01GB |
| tinyllama-15M-stories.Q4_0.gguf | Q4_0 | 0.01GB |
| tinyllama-15M-stories.IQ4_NL.gguf | IQ4_NL | 0.01GB |
| tinyllama-15M-stories.Q4_K_S.gguf | Q4_K_S | 0.01GB |
| tinyllama-15M-stories.Q4_K.gguf | Q4_K | 0.01GB |
| tinyllama-15M-stories.Q4_K_M.gguf | Q4_K_M | 0.01GB |
| tinyllama-15M-stories.Q4_1.gguf | Q4_1 | 0.01GB |
| tinyllama-15M-stories.Q5_0.gguf | Q5_0 | 0.01GB |
| tinyllama-15M-stories.Q5_K_S.gguf | Q5_K_S | 0.01GB |
| tinyllama-15M-stories.Q5_K.gguf | Q5_K | 0.01GB |
| tinyllama-15M-stories.Q5_K_M.gguf | Q5_K_M | 0.01GB |
| tinyllama-15M-stories.Q5_1.gguf | Q5_1 | 0.01GB |
| tinyllama-15M-stories.Q6_K.gguf | Q6_K | 0.02GB |
| tinyllama-15M-stories.Q8_0.gguf | Q8_0 | 0.02GB |
Original model description:
license: mit
This is the 15M parameter Llama 2 architecture model trained on the TinyStories dataset. These are converted from karpathy/tinyllamas. See the llama2.c project for more details.
- Created
- Jul 14, 2024
- Updated
- Jul 14, 2024