There have been multiple accounts created with the sole purpose of posting advertisement posts or replies containing unsolicited advertising.

Accounts which solely post advertisements, or persistently post them may be terminated.

BaroqueInMind , (edited )

I’m looking at the HuggingFace leader boards and Gemma isn’t even top 10. How does it stack up against Llama3 or Mistral-Open-Orca?

simple OP ,

It’s currently number 11 in the LMSys chatbot leaderboard. It’s sitting above Llama 3 and Claude 3 Sonnet.

ExtravagantEnzyme ,

Just to be clear, Gemma is only partially open sourced in select area’s of the code.

https://lemm.ee/pictrs/image/35b4c57f-41b8-46db-af97-dc55515a3f35.png

eager_eagle ,
@eager_eagle@lemmy.world avatar

how are the weights partially open?

ExtravagantEnzyme ,

Only portions of the code are published while the rest is kept under wraps. Classic corporate America bs finding a loop hole to use a trendy term.

eager_eagle , (edited )
@eager_eagle@lemmy.world avatar

neural network weights are just files, collections of numbers forming matrices; how is a partially open collection of weights of any use

the weights are open


<span style="color:#323232;">$ docker exec -it ollama ollama show gemma:7b
</span><span style="color:#323232;">  Model                              
</span><span style="color:#323232;">  	arch            	gemma	             
</span><span style="color:#323232;">  	parameters      	9B   	             
</span><span style="color:#323232;">  	quantization    	Q4_0 	             
</span><span style="color:#323232;">  	context length  	8192 	             
</span><span style="color:#323232;">  	embedding length	3072 	             
</span><span style="color:#323232;">  	                                  
</span><span style="color:#323232;">  Parameters                         
</span><span style="color:#323232;">  	stop            	"<start_of_turn>"	 
</span><span style="color:#323232;">  	stop            	"<end_of_turn>"  	 
</span><span style="color:#323232;">  	penalize_newline	false            	 
</span><span style="color:#323232;">  	repeat_penalty  	1                	 
</span><span style="color:#323232;">  	                                  
</span><span style="color:#323232;">  License                            
</span><span style="color:#323232;">  	Gemma Terms of Use              	  
</span><span style="color:#323232;">  	Last modified: February 21, 2024	
</span>
jacksilver ,

Since there is a user acceptance policy that restricts what you can do with the model that might be considered “partially” open.

Yeah you can see the weights, but it seems you are limited on what you can do with the weights. How we’ve gotten to the point you can protect these random numbers that I’ve shared with you through a UA is beyond me.

eager_eagle ,
@eager_eagle@lemmy.world avatar

the same happens with BloomZ, and that is listed as open

jacksilver ,

Wasn’t aware of that, I was just taking a guess.

That being said I wouldn’t consider either open given those restrictions.

passepartout ,
@passepartout@feddit.org avatar

It’s already on Ollama. Exciting times!

  • All
  • Subscribed
  • Moderated
  • Favorites
  • •
  • [email protected]
  • random
  • lifeLocal
  • goranko
  • All magazines
    •