Rishabh

rishdotblog's activity

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

New activity in defog/llama-3-sqlcoder-8b about 1 year ago

Remove sampling and set temperature to zero.

1

#19 opened about 1 year ago by

trifltt

New activity in mlx-community/defog-llama-3-sqlcoder-8b about 1 year ago

Replace the `eos_token` with `<eot_id>`, to prevent model from going on unnecessarily long

1

#2 opened about 1 year ago by

rishdotblog

New activity in defog/sqlcoder-70b-alpha over 1 year ago

Expected inputs Azure ML Studio

2

#12 opened over 1 year ago by

spleeneo

New activity in defog/sqlcoder-7b-2 over 1 year ago

SQL Query always points to PostgreSQL, even if strongly prompted not to do

1

#18 opened over 1 year ago by

yashsoni369

context length higher than 100K

2

#13 opened over 1 year ago by

Iamexperimenting

Fine-tuning with SQL coder

👍 1

6

#14 opened over 1 year ago by

Iamexperimenting

为什么生成的like查询语句总是包含ILIKE

4

#10 opened over 1 year ago by

caojunjiang

How did this 7b model get such high accuracy

1

#12 opened over 1 year ago by

zhangye123

how to use sqlcoder-7b-q5_k_m.gguf in llama.cpp

1

#9 opened over 1 year ago by

caojunjiang

Supplementary data

1

#8 opened over 1 year ago by

eddyjoey

Amazon Sagemaker endpoint implementation doesn't work accurately.

2

#7 opened over 1 year ago by

singhmanas1

Prompt in the model card is slightly different from the one provided in Github

1

#2 opened over 1 year ago by

mus-shd

What SQL dialects are supported?

1

#3 opened over 1 year ago by

moltar

Is using the database schema the best way to describe prime the model?

1

#4 opened over 1 year ago by

moltar

Dates

👍 1

7

#5 opened over 1 year ago by

pcapazzi

Context-Window

3

#6 opened over 1 year ago by

HuggySSO

New activity in defog/sqlcoder-70b-alpha over 1 year ago

Not able to run the with 4bit quantization on RTX4090 (24GB vRAM) local GPU

1

#6 opened over 1 year ago by

miteshgarg

Does not work

10

#2 opened over 1 year ago by

buddyroo30

Excuse me, is the current model a chat model?

1

#5 opened over 1 year ago by

obtion

Can't host with vLLM - "LlamaModel" architecture is not supported.

2

#4 opened over 1 year ago by

huggingfacemotnt