1+ model,n_params,phase,model_family
2+ Qwen/Qwen2.5-7B,7,PT,non_bamba
3+ Zyphra/Zamba-7B-v1,7,PT,non_bamba
4+ allenai/OLMo-2-1124-7B,7,PT,non_bamba
5+ allenai/OLMo-7B-0424-hf,7,PT,non_bamba
6+ allenai/OLMo-7B-hf,7,PT,non_bamba
7+ google/gemma-2-9b,9,PT,non_bamba
8+ ibm-fms/Bamba-9.8b-1.8T-hf,9,PT,bamba
9+ ibm-fms/Bamba-9.8b-2.2T-hf,9,PT,bamba
10+ ibm-fms/Bamba-9.8b-2T-hf,9,PT,bamba
11+ ibm-fms/Bamba-9B-1.8T-fp8,9,PT,bamba
12+ ibm-fms/Bamba-9B-2.65T,9,PT,bamba
13+ ibm-fms/Bamba-9B-2T-fp8,9,PT,bamba
14+ ibm-fms/Bamba-9B-fp8,9,PT,bamba
15+ ibm-fms/Bamba-9b-2.1T-hf,9,PT,bamba
16+ ibm-fms/Bamba-9b-2.3T-hf,9,PT,bamba
17+ ibm-fms/Bamba-9b-2.5T-hf,9,PT,bamba
18+ ibm-fms/Bamba-9b-2.6T-hf,9,PT,bamba
19+ ibm-fms/Bamba-9b-2.8T-hf,9,PT,bamba
20+ ibm-fms/Bamba_annealed_models/Bamba-9b-2.1T-finemath-hf,9,PT,bamba
21+ ibm-fms/Bamba_annealed_models/Bamba-9b-Olmo-constant-2.5T-hf,9,PT,bamba
22+ ibm-fms/Bamba_annealed_models/Bamba-9b-Olmo-cosine-2.5T-hf,9,PT,bamba
23+ ibm-fms/Bamba_annealed_models/Bamba-9b-Olmo-cosine-4e5-2.5T-hf,9,PT,bamba
24+ ibm-fms/agentinstruct_lr1e_5-hf,9,SFT,bamba
25+ ibm-fms/agentinstruct_lr1e_6-hf,9,SFT,bamba
26+ ibm-fms/anteater_lr1e_5-hf,9,SFT,bamba
27+ ibm-fms/anteater_lr1e_6-hf,9,SFT,bamba
28+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_gbs_256-hf,9,SFT,bamba
29+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_gbs_32-hf,9,SFT,bamba
30+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_gbs_64-hf,9,SFT,bamba
31+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_wd_0.06-hf,9,SFT,bamba
32+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_wd_0.1-hf,9,SFT,bamba
33+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_wd_0.1_gbs_16-hf,9,SFT,bamba
34+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_wd_0.1_gbs_32-hf,9,SFT,bamba
35+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_wd_0_gbs_128_base-hf,9,SFT,bamba
36+ ibm-fms/instruct_models/tuluv3/2.3T_base/lr1e_6_wd_0_gbs_16-hf,9,SFT,bamba
37+ ibm-fms/lchu/70b_hsdp_768/hf/step-225000,70,PT,non_bamba
38+ ibm-fms/tuluv3_lr1e_5-hf,9,SFT,bamba
39+ ibm-fms/tuluv3_lr1e_6-hf,9,SFT,bamba
40+ ibm-granite/granite-3.0-8b-base,8,PT,non_bamba
41+ ibm-granite/granite-7b-base,7,PT,non_bamba
42+ meta-llama/Llama-2-7b-hf,7,PT,non_bamba
43+ meta-llama/Llama-3.1-8B,8,PT,non_bamba
44+ meta-llama/Meta-Llama-3.1-70B,70,PT,non_bamba
45+ nvidia/mamba2-hybrid-8b-3t-4k*,8,PT,non_bamba
46+ tiiuae/falcon-mamba-7b,7,PT,non_bamba
0 commit comments