Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
tags:
|
4 |
- text-generation-inference
|
5 |
- transformers
|
@@ -15,8 +15,50 @@ language:
|
|
15 |
|
16 |
- **Developed by:** alphaaico
|
17 |
- **License:** apache-2.0
|
18 |
-
- **Finetuned from model :**
|
19 |
|
20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: llama-3.2-3b-instruct-bnb-4bit
|
3 |
tags:
|
4 |
- text-generation-inference
|
5 |
- transformers
|
|
|
15 |
|
16 |
- **Developed by:** alphaaico
|
17 |
- **License:** apache-2.0
|
18 |
+
- **Finetuned from model :** llama-3.2-3b-instruct-bnb-4bit
|
19 |
|
20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
+
AlphaAI-Chatty-INT1
|
23 |
+
|
24 |
+
Overview
|
25 |
+
|
26 |
+
AlphaAI-Chatty-INT1 is a fine-tuned LLaMA 3B Small model optimized for chatty and engaging conversations. This model has been trained on a proprietary conversational dataset, making it well-suited for local deployments that require a natural, interactive dialogue experience.
|
27 |
+
|
28 |
+
The model is available in GGUF format and has been quantized to different levels to support various hardware configurations.
|
29 |
+
|
30 |
+
Model Details
|
31 |
+
|
32 |
+
Base Model: LLaMA 3B Small
|
33 |
+
|
34 |
+
Fine-tuned By: Alpha AI
|
35 |
+
|
36 |
+
Training Framework: Unsloth
|
37 |
+
|
38 |
+
Quantization Levels Available:
|
39 |
+
-q4_k_m
|
40 |
+
-q5_k_m
|
41 |
+
-q8_0
|
42 |
+
-16-bit (full precision) https://huggingface.co/alphaaico/AlphaAI-Chatty-INT1-16bit
|
43 |
+
|
44 |
+
Format: GGUF (Optimized for local deployments)
|
45 |
+
|
46 |
+
Use Cases:
|
47 |
+
-Conversational AI – Ideal for chatbots, virtual assistants, and customer support.
|
48 |
+
-Local AI Deployments – Runs efficiently on local machines without requiring cloud-based inference.
|
49 |
+
-Research & Experimentation – Suitable for studying conversational AI and fine-tuning on domain-specific datasets.
|
50 |
+
|
51 |
+
Model Performance
|
52 |
+
The model has been optimized for chat-style interactions, ensuring:
|
53 |
+
-Engaging and context-aware responses
|
54 |
+
-Efficient performance on consumer hardware
|
55 |
+
-Balanced coherence and creativity in conversations
|
56 |
+
|
57 |
+
Limitations & Biases
|
58 |
+
This model, like any AI system, may have biases from the training data. It is recommended to use it responsibly and fine-tune further if needed for specific applications.
|
59 |
+
|
60 |
+
License
|
61 |
+
This model is released under a permissible license. Please check the Hugging Face repository for more details.
|
62 |
+
|
63 |
+
Acknowledgments
|
64 |
+
Special thanks to the Unsloth team for providing an optimized training pipeline for LLaMA models.
|