MikiV
/

LLMC_8bits_32blocksize_Qwen3-0.6B

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions Community

LLMC_8bits_32blocksize_Qwen3-0.6B / recipe.yaml

MikiV's picture

Upload Qwen3ForCausalLM

ff4dbd3 verified about 2 months ago

history blame contribute delete

141 Bytes

	default_stage:
	default_modifiers:
	GPTQModifier:
	block_size: 32
	scheme: W8A16
	targets: Linear
	ignore: [lm_head]