Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- nvidia/Llama-3_3-Nemotron-Super-49B-v1
|
| 4 |
+
---
|
| 5 |
+
# Join our Discord! https://discord.gg/Nbv9pQ88Xb
|
| 6 |
+
## More than 5500 members of helpful, LLM enthusiasts! A hub for players and makers alike!
|
| 7 |
+
### We need testers!
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
Drummer proudly presents...
|
| 11 |
+
|
| 12 |
+
# Valkyrie 49B v1
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Description
|
| 17 |
+
|
| 18 |
+
> it swears unprompted 10/10 model
|
| 19 |
+
|
| 20 |
+
> ... characters work well, groups work well, scenarios also work really well so great model overall
|
| 21 |
+
|
| 22 |
+
> This is pretty exciting though. GLM-4 already had me on the verge of deleting all of my other 32b and lower models. I got to test this more but I think this model at Q3m is the death blow lol
|
| 23 |
+
|
| 24 |
+
> Smart Nemotron 49b learned how to roleplay
|
| 25 |
+
|
| 26 |
+
> Even without thinking it rock solid at 4qm.
|
| 27 |
+
|
| 28 |
+
> Without thinking is like 40-70b level. With thinking is 100+b level
|
| 29 |
+
|
| 30 |
+
> This model would have been AGI if it were named properly with a name like "Bob". Alas, it was not.
|
| 31 |
+
|
| 32 |
+
> I think this model is nice. It follows prompts very well. I didn't really note any major issues or repetition
|
| 33 |
+
|
| 34 |
+
> Yeah this is good. I think its clearly smart enough, close to the other L3.3 70b models. It follows directions and formatting very well. I asked it to create the intro message, my first response was formatted differently, and it immediately followed my format on the second message. I also have max tokens at 2k cause I like the model to finish it's thought. But I started trimming the models responses when I felt the last bit was unnecessary and it started replying closer to that length. It's pretty much uncensored.
|
| 35 |
+
|
| 36 |
+
## Usage
|
| 37 |
+
- Llama 3 Chat Template
|
| 38 |
+
- \<think\> capable upon prefill or `detailed thinking on` on top of the system prompt
|
| 39 |
+
|
| 40 |
+
## Links
|
| 41 |
+
- Original: https://huggingface.co/TheDrummer/Valkyrie-49B-v1
|
| 42 |
+
- GGUF: https://huggingface.co/TheDrummer/Valkyrie-49B-v1-GGUF
|
| 43 |
+
- iMatrix (recommended): https://huggingface.co/bartowski/TheDrummer_Valkyrie-49B-v1-GGUF
|
| 44 |
+
|
| 45 |
+
## Special Thanks
|
| 46 |
+
- Thank you to the testers at BeaverAI! You da MVP!
|
| 47 |
+
- Thank you to each and everyone who donated and subscribed in [Patreon](https://www.patreon.com/TheDrummer) and [Ko-Fi](https://ko-fi.com/thedrummer) to make our venture a little bit easier.
|
| 48 |
+
- [Subscribe to my Patreon!](https://www.patreon.com/TheDrummer)
|
| 49 |
+
|
| 50 |
+
`config-v1a`
|