Hugging Face's logo
Sung Kim's picture
63 5 97

Sung Kim

hunkim
carpedkm's profile picture Yescia's profile picture mondalsurojit's profile picture
·
https://upstage.ai

AI & ML interests

Making AI Beneficial

Articles

Organizations

upstage's profile picture UpstageShareSpace's profile picture Social Post Explorers's profile picture

hunkim's activity

New activity in upstage/solar-pro-preview-instruct about 19 hours ago

There really seems to be some problem with the tokenizer or the ggufs

6
#12 opened 1 day ago by Smorty100
New activity in upstage/solar-pro-preview-instruct 1 day ago

Tested with GGUF Quantization and not receiving expected output

4
#11 opened 4 days ago by ReXommendation
New activity in princeton-nlp/gemma-2-9b-it-SimPO 2 days ago

Solar-Pro-SImPo
#2 opened 2 days ago by hunkim
New activity in upstage/solar-pro-preview-instruct 5 days ago

Is there any way to use multi gpu?

2
#5 opened 8 days ago by lee1111

Low Context Lenght.

2
#8 opened 7 days ago by avneetsingh
New activity in upstage/solar-pro-preview-instruct 8 days ago

November release

2
#3 opened 8 days ago by joujiboi

GGUF or Ollama?

1
#2 opened 8 days ago by windkkk
New activity in upstage/solar-pro-preview-instruct 9 days ago

Appreciate the model drop!

3
#1 opened 9 days ago by Nitral-AI
New activity in upstage/SOLAR-10.7B-Instruct-v1.0 6 months ago

GPU setting value

1
#31 opened 7 months ago by WRBEAR

Adding Evaluation Results
#30 opened 7 months ago by leaderboard-pr-bot

Please release a 16k version

2
#27 opened 7 months ago by Hoioi

Is this the model used in "https://poe.com/Solar-Mini"?

1
#25 opened 8 months ago by oaha

Finetuning upstage/SOLAR-10.7B-Instruct-v1.0

2
#24 opened 8 months ago by bertdirt

How to load with Langchain using Ctransformers?

1
#20 opened 9 months ago by ianuvrat

miss
#21 opened 9 months ago by 3838seungsheon

Create app.py
#17 opened 9 months ago by charanhu

11212
#22 opened 9 months ago by 3838seungsheon

How many A100-days took for training this model?

1
#29 opened 7 months ago by drun

[AUTOMATED] Model Memory Requirements
#28 opened 7 months ago by model-sizer-bot

Adding Evaluation Results
#33 opened 6 months ago by leaderboard-pr-bot

Adding Evaluation Results
#34 opened 6 months ago by playdigit

Adding Evaluation Results
#35 opened 6 months ago by playdigit

korean support

1
#36 opened 6 months ago by amphora
New activity in upstage/SOLAR-10.7B-Instruct-v1.0 7 months ago

hyperparameters
#19 opened 9 months ago by ehartford

How to fine tune upstage merge models?

1
#26 opened 7 months ago by wizmak
commented a paper 8 months ago
New activity in upstage/SOLAR-10.7B-v1.0 9 months ago

Data for Continued Pre-Training

6
#8 opened 9 months ago by pszemraj
New activity in upstage/SOLAR-10.7B-Instruct-v1.0 9 months ago

I feel that this 11B model is smarter and hallucinates less than other leaders

20
#9 opened 9 months ago by agershun
New activity in upstage/SOLAR-10.7B-v1.0 9 months ago

chat format

1
#7 opened 9 months ago by xavier7778

llama2 weights used?

2
#1 opened 9 months ago by KnutJaegersberg

I couldn't do a full fine-tune on Axo

1
#6 opened 9 months ago by migtissera
New activity in upstage/SOLAR-10.7B-Instruct-v1.0 9 months ago

Change licence type to commercial friendly

1
#16 opened 9 months ago by rjmehta

Do Korean dataset used when Finetune?

1
#15 opened 9 months ago by maywell

Expanding the window size

1
#12 opened 9 months ago by agershun

"Upstage" or "upstage"?

2
#14 opened 9 months ago by agershun

Depth Up-Scaling

6
#7 opened 9 months ago by mrfakename
New activity in maywell/PiVoT-MoE 9 months ago

Great work on MoE!

4
#1 opened 9 months ago by killawhale2
New activity in upstage/SOLAR-10.7B-v1.0 9 months ago

Training code

3
#2 opened 9 months ago by kristaller486

can you introduce the Depth Up-Scaling

1
#4 opened 9 months ago by zyh3826

Is this model multilingual?

1
#5 opened 9 months ago by seonglae
New activity in upstage/SOLAR-10.7B-Instruct-v1.0 9 months ago

RuntimeError: cutlassF: no kernel found to launch!

2
#5 opened 9 months ago by Manmax31
New activity in upstage/open-ko-llm-leaderboard 11 months ago

Update on the Evaluation Method for Ko Common Gen V2

2
#11 opened 11 months ago by Limerobot
New activity in mistralai/Mistral-7B-v0.1 11 months ago

Open-Ko-LLM Leaderboard - Thanks for Uploading!
#55 opened 11 months ago by hunkim
New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

Update Model Name: Llama-2-70b-instruct-v2 to SOLAR-0-70b-16bit in the Leaderboard

7
#280 opened about 1 year ago by hunkim
New activity in upstage/SOLAR-0-70b-16bit about 1 year ago

Prompt for multi round chat

1
#11 opened about 1 year ago by ancv

Introducing Our Model API: Now Available at togather.ai

1
#12 opened about 1 year ago by hunkim
New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

[FLAG] deepnight-research/llama-2-70B-inst: Identical models on leaderboard

15
#207 opened about 1 year ago by jaspercatapang
New activity in upstage/SOLAR-0-70b-16bit about 1 year ago

Someone possibly just reuploaded this model and renamed it

3
#6 opened about 1 year ago by llama-anon

License

2
#9 opened about 1 year ago by Andreas222

Dataset

3
#5 opened about 1 year ago by Komposter43

70b fine tuned coding model?

5
#1 opened about 1 year ago by rombodawg

Difference compared to the v1 model

1
#4 opened about 1 year ago by howard50b

How long did the fine tuning process take ?

1
#7 opened about 1 year ago by deleted

Call w/ LiteLLM

2
#8 opened about 1 year ago by krrish-litellm
New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

Llama-based model evaluation failure again

4
#156 opened about 1 year ago by deleted
New activity in upstage/SOLAR-0-70b-16bit about 1 year ago

License and commercial use

1
#3 opened about 1 year ago by Bauzer

Does it say "as an AI"?

5
#2 opened about 1 year ago by jackboot
New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

Our submitted model is still not visible on the leaderboard

10
#129 opened about 1 year ago by Limerobot

Benchmarks for GPT-3.5 & GPT-4 for comparison

10
#145 opened about 1 year ago by mantrakp
New activity in TheBloke/llama-2-70b-Guanaco-QLoRA-fp16 about 1 year ago

Amazing work
#3 opened about 1 year ago by hunkim