File size: 2,754 Bytes
43b6fa7 57f0eee 43b6fa7 57f0eee 43b6fa7 57f0eee 43b6fa7 57f0eee f12e4a9 43b6fa7 57f0eee f12e4a9 57f0eee f12e4a9 57f0eee 101fcdd 57f0eee d9c1cc1 57f0eee 1010d28 57f0eee f9870c4 57f0eee d9c1cc1 f12e4a9 57f0eee 1010d28 57f0eee d9c1cc1 57f0eee 1010d28 57f0eee f42d00c d9c1cc1 f42d00c 57f0eee d9c1cc1 57f0eee 225c8ec f42d00c 225c8ec f42d00c 225c8ec f42d00c 225c8ec f42d00c 225c8ec f42d00c 225c8ec f42d00c 225c8ec f42d00c 225c8ec f42d00c 225c8ec f42d00c 225c8ec 57f0eee |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
---
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
---
# Model Card for Model ID
Introducing Pixie Zehir Nano.
Excelling in writing.
A fine tune of Llama 3.2 3B on HQ DATA™ from Pixie Zehir.
## Model Details
- **Developed by:** [Maani x BLNKBLK]
- **Language(s) (NLP):** [English]
- **License:** [Apache 2.0]
- **Finetuned from model :** [meta-llama/Llama-3.2-3B-Instruct]
## Agreements
Model is created for research purposes.
## Usage
```python
!pip install -qqq transformers
import torch
from transformers import pipeline
pipe = pipeline(
"text-generation",
model="Maani/PXZNNO",
torch_dtype=torch.bfloat16,
device_map="auto",
)
prompt = "Write a haiku."
messages = [
{"role": "user", "content": prompt},
]
prompt = pipe.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
res = pipe(
prompt,
max_new_tokens=4096,
temperature=0.8,
top_p=0.95,
top_k=20,
min_p=0.1,
do_sample=True,
)
print(res[0]["generated_text"])
```
```markdown
#sample of output
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Enable deep thinking subroutine.<|eot_id|><|start_header_id|>user<|end_header_id|>
Write a haiku.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
<think>
Okay, I need to write a haiku. Let me remember the structure. A haiku is a traditional Japanese poem with three lines. The syllable count is 5-7-5. The first line has 5 syllables, the second 7, and the third 5.
Hmm, what's a common haiku theme? Nature is often popular. Maybe something about seasons. Let me think of a season. Autumn? Leaves falling, that's a classic image.
First line: "Falling leaves dance" – that's 5 syllables. Leaves, falling, dance. Nice and simple.
Second line: "Whispers of autumn's sigh" – that's 7 syllables. Whispers, autumn's, sigh. It captures the gentle sound of falling leaves.
Third line: "Time's fleeting breath" – 5 syllables. Time's fleeting, breath. It's a metaphor for the passage of time.
Does that work? Let me check the syllable count again. Yes, 5-7-5. The imagery is cohesive, and it evokes a sense of time passing and the beauty of autumn. I think this works. Let me see if there's a better option, but I think this one is solid.
</think>
Falling leaves dance
Whispers of autumn's sigh
Time's fleeting breath
```
Thanks to mradermacher, You can find the GGUF quantized versions of earlier 1.8B Zehir nano at: mradermacher/PixieZehirNano-GGUF |