Pablo Montalvo PRO

Molbap's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in mistralai/Mistral-Small-Instruct-2409 10 months ago

Update config.json with correct max_position_embeddings (32k to 131k)

1

#14 opened 10 months ago by

Molbap

Upload MistralForCausalLM

#1 opened 10 months ago by

Molbap

New activity in pixparse/pdfa-eng-wds 10 months ago

heuristic to obtain lines from individual text

3

#4 opened 10 months ago by

VictorSanh

New activity in mistralai/Mamba-Codestral-7B-v0.1 11 months ago

When will config.json be available?

👍 1

8

#10 opened 11 months ago by

DevJain7

Upload HF format weights for Mamba2ForCausalLM

❤️ 2

#9 opened 11 months ago by

Molbap

New activity in mistralai/Mathstral-7B-v0.1 12 months ago

Add chat_template to tokenizer config

3

#6 opened 12 months ago by

Molbap

New activity in mistralai/Mamba-Codestral-7B-v0.1 12 months ago

Missing config.json

➕ 2

5

#6 opened 12 months ago by

wxl2001

Support state-spaces/mamba?

👍 1

3

#7 opened 12 months ago by

hackeys

New activity in mistralai/Mathstral-7B-v0.1 12 months ago

Change main weights precision to bfloat16

1

#5 opened 12 months ago by

Molbap

New activity in google/paligemma-3b-mix-448 about 1 year ago

Torch detection bbox differs from JAX models?

15

#6 opened about 1 year ago by

tlpss

New activity in pixparse/pdfa-eng-wds about 1 year ago

How were the PDF annotations generated?

1

#3 opened about 1 year ago by

nfliu

Where do I see the list of textbooks about mathematics?

1

#2 opened about 1 year ago by

brando

New activity in pixparse/idl-wds over 1 year ago

ValueError raised upon loading dataset

2

#2 opened over 1 year ago by

rufimelo

New activity in adept/fuyu-8b over 1 year ago

Are there special tokens that are ignored during loss computation?

9

#62 opened over 1 year ago by

Nyandwi

Tips on resolving this typing.Optional error seemingly related to PIL.Image?

3

#56 opened over 1 year ago by

justinwickett

demo of PDF vqa

1

#55 opened over 1 year ago by

verigle

New activity in google/pix2struct-base over 1 year ago

How to use this model to extract html structure from image?

8

#7 opened over 1 year ago by

Alexziyu

New activity in adept/fuyu-8b over 1 year ago

fine-tuning using FSDP and non 80GB cards?

8

#43 opened over 1 year ago by

besiktas

For the vqav2 data set example "fish and carrot", why does the model output a sentence instead of a phrase?

8

#44 opened over 1 year ago by

changgeli

Colab

👍 1

1

#39 opened over 1 year ago by

nengelmann