Pankaj Mathur
commited on
Commit
•
21ef508
1
Parent(s):
373e60f
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,31 @@ pipeline_tag: text-generation
|
|
| 13 |
|
| 14 |
A LLama2-7b model trained on Orca Style datasets.
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
### quantized versions
|
| 17 |
|
| 18 |
Big thanks to [@TheBloke](https://huggingface.co/TheBloke)
|
|
@@ -21,11 +46,13 @@ Big thanks to [@TheBloke](https://huggingface.co/TheBloke)
|
|
| 21 |
|
| 22 |
2) https://huggingface.co/TheBloke/orca_mini_v3_7B-GPTQ
|
| 23 |
|
|
|
|
| 24 |
|
| 25 |
#### license disclaimer:
|
| 26 |
|
| 27 |
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
|
| 28 |
|
|
|
|
| 29 |
|
| 30 |
## evaluation
|
| 31 |
|
|
@@ -43,8 +70,7 @@ Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](htt
|
|
| 43 |
|**Total Average**|-|**0.59865**||
|
| 44 |
|
| 45 |
|
| 46 |
-
|
| 47 |
-
|
| 48 |
|
| 49 |
## example esage
|
| 50 |
|
|
@@ -87,6 +113,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
|
|
| 87 |
|
| 88 |
```
|
| 89 |
|
|
|
|
| 90 |
|
| 91 |
#### limitations & biases:
|
| 92 |
|
|
@@ -97,6 +124,7 @@ Despite diligent efforts in refining the pretraining data, there remains a possi
|
|
| 97 |
Exercise caution and cross-check information when necessary.
|
| 98 |
|
| 99 |
|
|
|
|
| 100 |
|
| 101 |
### citiation:
|
| 102 |
|
|
|
|
| 13 |
|
| 14 |
A LLama2-7b model trained on Orca Style datasets.
|
| 15 |
|
| 16 |
+
<br>
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
<br>
|
| 21 |
+
|
| 22 |
+
🤔 How good is orca-mini-v3-7b? Do the evaluation results from HuggingFace Open LLM leaderboard translate to real-world use cases?
|
| 23 |
+
|
| 24 |
+
🔍 Now you can figure it out for yourself!
|
| 25 |
+
|
| 26 |
+
Introducing the orca-mini chatbot powered by the orca-mini-v3-7b model. Dive in and see how the open source 7b model stacks up in the world of massive language models. 🌍
|
| 27 |
+
|
| 28 |
+
⏰ Hurry up before I run out of GPU credits! 😉
|
| 29 |
+
|
| 30 |
+
Check it out here 👉
|
| 31 |
+
|
| 32 |
+
[https://huggingface.co/spaces/psmathur/psmathur-orca_mini_v3_7b](https://huggingface.co/spaces/psmathur/psmathur-orca_mini_v3_7b)
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
<br>
|
| 36 |
+
|
| 37 |
+
**P.S. I am actively seeking sponsorship and partnership opportunities. If you're interested, please connect with me at www.linkedin.com/in/pankajam.**
|
| 38 |
+
|
| 39 |
+
<br>
|
| 40 |
+
|
| 41 |
### quantized versions
|
| 42 |
|
| 43 |
Big thanks to [@TheBloke](https://huggingface.co/TheBloke)
|
|
|
|
| 46 |
|
| 47 |
2) https://huggingface.co/TheBloke/orca_mini_v3_7B-GPTQ
|
| 48 |
|
| 49 |
+
<br>
|
| 50 |
|
| 51 |
#### license disclaimer:
|
| 52 |
|
| 53 |
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
|
| 54 |
|
| 55 |
+
<br>
|
| 56 |
|
| 57 |
## evaluation
|
| 58 |
|
|
|
|
| 70 |
|**Total Average**|-|**0.59865**||
|
| 71 |
|
| 72 |
|
| 73 |
+
<br>
|
|
|
|
| 74 |
|
| 75 |
## example esage
|
| 76 |
|
|
|
|
| 113 |
|
| 114 |
```
|
| 115 |
|
| 116 |
+
<br>
|
| 117 |
|
| 118 |
#### limitations & biases:
|
| 119 |
|
|
|
|
| 124 |
Exercise caution and cross-check information when necessary.
|
| 125 |
|
| 126 |
|
| 127 |
+
<br>
|
| 128 |
|
| 129 |
### citiation:
|
| 130 |
|