Downloads · 30 days
108
14% of all-time downloads
RichardErkhov/kevin009_-_TinyNaughtyLlama-v1.0-gguf
kevin009_-_TinyNaughtyLlama-v1.0-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
108
14% of all-time downloads
All-time downloads
750
Public
Repo size
12.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf14.7 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
TinyNaughtyLlama-v1.0 - GGUF
| Name | Quant method | Size |
|---|---|---|
| TinyNaughtyLlama-v1.0.Q2_K.gguf | Q2_K | 0.4GB |
| TinyNaughtyLlama-v1.0.IQ3_XS.gguf | IQ3_XS | 0.44GB |
| TinyNaughtyLlama-v1.0.IQ3_S.gguf | IQ3_S | 0.47GB |
| TinyNaughtyLlama-v1.0.Q3_K_S.gguf | Q3_K_S | 0.47GB |
| TinyNaughtyLlama-v1.0.IQ3_M.gguf | IQ3_M | 0.48GB |
| TinyNaughtyLlama-v1.0.Q3_K.gguf | Q3_K | 0.51GB |
| TinyNaughtyLlama-v1.0.Q3_K_M.gguf | Q3_K_M | 0.51GB |
| TinyNaughtyLlama-v1.0.Q3_K_L.gguf | Q3_K_L | 0.55GB |
| TinyNaughtyLlama-v1.0.IQ4_XS.gguf | IQ4_XS | 0.57GB |
| TinyNaughtyLlama-v1.0.Q4_0.gguf | Q4_0 | 0.59GB |
| TinyNaughtyLlama-v1.0.IQ4_NL.gguf | IQ4_NL | 0.6GB |
| TinyNaughtyLlama-v1.0.Q4_K_S.gguf | Q4_K_S | 0.6GB |
| TinyNaughtyLlama-v1.0.Q4_K.gguf | Q4_K | 0.62GB |
| TinyNaughtyLlama-v1.0.Q4_K_M.gguf | Q4_K_M | 0.62GB |
| TinyNaughtyLlama-v1.0.Q4_1.gguf | Q4_1 | 0.65GB |
| TinyNaughtyLlama-v1.0.Q5_0.gguf | Q5_0 | 0.71GB |
| TinyNaughtyLlama-v1.0.Q5_K_S.gguf | Q5_K_S | 0.71GB |
| TinyNaughtyLlama-v1.0.Q5_K.gguf | Q5_K | 0.73GB |
| TinyNaughtyLlama-v1.0.Q5_K_M.gguf | Q5_K_M | 0.73GB |
| TinyNaughtyLlama-v1.0.Q5_1.gguf | Q5_1 | 0.77GB |
| TinyNaughtyLlama-v1.0.Q6_K.gguf | Q6_K | 0.84GB |
| TinyNaughtyLlama-v1.0.Q8_0.gguf | Q8_0 | 1.09GB |
license: apache-2.0 model-index:
A DPO version of TinyLlama
Finetunned based on TinyLlama 1.1B Chat is a language model designed for various natural language processing tasks. It utilizes the Llama architecture with a substantial number of hidden layers, attention heads, and a large vocabulary size. The model is trained to generate text in a causal manner, which means it predicts the next word in a sequence based on the preceding context.
The model has undergone pretraining with a pretraining task weight of 1.
While this model can generate text, it should be used responsibly and ethically. It may generate inappropriate or biased content, and it is the responsibility of users to filter and moderate the output.
The model is available at TinyLlama/TinyLlama-1.1B-Chat-v1.0.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 37.03 |
| AI2 Reasoning Challenge (25-Shot) | 35.92 |
| HellaSwag (10-Shot) | 61.04 |
| MMLU (5-Shot) | 25.82 |
| TruthfulQA (0-shot) | 36.77 |
| Winogrande (5-shot) | 60.22 |
| GSM8k (5-shot) | 2.43 |