Hugging Face's logo
Brando Miranda's picture
36 2 28

Brando Miranda

brando
muhtasham's profile picture roseking's profile picture Mr-aio's profile picture
·
https://brando90.github.io/brandomiranda/

AI & ML interests

soccer, music, dance, reading

Organizations

Stanford AI's profile picture Stanford CRFM's profile picture Data Centric Machine Learning for Math's profile picture MAFmaticians's profile picture byndscl's profile picture The Ultimate Data Centric Alliance's profile picture The AI Alliance for Solving Mathematics for All (AI4M)'s profile picture

brando's activity

New activity in internlm/internlm2_5-1_8b 13 days ago

internlm-2.5 1.8B Matm model available?
#3 opened 13 days ago by brando
New activity in deepseek-ai/deepseek-math-7b-instruct 17 days ago

If I want the model to output something in a specific format, which format do you recommend?
#3 opened 17 days ago by brando
New activity in Iddah/llama3-8B-informalization 27 days ago

what base model was used? base or instruct?

1
#1 opened 27 days ago by brando
New activity in deepseek-ai/DeepSeek-Prover-V1.5-RL about 1 month ago

demo with vllm?

1
#4 opened about 1 month ago by brando
New activity in internlm/internlm2_5-1_8b about 1 month ago

recommended max length?

1
#2 opened about 1 month ago by brando

vllm support?
#1 opened about 1 month ago by brando
New activity in openai-community/gpt2-xl about 1 month ago

training gpt2 xl from stratch?

2
#12 opened about 1 month ago by brando
New activity in brando/Coq-Gym-Data-Set about 1 month ago

Add data structure to README.md
#7 opened about 1 month ago by jizej

upload lemma definitions
#6 opened about 1 month ago by jizej

Upload dataset

1
#5 opened 4 months ago by jizej
New activity in Qwen/Qwen2-1.5B about 1 month ago

recommended context length for SFT?
#6 opened about 1 month ago by brando
New activity in internlm/internlm2-1_8b about 1 month ago

recommended context length for SFT?
#6 opened about 1 month ago by brando
New activity in l3lab/ntp-mathlib-instruct-context 4 months ago

How is the [STATE]...[/STATE] supposed to be filled by training, any code for it? and similar things [TAC]...[/TAC] etc?
#2 opened 4 months ago by brando
New activity in l3lab/ntp-mathlib-instruct-st 4 months ago

How is the [STATE]...[/STATE] supposed to be filled by training, any code for it?
#1 opened 4 months ago by brando
New activity in EleutherAI/proof-pile-2 4 months ago

How does one load a data set using the math-pile2 and load specific languages from the algebraic stack?
#12 opened 4 months ago by brando

Dataset Viewer issue: ConfigNamesError
#11 opened 4 months ago by brando
New activity in tasksource/leandojo 4 months ago

is this lean4 or lean3 ?
#1 opened 4 months ago by brando
New activity in pixparse/pdfa-eng-wds 5 months ago

Where do I see the list of textbooks about mathematics?

1
#2 opened 5 months ago by brando
New activity in math-eval/TAL-SCQ5K 6 months ago

what is the website for tal?
#1 opened 6 months ago by brando
New activity in UDACA/AF 7 months ago

error no card
#3 opened 7 months ago by brando
New activity in google/gemma-7b 7 months ago

What is the context size for Gemma? I get error when asking for it in the config file e.g., AttributeError("'GemmaConfig' object has no attribute 'context_length'")

1
#63 opened 7 months ago by brando
New activity in google/gemma-2b 7 months ago

What is the context size for Gemma? I get error when asking for it in the config file e.g., AttributeError("'GemmaConfig' object has no attribute 'context_length'")

3
#32 opened 7 months ago by brando
New activity in UDACA/AF-with-metaData 7 months ago

we need to improve this with more details of data e.g., is this isabelle what datasets where merged etc?
#1 opened 7 months ago by brando
New activity in UDACA/AF 7 months ago

we need to improve this with more details of data e.g., is this isabelle what datasets where merged etc?
#2 opened 7 months ago by brando
New activity in brando/Coq-Gym-Data-Set 10 months ago

Upload dataset
#2 opened 10 months ago by jizej

test commit
#1 opened 10 months ago by jizej
New activity in morph-labs/morph-prover-v0-7b 11 months ago

request link to blog in model card

1
#3 opened 11 months ago by brando
New activity in kittn/mistral-7B-v0.1-hf 11 months ago

If I trained a model on mistral already, do I need to start from scratch due to difficulties of fine-tuning?

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

If I trained a model on mistral already, do I need to start from scratch due to difficulties of fine-tuning?

2
#62 opened 11 months ago by brando
New activity in open-web-math/open-web-math 11 months ago

val/test sets?

1
#3 opened 11 months ago by brando
New activity in togethercomputer/RedPajama-Data-1T about 1 year ago

Q: Why does RePajama exist? what problem are you solving?

1
#25 opened about 1 year ago by brando
commented 2 papers about 1 year ago
New activity in Mikael110/llama-2-70b-guanaco-qlora about 1 year ago

where is the code to actually fine tune with qlora?

1
#4 opened about 1 year ago by brando