Hugging Face's logo
Samuel Azran's picture
16 1 73

Samuel Azran

SamuelAzran
·

AI & ML interests

None yet

Organizations

None yet

SamuelAzran's activity

New activity in hebrew-llm-leaderboard/leaderboard 3 months ago

New Gemma 2 27B?

2
#3 opened 4 months ago by SamuelAzran
New activity in yam-peleg/Hebrew-Gemma-11B-Instruct 8 months ago

Was it train after the latest Huggingface Transformers Gemma fix? if not any update plans?
#4 opened 8 months ago by SamuelAzran
New activity in cloudyu/Mixtral_34Bx2_MoE_60B 10 months ago

Should not be called mixtral, the models made into the moe are yi based

9
#2 opened 10 months ago by teknium

How does the MoE work?

3
#5 opened 10 months ago by PacmanIncarnate
New activity in cloudyu/Mixtral_7Bx2_MoE 10 months ago

One or two models during inference?

3
#3 opened 10 months ago by Venkman42
New activity in upstage/SOLAR-10.7B-Instruct-v1.0 11 months ago

You know Mixtral, Llama 2 70b, GPT3.5... Are All Much Better

1
#13 opened 11 months ago by deleted
New activity in VAGOsolutions/SauerkrautLM-SOLAR-Instruct 11 months ago

Awesome- Could you help with pointers on doing same for Other languages(Swedish)?

3
#2 opened 11 months ago by Olofp

QLora or full fine-tuning?

1
#1 opened 11 months ago by SamuelAzran
New activity in NousResearch/Nous-Capybara-34B 12 months ago

Was system message used during training?

1
#8 opened 12 months ago by SamuelAzran
New activity in open-llm-leaderboard/open_llm_leaderboard 12 months ago

NEW! OpenLLMLeaderboard 2023 fall update

20
#356 opened 12 months ago by clefourrier
New activity in NousResearch/Nous-Capybara-34B 12 months ago

Did you do full model fine tuning (all layers) or only adapters?

1
#2 opened 12 months ago by SamuelAzran
New activity in 01-ai/Yi-34B 12 months ago

Can you release a chat version soon ?

11
#8 opened 12 months ago by dong0213
New activity in openchat/openchat_v2_w over 1 year ago

Great work, but why only 2048 context length?

1
#4 opened over 1 year ago by SamuelAzran
New activity in nomic-ai/gpt4all-mpt over 1 year ago

Would it work well with sequence length > 2048?

2
#1 opened over 1 year ago by SamuelAzran
New activity in TheBloke/alpaca-lora-65B-GGML over 1 year ago

Thank you very much!

10
#2 opened over 1 year ago by AiCreatornator
New activity in google/flan-ul2 over 1 year ago

Error running the example code

21
#6 opened over 1 year ago by will33am