Text-to-SQL Model
AI & ML interests
Benchmark, Code Generation, LLM
Recent Activity
View all activity
Open-source works to reproduce DeepSeek R1
-
perplexity-ai/r1-1776
Text Generation • 671B • Updated • 1.17k • 2.33k -
unsloth/r1-1776-GGUF
Text Generation • 671B • Updated • 397 • 103 -
unsloth/r1-1776-distill-llama-70b-unsloth-bnb-4bit
Text Generation • 73B • Updated • 9 • 2 -
open-r1/OpenR1-Qwen-7B
Text Generation • 8B • Updated • 55 • • 54
For Finetuning. GPU is needed for both quantization and inference.
-
onekq-ai/OpenCoder-8B-Instruct-bnb-4bit
Text Generation • 8B • Updated • 6 -
onekq-ai/OpenCoder-8B-Base-bnb-4bit
Text Generation • 8B • Updated • 8 -
onekq-ai/starcoder2-15b-bnb-4bit
Text Generation • 16B • Updated • 8 • 1 -
onekq-ai/starcoder2-7b-bnb-4bit
Text Generation • 7B • Updated • 14
Text-to-SQL model
For inference. CPU is enough for both quantization and inference.
-
QuantFactory/OpenCoder-8B-Instruct-GGUF
Text Generation • 8B • Updated • 261 • 6 -
QuantFactory/OpenCoder-8B-Base-GGUF
Text Generation • 8B • Updated • 464 • 3 -
bartowski/starcoder2-15b-instruct-GGUF
Text Generation • 16B • Updated • 1.46k • 5 -
QuantFactory/starcoder2-15b-GGUF
Text Generation • 16B • Updated • 163 • 2
Text-to-SQL Model
Text-to-SQL model
Open-source works to reproduce DeepSeek R1
-
perplexity-ai/r1-1776
Text Generation • 671B • Updated • 1.17k • 2.33k -
unsloth/r1-1776-GGUF
Text Generation • 671B • Updated • 397 • 103 -
unsloth/r1-1776-distill-llama-70b-unsloth-bnb-4bit
Text Generation • 73B • Updated • 9 • 2 -
open-r1/OpenR1-Qwen-7B
Text Generation • 8B • Updated • 55 • • 54
For inference. CPU is enough for both quantization and inference.
-
QuantFactory/OpenCoder-8B-Instruct-GGUF
Text Generation • 8B • Updated • 261 • 6 -
QuantFactory/OpenCoder-8B-Base-GGUF
Text Generation • 8B • Updated • 464 • 3 -
bartowski/starcoder2-15b-instruct-GGUF
Text Generation • 16B • Updated • 1.46k • 5 -
QuantFactory/starcoder2-15b-GGUF
Text Generation • 16B • Updated • 163 • 2
For Finetuning. GPU is needed for both quantization and inference.
-
onekq-ai/OpenCoder-8B-Instruct-bnb-4bit
Text Generation • 8B • Updated • 6 -
onekq-ai/OpenCoder-8B-Base-bnb-4bit
Text Generation • 8B • Updated • 8 -
onekq-ai/starcoder2-15b-bnb-4bit
Text Generation • 16B • Updated • 8 • 1 -
onekq-ai/starcoder2-7b-bnb-4bit
Text Generation • 7B • Updated • 14