daslab-testing/DeepSeek-R1-Distill-Qwen-1.5B-HRSTQ-4bit-128g
daslab-testing/QwQ-32B-HRSTQ-4bit-128g
daslab-testing/QwQ-32B-GPTQ-4b-128g-act_order-mse_scale
daslab-testing/DeepSeek-R1-GPTQ-4b-128g-experts
daslab-testing/Meta-Llama-3.1-8B-Instruct-GPTQ-4_8-bit
Updated
daslab-testing/QuEST-800M-BF16
Updated
daslab-testing/QuEST-800M-INT4
Updated
daslab-testing/QuEST-800M-INT4-SPARSE
Updated
daslab-testing/QuEST-800M-INT4-NOHAD
Updated
daslab-testing/four-eight-testing-50m
Updated
daslab-testing/hadamard-four-eight-testing-50m
Updated
daslab-testing/QuEST-800M-INT4-SPARSE-NOHAD
Updated
daslab-testing/four-eight-testing
Updated
daslab-testing/Llama-3.3-70B-Instruct-GPTQ-4bit
11B
•
Updated
•
2
daslab-testing/Llama-3.2-3B-OBQ-4b32g
3B
•
Updated
•
3
daslab-testing/Llama-3.2-1B-OBQ-4b128g
1B
•
Updated
•
2
daslab-testing/Llama-3.2-1B-OBQ-4b64g
1B
•
Updated
•
1
daslab-testing/Llama-3.2-3B-OBQ-4b64g
3B
•
Updated
•
2
daslab-testing/Llama-3.2-3B-OBQ-4b128g
3B
•
Updated
•
2
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipTrue_fineweb
2B
•
Updated
•
2
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb
2B
•
Updated
•
2
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipTrue_fineweb
2B
•
Updated
•
2
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipFalse_fineweb
2B
•
Updated
•
2
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb
12B
•
Updated
•
2
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipTrue_fineweb
12B
•
Updated
•
2
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipTrue_fineweb
12B
•
Updated
•
2
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipFalse_fineweb
Updated
daslab-testing/Llama-3.1-Nemotron-70B-Instruct-HF-gptq4-128-True-seed1_mse1_staticTrue_clipTrue_fineweb
11B
•
Updated
•
3
daslab-testing/Llama-3.1-Nemotron-70B-Instruct-HF-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb
Updated
daslab-testing/Llama-3.1-Nemotron-70B-Instruct-HF-gptq4-128-True-seed1_mse1_staticFalse_clipFalse_fineweb
11B
•
Updated
•
3