Update README.md
Browse files
README.md
CHANGED
@@ -1,39 +1,39 @@
|
|
1 |
---
|
2 |
license: gemma
|
3 |
---
|
4 |
-
# π Nidum Gemma-3-4B IT Uncensored
|
5 |
|
6 |
-
Welcome to Nidum's Gemma-3-4B IT Uncensored,
|
7 |
|
8 |
-
## β¨
|
9 |
|
10 |
-
- **
|
11 |
-
- **
|
12 |
-
- **
|
13 |
|
14 |
-
## π₯
|
15 |
|
16 |
-
| Quantization | Description
|
17 |
-
|
18 |
-
| **Q8_0**
|
19 |
-
| **Q6_K**
|
20 |
-
| **Q5_K_M**
|
21 |
-
| **Q3_K_M**
|
22 |
-
| **TQ2_0**
|
23 |
-
| **TQ1_0**
|
24 |
|
25 |
-
|
|
|
|
|
26 |
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
| **Educational Support** | Interactive lessons, open-ended Q&A |
|
32 |
-
| **Entertainment & Gaming** | Immersive storytelling, role-playing scenarios |
|
33 |
|
34 |
---
|
35 |
|
36 |
-
##
|
37 |
|
38 |
```python
|
39 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
@@ -44,16 +44,17 @@ model_name = "nidum/nidum-gemma-3-4b-it-uncensored"
|
|
44 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
45 |
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
|
46 |
|
47 |
-
prompt = "Tell me an imaginative story about
|
48 |
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
|
49 |
|
50 |
generated_ids = model.generate(input_ids, max_length=200)
|
51 |
output = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
|
|
|
52 |
print(output)
|
53 |
```
|
54 |
|
55 |
---
|
56 |
|
57 |
-
##
|
58 |
|
59 |
-
Experience
|
|
|
1 |
---
|
2 |
license: gemma
|
3 |
---
|
4 |
+
# π Nidum Gemma-3-4B IT Uncensored
|
5 |
|
6 |
+
Welcome to Nidum's Gemma-3-4B IT Uncensored, your gateway to an open and unrestricted AI experience. This powerful model enables users to explore and innovate without boundaries.
|
7 |
|
8 |
+
## β¨ Why Choose Nidum Gemma-3-4B IT Uncensored?
|
9 |
|
10 |
+
- **Unrestricted AI Interaction**: Freedom to discuss, explore, and innovate without content limitations.
|
11 |
+
- **Efficient and Versatile**: Optimized performance suitable for various hardware configurations.
|
12 |
+
- **Diverse Applications**: Perfect for creative projects, conversational AI, educational tools, and entertainment.
|
13 |
|
14 |
+
## π₯ Available Quantized Versions (GGUF)
|
15 |
|
16 |
+
| Quantization | Description | Bits per Weight | Download |
|
17 |
+
|--------------|-------------------------------------------|-----------------|---------------|
|
18 |
+
| **Q8_0** | Best accuracy and performance | 8-bit | [model-Q8_0.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-Q8_0.gguf) |
|
19 |
+
| **Q6_K** | Balance between speed and quality | 6-bit | [model-Q6_K.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-Q6_K.gguf) |
|
20 |
+
| **Q5_K_M** | Good accuracy with lower memory usage | 5-bit | [model-Q5_K_M.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-Q5_K_M.gguf) |
|
21 |
+
| **Q3_K_M** | Smaller footprint, good for limited resources | 3-bit | [model-Q3_K_M.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-Q3_K_M.gguf) |
|
22 |
+
| **TQ2_0** | Very fast inference, minimal memory usage | 2-bit | [model-TQ2_0.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-TQ2_0.gguf) |
|
23 |
+
| **TQ1_0** | Minimal memory usage, fastest inference | 2-bit | [model-TQ1_0.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-TQ1_0.gguf) |
|
24 |
|
25 |
+
---
|
26 |
+
|
27 |
+
## π Recommended Applications
|
28 |
|
29 |
+
- **Creative Writing & Arts**: Generate stories, scripts, poetry, and explore creative ideas.
|
30 |
+
- **Virtual Assistants**: Provide natural and unrestricted conversational experiences.
|
31 |
+
- **Educational Resources**: Facilitate engaging, interactive learning environments.
|
32 |
+
- **Entertainment & Gaming**: Create immersive narratives and interactive gameplay experiences.
|
|
|
|
|
33 |
|
34 |
---
|
35 |
|
36 |
+
## π Example Usage
|
37 |
|
38 |
```python
|
39 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
44 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
45 |
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
|
46 |
|
47 |
+
prompt = "Tell me an imaginative story about a hidden city."
|
48 |
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
|
49 |
|
50 |
generated_ids = model.generate(input_ids, max_length=200)
|
51 |
output = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
|
52 |
+
|
53 |
print(output)
|
54 |
```
|
55 |
|
56 |
---
|
57 |
|
58 |
+
## π Unlock Limitless Creativity
|
59 |
|
60 |
+
Experience the freedom to innovate and explore without boundaries using **Nidum Gemma-3-4B IT Uncensored**.
|