Downloads · 30 days
46
5% of all-time downloads
nnpy_-_Nape-0-gguf
RichardErkhov/nnpy_-_Nape-0-gguf
nnpy_-_Nape-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.
All-time downloads
872
Public
Repo size
12.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf14.7 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024
- SHA
- 11762888
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Nape-0 - GGUF
- Model creator: https://huggingface.co/nnpy/
- Original model: https://huggingface.co/nnpy/Nape-0/
| Name | Quant method | Size |
|---|---|---|
| Nape-0.Q2_K.gguf | Q2_K | 0.4GB |
| Nape-0.IQ3_XS.gguf | IQ3_XS | 0.44GB |
| Nape-0.IQ3_S.gguf | IQ3_S | 0.47GB |
| Nape-0.Q3_K_S.gguf | Q3_K_S | 0.47GB |
| Nape-0.IQ3_M.gguf | IQ3_M | 0.48GB |
| Nape-0.Q3_K.gguf | Q3_K | 0.51GB |
| Nape-0.Q3_K_M.gguf | Q3_K_M | 0.51GB |
| Nape-0.Q3_K_L.gguf | Q3_K_L | 0.55GB |
| Nape-0.IQ4_XS.gguf | IQ4_XS | 0.57GB |
| Nape-0.Q4_0.gguf | Q4_0 | 0.59GB |
| Nape-0.IQ4_NL.gguf | IQ4_NL | 0.6GB |
| Nape-0.Q4_K_S.gguf | Q4_K_S | 0.6GB |
| Nape-0.Q4_K.gguf | Q4_K | 0.62GB |
| Nape-0.Q4_K_M.gguf | Q4_K_M | 0.62GB |
| Nape-0.Q4_1.gguf | Q4_1 | 0.65GB |
| Nape-0.Q5_0.gguf | Q5_0 | 0.71GB |
| Nape-0.Q5_K_S.gguf | Q5_K_S | 0.71GB |
| Nape-0.Q5_K.gguf | Q5_K | 0.73GB |
| Nape-0.Q5_K_M.gguf | Q5_K_M | 0.73GB |
| Nape-0.Q5_1.gguf | Q5_1 | 0.77GB |
| Nape-0.Q6_K.gguf | Q6_K | 0.84GB |
| Nape-0.Q8_0.gguf | Q8_0 | 1.09GB |
Original model description:
language:
- en license: mit
Nape-0
Nape series are small models that tries to exihibit much capabilities. The model is still in training process. This is very early preview.
You can load it as follows:
from transformers import LlamaForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("nnpy/Nape-0")
model = LlamaForCausalLM.from_pretrained("nnpy/Nape-0")
Training
It took 1 days to train 3 epochs on 4x A6000s using native deepspeed.
assistant role: You are Semica, a helpful AI assistant.
user: {prompt}
assistant:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 30.93 |
| ARC (25-shot) | 32.68 |
| HellaSwag (10-shot) | 58.68 |
| MMLU (5-shot) | 24.88 |
| TruthfulQA (0-shot) | 38.99 |
| Winogrande (5-shot) | 57.3 |
| GSM8K (5-shot) | 0.08 |
| DROP (3-shot) | 3.89 |
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024