uploaded readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Quantization made by Richard Erkhov.
|
| 2 |
+
|
| 3 |
+
[Github](https://github.com/RichardErkhov)
|
| 4 |
+
|
| 5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
| 6 |
+
|
| 7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
greesychat-turbo - GGUF
|
| 11 |
+
- Model creator: https://huggingface.co/OnlyCheeini/
|
| 12 |
+
- Original model: https://huggingface.co/OnlyCheeini/greesychat-turbo/
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
| Name | Quant method | Size |
|
| 16 |
+
| ---- | ---- | ---- |
|
| 17 |
+
| [greesychat-turbo.Q2_K.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q2_K.gguf) | Q2_K | 2.96GB |
|
| 18 |
+
| [greesychat-turbo.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
|
| 19 |
+
| [greesychat-turbo.IQ3_S.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.IQ3_S.gguf) | IQ3_S | 3.43GB |
|
| 20 |
+
| [greesychat-turbo.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
|
| 21 |
+
| [greesychat-turbo.IQ3_M.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.IQ3_M.gguf) | IQ3_M | 3.52GB |
|
| 22 |
+
| [greesychat-turbo.Q3_K.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q3_K.gguf) | Q3_K | 3.74GB |
|
| 23 |
+
| [greesychat-turbo.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
|
| 24 |
+
| [greesychat-turbo.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
|
| 25 |
+
| [greesychat-turbo.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
|
| 26 |
+
| [greesychat-turbo.Q4_0.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q4_0.gguf) | Q4_0 | 4.34GB |
|
| 27 |
+
| [greesychat-turbo.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
|
| 28 |
+
| [greesychat-turbo.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
|
| 29 |
+
| [greesychat-turbo.Q4_K.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q4_K.gguf) | Q4_K | 4.58GB |
|
| 30 |
+
| [greesychat-turbo.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
|
| 31 |
+
| [greesychat-turbo.Q4_1.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q4_1.gguf) | Q4_1 | 4.78GB |
|
| 32 |
+
| [greesychat-turbo.Q5_0.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q5_0.gguf) | Q5_0 | 5.21GB |
|
| 33 |
+
| [greesychat-turbo.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
|
| 34 |
+
| [greesychat-turbo.Q5_K.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q5_K.gguf) | Q5_K | 5.34GB |
|
| 35 |
+
| [greesychat-turbo.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
|
| 36 |
+
| [greesychat-turbo.Q5_1.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q5_1.gguf) | Q5_1 | 5.65GB |
|
| 37 |
+
| [greesychat-turbo.Q6_K.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q6_K.gguf) | Q6_K | 6.14GB |
|
| 38 |
+
| [greesychat-turbo.Q8_0.gguf](https://huggingface.co/RichardErkhov/OnlyCheeini_-_greesychat-turbo-gguf/blob/main/greesychat-turbo.Q8_0.gguf) | Q8_0 | 7.95GB |
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
Original model description:
|
| 44 |
+
---
|
| 45 |
+
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
| 46 |
+
language:
|
| 47 |
+
- en
|
| 48 |
+
license: apache-2.0
|
| 49 |
+
tags:
|
| 50 |
+
- text-generation-inference
|
| 51 |
+
- transformers
|
| 52 |
+
- unsloth
|
| 53 |
+
- llama
|
| 54 |
+
- trl
|
| 55 |
+
- sft
|
| 56 |
+
datasets:
|
| 57 |
+
- OnlyCheeini/greesychat
|
| 58 |
+
---
|
| 59 |
+
|
| 60 |
+

|
| 61 |
+
|
| 62 |
+
# GreesyChat-Turbo AI Model
|
| 63 |
+
|
| 64 |
+
## Overview
|
| 65 |
+
|
| 66 |
+
GreesyChat-Turbo is an advanced AI model designed for robust text generation using the LLaMA 3 architecture. This model excels in providing high-quality responses for general conversation, mathematical queries, and more. It’s perfect for powering chatbots, virtual assistants, and any application requiring intelligent dialogue capabilities.
|
| 67 |
+
|
| 68 |
+
## Benchmark Results
|
| 69 |
+
|
| 70 |
+
| Metric | Value |
|
| 71 |
+
|--------------------|------------|
|
| 72 |
+
| **Perplexity** | 22.5 |
|
| 73 |
+
| **Generation Speed** | 75 ms per token |
|
| 74 |
+
| **Accuracy** | 70% |
|
| 75 |
+
| **Response Time** | 200 ms |
|
| 76 |
+
|
| 77 |
+
| Metric | GreesyChat-Turbo | Mixtral-8x7b | GPT-4 |
|
| 78 |
+
|---------------|------------------|---------------|-------------|
|
| 79 |
+
| **Code** | 79.2 | 75.6 | 83.6 |
|
| 80 |
+
| **MMLU** | 74.5 | 79.9 | 85.1 |
|
| 81 |
+
| **Gms8k** | 89.2 (5) | 88.7 | 94.2 |
|
| 82 |
+
|
| 83 |
+
## Contact
|
| 84 |
+
|
| 85 |
+
For support or inquiries, please contact: [mail@nicatdcw.dev](mailto:mail@nicatdcw.dev)
|
| 86 |
+
|
| 87 |
+
|