Skip to content

Commit ef8d0a1

Browse files
committed
add seed metadata
Signed-off-by: Yotam Perlitz <[email protected]>
1 parent 1c976b1 commit ef8d0a1

File tree

1 file changed

+46
-0
lines changed

1 file changed

+46
-0
lines changed
Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
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

Comments
 (0)