cycy233/misllm_v4.2 |
base |
1187.37 |
1187.37 |
27316 |
27316 |
0.53 |
0.53 |
0.33 |
0.33 |
0.19 |
0.19 |
1068 |
1068 |
0.97 |
7B |
0.97 |
7.86 |
7.86 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v4-2_v1 |
2024-05-19 |
cycy233/misllm_v4.2 |
cycy233/misllm_v4.1 |
base |
1184.99 |
1184.99 |
11413 |
11413 |
0.51 |
0.51 |
0.32 |
0.32 |
0.19 |
0.19 |
490 |
490 |
0.98 |
7B |
0.98 |
7.60 |
7.60 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v4-1_v1 |
2024-05-18 |
cycy233/misllm_v4.1 |
cycy233/misllm_v4.3 |
base |
1182.95 |
1182.95 |
17146 |
50529 |
0.52 |
0.52 |
0.32 |
0.37 |
0.24 |
0.24 |
755 |
1979 |
0.94 |
7B |
0.94 |
7.55 |
7.65 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v4-3_v1 |
2024-05-20 |
cycy233/misllm_v4.3 |
cycy233/misllm_v4.3 |
base_v |
1180.95 |
1182.95 |
17199 |
50529 |
0.52 |
0.52 |
0.37 |
0.37 |
0.20 |
0.24 |
675 |
1979 |
0.93 |
7B |
0.94 |
7.59 |
7.65 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v4-3_v2 |
2024-05-20 |
cycy233/misllm_v4.3 |
cycy233/misllm_v4.3 |
rolej |
1180.00 |
1182.95 |
16184 |
50529 |
0.51 |
0.52 |
0.34 |
0.37 |
0.20 |
0.24 |
549 |
1979 |
0.93 |
7B |
0.94 |
7.65 |
7.65 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v4-3_v3 |
2024-05-20 |
cycy233/misllm_v4.3 |
cycy233/misllm_v4.0 |
base |
1171.46 |
1171.46 |
19385 |
19385 |
0.50 |
0.50 |
0.33 |
0.33 |
0.24 |
0.24 |
654 |
654 |
0.97 |
7B |
0.97 |
7.63 |
7.63 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v4-0_v1 |
2024-05-18 |
cycy233/misllm_v4.0 |
cycy233/misllm_v2.3 |
base |
1169.35 |
1169.35 |
24783 |
38069 |
0.50 |
0.50 |
0.28 |
0.32 |
0.28 |
0.28 |
1024 |
1517 |
0.8 |
7B |
0.80 |
7.40 |
7.40 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v2-3_v1 |
2024-05-13 |
cycy233/misllm_v2.3 |
cycy233/misllm_v3.0 |
base |
1169.23 |
1169.23 |
18398 |
69652 |
0.51 |
0.51 |
0.26 |
0.28 |
0.29 |
0.29 |
639 |
2439 |
|
7B |
0.85 |
7.48 |
7.48 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-0_v2 |
2024-05-16 |
cycy233/misllm_v3.0 |
cycy233/misllm_v3.2 |
base |
1168.59 |
1168.59 |
24847 |
24847 |
0.50 |
0.50 |
0.28 |
0.28 |
0.29 |
0.29 |
926 |
926 |
0.81 |
7B |
0.81 |
7.40 |
7.40 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-2_v1 |
2024-05-16 |
cycy233/misllm_v3.2 |
cycy233/misllm_v3.1 |
basep |
1167.72 |
1167.72 |
16993 |
40137 |
0.50 |
0.50 |
0.25 |
0.31 |
0.30 |
0.30 |
762 |
1686 |
0.85 |
7B |
0.86 |
7.31 |
7.34 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-1_v3 |
2024-05-16 |
cycy233/misllm_v3.1 |
cycy233/misllm_v3.1 |
base |
1166.91 |
1167.72 |
11622 |
40137 |
0.50 |
0.50 |
0.30 |
0.31 |
0.27 |
0.30 |
486 |
1686 |
0.81 |
7B |
0.86 |
7.32 |
7.34 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-1_v2 |
2024-05-16 |
cycy233/misllm_v3.1 |
cycy233/misllm1.1 |
base |
1165.60 |
1165.60 |
23367 |
84516 |
0.50 |
0.50 |
0.31 |
0.31 |
0.27 |
0.27 |
812 |
3591 |
0.61 |
7B |
0.61 |
7.40 |
7.48 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm1-1_v1 |
2024-05-10 |
cycy233/misllm1.1 |
cycy233/misllm_v2.4 |
base |
1163.93 |
1163.93 |
29201 |
29201 |
0.49 |
0.49 |
0.28 |
0.28 |
0.28 |
0.28 |
1074 |
1074 |
0.8 |
7B |
0.80 |
7.31 |
7.31 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v2-4_v1 |
2024-05-14 |
cycy233/misllm_v2.4 |
cycy233/misllm_v2.6 |
base |
1162.25 |
1162.25 |
10593 |
10593 |
0.49 |
0.49 |
0.31 |
0.31 |
0.24 |
0.24 |
376 |
376 |
0.53 |
7B |
0.53 |
7.45 |
7.45 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v2-6_v1 |
2024-05-15 |
cycy233/misllm_v2.6 |
cycy233/misllm1.1 |
rirv_test |
1162.25 |
1165.60 |
28909 |
84516 |
0.48 |
0.50 |
0.30 |
0.31 |
0.25 |
0.27 |
1448 |
3591 |
0.59 |
7B |
0.61 |
7.48 |
7.48 |
shiroe40 |
basic |
rirv938/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm1-1_v2 |
2024-05-10 |
cycy233/misllm1.1 |
cycy233/misllm_v3.0 |
baseii |
1162.24 |
1169.23 |
14060 |
69652 |
0.50 |
0.51 |
0.28 |
0.28 |
0.26 |
0.29 |
488 |
2439 |
0.85 |
7B |
0.85 |
7.44 |
7.48 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-0_v4 |
2024-05-16 |
cycy233/misllm_v3.0 |
cycy233/misllm_v1.4 |
base_v1 |
1162.11 |
1162.11 |
14698 |
14698 |
0.50 |
0.50 |
0.26 |
0.26 |
0.29 |
0.29 |
705 |
705 |
0.7 |
7B |
0.70 |
7.41 |
7.41 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v1-4_v1 |
2024-05-11 |
cycy233/misllm_v1.4 |
cycy233/misllm_v2.3 |
basev |
1161.20 |
1169.35 |
13286 |
38069 |
0.49 |
0.50 |
0.32 |
0.32 |
0.22 |
0.28 |
493 |
1517 |
0.75 |
7B |
0.80 |
7.28 |
7.40 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v2-3_v2 |
2024-05-14 |
cycy233/misllm_v2.3 |
cycy233/misllm_v2.5 |
base |
1161.15 |
1161.15 |
23365 |
23365 |
0.49 |
0.49 |
0.28 |
0.28 |
0.25 |
0.25 |
1062 |
1062 |
0.61 |
7B |
0.61 |
7.39 |
7.39 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v2-5_v1 |
2024-05-15 |
cycy233/misllm_v2.5 |
cycy233/misllm1.1 |
hot |
1160.36 |
1165.60 |
16083 |
84516 |
0.49 |
0.50 |
0.31 |
0.31 |
0.23 |
0.27 |
513 |
3591 |
0.58 |
7B |
0.61 |
7.38 |
7.48 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm1-1_v4 |
2024-05-13 |
cycy233/misllm1.1 |
cycy233/misllm_v1.3 |
base_v1 |
1159.41 |
1159.41 |
6762 |
25612 |
0.49 |
0.49 |
0.32 |
0.32 |
0.24 |
0.26 |
373 |
1358 |
0.65 |
7B |
0.65 |
7.18 |
7.35 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v1-3_v2 |
2024-05-11 |
cycy233/misllm_v1.3 |
cycy233/misllm1.0 |
base2 |
1158.92 |
1158.92 |
22705 |
47953 |
0.49 |
0.49 |
0.30 |
0.30 |
0.25 |
0.29 |
813 |
2186 |
0.71 |
7B |
0.91 |
7.45 |
7.45 |
shiroe40 |
basic |
rirv938/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm1-0_v3 |
2024-05-10 |
cycy233/misllm1.0 |
cycy233/misllm_v3.3 |
base |
1158.32 |
1158.32 |
14202 |
39902 |
0.49 |
0.49 |
0.28 |
0.28 |
0.26 |
0.26 |
523 |
1636 |
0.98 |
7B |
0.98 |
7.45 |
7.47 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-3_v1 |
2024-05-17 |
cycy233/misllm_v3.3 |
cycy233/misllm_v3.0 |
inference_test |
1156.42 |
1169.23 |
18551 |
69652 |
0.49 |
0.51 |
0.28 |
0.28 |
0.25 |
0.29 |
675 |
2439 |
|
7B |
0.85 |
7.34 |
7.48 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-0_v3 |
2024-05-16 |
cycy233/misllm_v3.0 |
cycy233/misllm_v3.3 |
basei |
1155.46 |
1158.32 |
25700 |
39902 |
0.48 |
0.49 |
0.28 |
0.28 |
0.24 |
0.26 |
1113 |
1636 |
0.97 |
7B |
0.98 |
7.47 |
7.47 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-3_v2 |
2024-05-17 |
cycy233/misllm_v3.3 |
cycy233/misllm_v2.1 |
base |
1155.29 |
1155.29 |
7970 |
7970 |
0.46 |
0.46 |
0.31 |
0.31 |
0.24 |
0.24 |
304 |
304 |
0.6 |
7B |
0.60 |
7.28 |
7.28 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v2-1_v1 |
2024-05-13 |
cycy233/misllm_v2.1 |
cycy233/misllm_v2.0 |
base_v1 |
1154.87 |
1154.87 |
13956 |
13956 |
0.48 |
0.48 |
0.31 |
0.31 |
0.25 |
0.25 |
754 |
754 |
0.53 |
7B |
0.53 |
7.24 |
7.24 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v2-0_v1 |
2024-05-12 |
cycy233/misllm_v2.0 |
cycy233/misllm_v2.2 |
base_v1 |
1153.96 |
1153.96 |
27182 |
27182 |
0.48 |
0.48 |
0.30 |
0.30 |
0.26 |
0.26 |
983 |
983 |
0.59 |
7B |
0.59 |
7.22 |
7.22 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v2-2_v1 |
2024-05-13 |
cycy233/misllm_v2.2 |
cycy233/misllm1.0 |
base |
1153.02 |
1158.92 |
13448 |
47953 |
0.48 |
0.49 |
0.30 |
0.30 |
0.26 |
0.29 |
756 |
2186 |
0.7 |
7B |
0.91 |
7.43 |
7.45 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm1-0_v1 |
2024-05-09 |
cycy233/misllm1.0 |
cycy233/misllm_v1.3 |
base_v1 |
1152.77 |
1159.41 |
18850 |
25612 |
0.48 |
0.49 |
0.30 |
0.32 |
0.26 |
0.26 |
985 |
1358 |
0.64 |
7B |
0.65 |
7.35 |
7.35 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v1-3_v1 |
2024-05-11 |
cycy233/misllm_v1.3 |
cycy233/misLLM_v1.2 |
base |
1149.82 |
1149.82 |
29253 |
29253 |
0.46 |
0.46 |
0.28 |
0.28 |
0.28 |
0.28 |
1562 |
1562 |
0.77 |
7B |
0.77 |
7.31 |
7.31 |
shiroe40 |
basic |
rirv938/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v1-2_v1 |
2024-05-10 |
cycy233/misLLM_v1.2 |
cycy233/misllm_v3.1 |
base |
1139.95 |
1167.72 |
11522 |
40137 |
0.46 |
0.50 |
0.31 |
0.31 |
0.30 |
0.30 |
438 |
1686 |
0.86 |
7B |
0.86 |
7.34 |
7.34 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
4 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-1_v1 |
2024-05-16 |
cycy233/misllm_v3.1 |
cycy233/misllm_v3.0 |
basett |
1137.55 |
1169.23 |
18643 |
69652 |
0.46 |
0.51 |
0.27 |
0.28 |
0.28 |
0.29 |
637 |
2439 |
|
7B |
0.85 |
7.30 |
7.48 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
4 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm-v3-0_v1 |
2024-05-16 |
cycy233/misllm_v3.0 |
cycy233/llm3.2 |
base |
1135.63 |
1135.63 |
24637 |
53104 |
0.45 |
0.45 |
0.29 |
0.31 |
0.25 |
0.26 |
922 |
1942 |
0.68 |
7B |
0.70 |
7.13 |
7.13 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm3-2_v1 |
2024-05-09 |
cycy233/llm3.2 |
cycy233/llm2.0 |
rolej |
1134.63 |
1134.63 |
23248 |
106635 |
0.46 |
0.46 |
0.27 |
0.29 |
0.31 |
0.32 |
829 |
4011 |
0.82 |
7B |
0.84 |
7.29 |
7.37 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm2-0_v4 |
2024-05-07 |
cycy233/llm2.0 |
cycy233/misllm1.1 |
base |
1133.33 |
1165.60 |
16157 |
84516 |
0.45 |
0.50 |
0.29 |
0.31 |
0.24 |
0.27 |
818 |
3591 |
0.53 |
7B |
0.61 |
7.26 |
7.48 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
4 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm1-1_v3 |
2024-05-11 |
cycy233/misllm1.1 |
cycy233/llm3.0 |
base |
1133.22 |
1133.22 |
24371 |
75735 |
0.45 |
0.45 |
0.26 |
0.27 |
0.27 |
0.29 |
1182 |
3627 |
0.7 |
7B |
0.81 |
7.31 |
7.31 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm3-0_v2 |
2024-05-08 |
cycy233/llm3.0 |
cycy233/llm2.0 |
role |
1132.96 |
1134.63 |
24074 |
106635 |
0.45 |
0.46 |
0.29 |
0.29 |
0.29 |
0.32 |
827 |
4011 |
0.75 |
7B |
0.84 |
7.37 |
7.37 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm2-0_v3 |
2024-05-07 |
cycy233/llm2.0 |
cycy233/llm3.0 |
rolel |
1131.82 |
1133.22 |
27000 |
75735 |
0.45 |
0.45 |
0.27 |
0.27 |
0.28 |
0.29 |
1263 |
3627 |
0.81 |
7B |
0.81 |
7.05 |
7.31 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm3-0_v3 |
2024-05-08 |
cycy233/llm3.0 |
cycy233/llm3.0 |
rolee |
1131.38 |
1133.22 |
24364 |
75735 |
0.45 |
0.45 |
0.25 |
0.27 |
0.29 |
0.29 |
1182 |
3627 |
0.65 |
7B |
0.81 |
7.17 |
7.31 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm3-0_v1 |
2024-05-08 |
cycy233/llm3.0 |
cycy233/llm3.1 |
base |
1129.04 |
1129.04 |
7316 |
19876 |
0.45 |
0.45 |
0.27 |
0.29 |
0.29 |
0.29 |
267 |
696 |
0.73 |
7B |
0.89 |
7.05 |
7.37 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm3-1_v2 |
2024-05-09 |
cycy233/llm3.1 |
cycy233/llm2.0 |
rolep |
1127.08 |
1134.63 |
13712 |
106635 |
0.44 |
0.46 |
0.29 |
0.29 |
0.27 |
0.32 |
748 |
4011 |
0.82 |
7B |
0.84 |
7.21 |
7.37 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm2-0_v5 |
2024-05-07 |
cycy233/llm2.0 |
cycy233/misllm1.0 |
test |
1125.80 |
1158.92 |
11800 |
47953 |
0.44 |
0.49 |
0.26 |
0.30 |
0.29 |
0.29 |
617 |
2186 |
0.91 |
7B |
0.91 |
7.25 |
7.45 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
MistralForCausalLM |
cycy233-misllm1-0_v2 |
2024-05-09 |
cycy233/misllm1.0 |
cycy233/llm3.2 |
base1 |
1123.51 |
1135.63 |
28467 |
53104 |
0.44 |
0.45 |
0.31 |
0.31 |
0.26 |
0.26 |
1020 |
1942 |
0.7 |
7B |
0.70 |
7.05 |
7.13 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm3-2_v2 |
2024-05-09 |
cycy233/llm3.2 |
cycy233/llm2.0 |
llmV2 |
1111.45 |
1134.63 |
23010 |
106635 |
0.42 |
0.46 |
0.29 |
0.29 |
0.29 |
0.32 |
800 |
4011 |
0.79 |
7B |
0.84 |
7.06 |
7.37 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
8 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm2-0_v2 |
2024-05-07 |
cycy233/llm2.0 |
cycy233/llm3.1 |
rolev1 |
1105.59 |
1129.04 |
12560 |
19876 |
0.41 |
0.45 |
0.29 |
0.29 |
0.28 |
0.29 |
429 |
696 |
0.89 |
7B |
0.89 |
7.37 |
7.37 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm3-1_v1 |
2024-05-09 |
cycy233/llm3.1 |
cycy233/llm2.0 |
rolei |
1079.06 |
1134.63 |
22591 |
106635 |
0.39 |
0.46 |
0.28 |
0.29 |
0.32 |
0.32 |
807 |
4011 |
0.84 |
7B |
0.84 |
7.12 |
7.37 |
shiroe40 |
basic |
ChaiML/reward_gpt2_medium_preference_24m_e2 |
16 |
512 |
64 |
LlamaForCausalLM |
cycy233-llm2-0_v1 |
2024-05-07 |
cycy233/llm2.0 |