hanxiao commited on
Commit
425faa5
·
verified ·
1 Parent(s): e5dae66

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +23 -22
README.md CHANGED
@@ -160,27 +160,28 @@ system_info: n_threads = 4 (n_threads_batch = 4) / 8 | CUDA : ARCHS = 890 | USE_
160
  | F16 | 5.75 GiB | 16.00 | 1050 | 1083 | +0% | +0% |
161
 
162
  #### Table 2: NDCG@5
163
- | Quantization Type | NanoHotpotQA | NanoFiQA2018 | Δ to v3 (HotpotQA) | Δ to v4 (HotpotQA) | Δ to v3 (FiQA2018) | Δ to v4 (FiQA2018) |
164
- |------------------|--------------|--------------|-------------------|-------------------|-------------------|-------------------|
165
- | IQ1_S | 0.6369 | 0.3178 | -14% | -20% | -38% | -43% |
166
- | IQ1_M | 0.6316 | 0.3313 | -15% | -21% | -36% | -41% |
167
- | IQ2_XXS | 0.7236 | 0.4582 | -2% | -9% | -11% | -18% |
168
- | IQ2_M | 0.7427 | 0.5869 | +0% | -7% | +14% | +5% |
169
- | Q2_K | 0.7683 | 0.5744 | +4% | -4% | +12% | +3% |
170
- | IQ3_XXS | 0.7780 | 0.5991 | +5% | -2% | +16% | +8% |
171
- | IQ3_XS | 0.7727 | 0.5615 | +5% | -3% | +9% | +1% |
172
- | IQ3_S | 0.8002 | 0.5505 | +8% | +0% | +7% | -1% |
173
- | IQ3_M | 0.8106 | 0.5387 | +10% | +2% | +5% | -3% |
174
- | Q3_K_M | 0.7567 | 0.5267 | +2% | -5% | +2% | -5% |
175
- | IQ4_NL | 0.7930 | 0.5598 | +7% | -1% | +9% | +0% |
176
- | IQ4_XS | 0.7979 | 0.5627 | +8% | +0% | +9% | +1% |
177
- | Q4_K_M | 0.8029 | 0.5569 | +9% | +1% | +8% | +0% |
178
- | Q5_K_S | 0.7969 | 0.5581 | +8% | +0% | +8% | +0% |
179
- | Q5_K_M | 0.7927 | 0.5601 | +7% | -1% | +9% | +1% |
180
- | Q6_K | 0.7951 | 0.5636 | +8% | +0% | +10% | +1% |
181
- | Q8_0 | 0.7938 | 0.5687 | +7% | +0% | +11% | +2% |
182
- | F16 | 0.7940 | 0.5610 | +7% | +0% | +9% | +1% |
183
- | jinaai-jina-embeddings-v3 | 0.7393 | 0.5144 | +0% | -7% | +0% | -8% |
184
- | jinaai-jina-embeddings-v4 | 0.7977 | 0.5571 | +8% | +0% | +8% | +0% |
 
185
 
186
 
 
160
  | F16 | 5.75 GiB | 16.00 | 1050 | 1083 | +0% | +0% |
161
 
162
  #### Table 2: NDCG@5
163
+ ## NDCG@5 Performance Comparison
164
+ | Quant | NanoHotpotQA | NanoFiQA2018 | NanoArguAna | NanoNFCorpus | NanoSciFact | Δ to v3 (HotpotQA) | Δ to v4 (HotpotQA) | Δ to v3 (FiQA2018) | Δ to v4 (FiQA2018) | Δ to v3 (ArguAna) | Δ to v4 (ArguAna) | Δ to v3 (NFCorpus) | Δ to v4 (NFCorpus) | Δ to v3 (SciFact) | Δ to v4 (SciFact) |
165
+ |------------------|--------------|--------------|-------------|--------------|-------------|-------------------|-------------------|-------------------|-------------------|------------------|------------------|-------------------|-------------------|------------------|------------------|
166
+ | IQ1_S | 0.6369 | 0.3178 | 0.3798 | 0.2933 | 0.5934 | -14% | -20% | -38% | -43% | -17% | -22% | -28% | -33% | -24% | -25% |
167
+ | IQ1_M | 0.6316 | 0.3313 | 0.5167 | 0.3256 | 0.6114 | -15% | -21% | -36% | -41% | +12% | +7% | -20% | -25% | -22% | -23% |
168
+ | IQ2_XXS | 0.7236 | 0.4582 | 0.4584 | 0.4067 | 0.7392 | -2% | -9% | -11% | -18% | -0% | -5% | -0% | -7% | -5% | -7% |
169
+ | IQ2_M | 0.7427 | 0.5869 | 0.5090 | 0.4468 | 0.7880 | +0% | -7% | +14% | +5% | +11% | +5% | +10% | +3% | +1% | -1% |
170
+ | Q2_K | 0.7683 | 0.5744 | 0.5168 | 0.4183 | 0.7546 | +4% | -4% | +12% | +3% | +12% | +7% | +3% | -4% | -4% | -5% |
171
+ | IQ3_XXS | 0.7780 | 0.5991 | 0.4811 | 0.4267 | 0.7610 | +5% | -2% | +16% | +8% | +5% | -1% | +5% | -2% | -3% | -4% |
172
+ | IQ3_XS | 0.7727 | 0.5615 | 0.5195 | 0.4439 | 0.7726 | +5% | -3% | +9% | +1% | +13% | +7% | +9% | +2% | -1% | -3% |
173
+ | IQ3_S | 0.8002 | 0.5505 | 0.4886 | 0.4381 | 0.7690 | +8% | +0% | +7% | -1% | +6% | +1% | +8% | +1% | -2% | -3% |
174
+ | IQ3_M | 0.8106 | 0.5387 | 0.5091 | 0.4462 | 0.7760 | +10% | +2% | +5% | -3% | +11% | +5% | +10% | +3% | -1% | -3% |
175
+ | Q3_K_M | 0.7567 | 0.5267 | 0.4486 | 0.4092 | 0.7775 | +2% | -5% | +2% | -5% | -2% | -7% | +1% | -6% | -1% | -2% |
176
+ | IQ4_NL | 0.7930 | 0.5598 | 0.4911 | 0.4285 | 0.7794 | +7% | -1% | +9% | +0% | +7% | +1% | +5% | -2% | -0% | -2% |
177
+ | IQ4_XS | 0.7979 | 0.5627 | 0.4947 | 0.4258 | 0.7789 | +8% | +0% | +9% | +1% | +8% | +2% | +5% | -2% | -0% | -2% |
178
+ | Q4_K_M | 0.8029 | 0.5569 | 0.4883 | 0.4226 | 0.7877 | +9% | +1% | +8% | +0% | +6% | +1% | +4% | -3% | +1% | -1% |
179
+ | Q5_K_S | 0.7969 | 0.5581 | 0.4721 | 0.4288 | 0.7842 | +8% | +0% | +8% | +0% | +3% | -3% | +5% | -1% | +0% | -2% |
180
+ | Q5_K_M | 0.7927 | 0.5601 | 0.4745 | 0.4247 | 0.7873 | +7% | -1% | +9% | +1% | +3% | -2% | +4% | -2% | +1% | -1% |
181
+ | Q6_K | 0.7951 | 0.5636 | 0.4822 | 0.4337 | 0.7846 | +8% | +0% | +10% | +1% | +5% | -0% | +7% | -0% | +0% | -1% |
182
+ | Q8_0 | 0.7938 | 0.5687 | 0.4784 | 0.4335 | 0.7851 | +7% | +0% | +11% | +2% | +4% | -1% | +7% | -0% | +0% | -1% |
183
+ | F16 | 0.7940 | 0.5610 | 0.4931 | 0.4343 | 0.7963 | +7% | +0% | +9% | +1% | +7% | +2% | +7% | -0% | +2% | +0% |
184
+ | jinaai-jina-embeddings-v3 | 0.7393 | 0.5144 | 0.4600 | 0.4068 | 0.7820 | +0% | -7% | +0% | -8% | +0% | -5% | +0% | -6% | +0% | -2% |
185
+ | jinaai-jina-embeddings-v4 | 0.7977 | 0.5571 | 0.4844 | 0.4351 | 0.7963 | +8% | +0% | +8% | +0% | +5% | +0% | +7% | +0% | +2% | +0% |
186
 
187