Downloads · 30 days
9
0% of all-time downloads
tensoropera_-_Fox-1-1.6B-gguf
RichardErkhov/tensoropera_-_Fox-1-1.6B-gguf
tensoropera_-_Fox-1-1.6B-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
7K
Public
Repo size
21.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf24.6 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 24, 2024
- Updated
- Jun 24, 2024
- SHA
- 80ec3744
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Fox-1-1.6B - GGUF
- Model creator: https://huggingface.co/tensoropera/
- Original model: https://huggingface.co/tensoropera/Fox-1-1.6B/
| Name | Quant method | Size |
|---|---|---|
| Fox-1-1.6B.Q2_K.gguf | Q2_K | 0.8GB |
| Fox-1-1.6B.IQ3_XS.gguf | IQ3_XS | 0.84GB |
| Fox-1-1.6B.IQ3_S.gguf | IQ3_S | 0.87GB |
| Fox-1-1.6B.Q3_K_S.gguf | Q3_K_S | 0.86GB |
| Fox-1-1.6B.IQ3_M.gguf | IQ3_M | 0.89GB |
| Fox-1-1.6B.Q3_K.gguf | Q3_K | 0.92GB |
| Fox-1-1.6B.Q3_K_M.gguf | Q3_K_M | 0.92GB |
| Fox-1-1.6B.Q3_K_L.gguf | Q3_K_L | 0.97GB |
| Fox-1-1.6B.IQ4_XS.gguf | IQ4_XS | 0.98GB |
| Fox-1-1.6B.Q4_0.gguf | Q4_0 | 1.0GB |
| Fox-1-1.6B.IQ4_NL.gguf | IQ4_NL | 1.01GB |
| Fox-1-1.6B.Q4_K_S.gguf | Q4_K_S | 1.01GB |
| Fox-1-1.6B.Q4_K.gguf | Q4_K | 1.04GB |
| Fox-1-1.6B.Q4_K_M.gguf | Q4_K_M | 1.04GB |
| Fox-1-1.6B.Q4_1.gguf | Q4_1 | 1.07GB |
| Fox-1-1.6B.Q5_0.gguf | Q5_0 | 1.14GB |
| Fox-1-1.6B.Q5_K_S.gguf | Q5_K_S | 1.14GB |
| Fox-1-1.6B.Q5_K.gguf | Q5_K | 1.16GB |
| Fox-1-1.6B.Q5_K_M.gguf | Q5_K_M | 1.16GB |
| Fox-1-1.6B.Q5_1.gguf | Q5_1 | 1.2GB |
| Fox-1-1.6B.Q6_K.gguf | Q6_K | 1.28GB |
| Fox-1-1.6B.Q8_0.gguf | Q8_0 | 1.65GB |
Original model description:
license: apache-2.0 language:
- en pipeline_tag: text-generation
Model Card for Fox-1-1.6B
[!IMPORTANT]
This model is a base pretrained model which requires further finetuning for most use cases. We will release the instruction-tuned version soon.
Fox-1 is a decoder-only transformer-based small language model (SLM) with 1.6B total parameters developed by TensorOpera AI. The model was trained with a 3-stage data curriculum on 3 trillion tokens of text and code data in 8K sequence length. Fox-1 uses grouped query attention (GQA) with 4 KV heads and 16 attention heads and has a deeper architecture than other SLMs.
For the full details of this model please read our release blog post.
- Created
- Jun 24, 2024
- Updated
- Jun 24, 2024