Updating model files
Browse files
README.md
CHANGED
|
@@ -4,6 +4,17 @@ datasets:
|
|
| 4 |
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
|
| 5 |
inference: false
|
| 6 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
# WizardLM - uncensored: An Instruction-following LLM Using Evol-Instruct
|
| 9 |
|
|
@@ -53,7 +64,18 @@ It was created without the `--act-order` parameter. It may have slightly lower i
|
|
| 53 |
```
|
| 54 |
python llama.py models/ehartford_WizardLM-7B-Uncensored c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors /workspace/eric-gptq/WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors
|
| 55 |
```
|
| 56 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
# Eric's original model card
|
| 58 |
|
| 59 |
This is WizardLM trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
|
|
@@ -66,4 +88,4 @@ Overview of Evol-Instruct
|
|
| 66 |
Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs.
|
| 67 |
|
| 68 |
|
| 69 |
-
|
|
|
|
| 4 |
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
|
| 5 |
inference: false
|
| 6 |
---
|
| 7 |
+
<div style="width: 100%;">
|
| 8 |
+
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 9 |
+
</div>
|
| 10 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
| 11 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
| 12 |
+
<p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
|
| 13 |
+
</div>
|
| 14 |
+
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
| 15 |
+
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? Patreon coming soon!</a></p>
|
| 16 |
+
</div>
|
| 17 |
+
</div>
|
| 18 |
|
| 19 |
# WizardLM - uncensored: An Instruction-following LLM Using Evol-Instruct
|
| 20 |
|
|
|
|
| 64 |
```
|
| 65 |
python llama.py models/ehartford_WizardLM-7B-Uncensored c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors /workspace/eric-gptq/WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors
|
| 66 |
```
|
| 67 |
+
|
| 68 |
+
## Want to support my work?
|
| 69 |
+
|
| 70 |
+
I've had a lot of people ask if they can contribute. I love providing models and helping people, but it is starting to rack up pretty big cloud computing bills.
|
| 71 |
+
|
| 72 |
+
So if you're able and willing to contribute, it'd be most gratefully received and will help me to keep providing models, and work on various AI projects.
|
| 73 |
+
|
| 74 |
+
Donaters will get priority support on any and all AI/LLM/model questions, and I'll gladly quantise any model you'd like to try.
|
| 75 |
+
|
| 76 |
+
* Patreon: coming soon! (just awaiting approval)
|
| 77 |
+
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
| 78 |
+
* Discord: https://discord.gg/UBgz4VXf
|
| 79 |
# Eric's original model card
|
| 80 |
|
| 81 |
This is WizardLM trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
|
|
|
|
| 88 |
Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs.
|
| 89 |
|
| 90 |
|
| 91 |
+
|