LumiOpen/Llama-Poro-2-8B-Long-Math-Reasoning-RL-Preview
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: LumiOpen/Llama-Poro-2-8B-Long-Math-Reasoning-RL-Preview
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-01 22:33:21 +08:00
commit 4a4173fbc9
16 changed files with 3200 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
config.json Normal file
View File

@@ -0,0 +1,171 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 128001,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": false,
"transformers_version": "4.55.0",
"use_cache": true,
"vocab_size": 128384,
"rope_scaling": {
"factor": 16.0,
"long_factor": [
1.0700000524520874,
1.100000023841858,
1.1399999856948853,
1.1399999856948853,
1.149999976158142,
1.159999966621399,
1.159999966621399,
1.1799999475479126,
1.1799999475479126,
1.1899999380111694,
1.2299998998641968,
1.2299998998641968,
1.2999998331069946,
1.3799998760223389,
1.429999828338623,
1.4399996995925903,
1.869999647140503,
1.9199997186660767,
1.9399996995925903,
2.3799996376037598,
2.4599997997283936,
2.499999761581421,
2.9099998474121094,
3.2799994945526123,
3.8399994373321533,
4.589999198913574,
4.739999771118164,
4.800000190734863,
5.260000228881836,
5.260000228881836,
6.310000419616699,
8.330000877380371,
9.209999084472656,
9.889999389648438,
10.729999542236328,
11.369999885559082,
13.589999198913574,
13.589999198913574,
15.479998588562012,
15.479998588562012,
15.489999771118164,
15.899998664855957,
15.989998817443848,
16.049999237060547,
16.10999870300293,
16.10999870300293,
16.1299991607666,
16.170000076293945,
16.190000534057617,
16.200000762939453,
16.200000762939453,
16.30000114440918,
16.329999923706055,
16.329999923706055,
16.34000015258789,
16.530000686645508,
16.64000129699707,
16.68000030517578,
16.700000762939453,
16.700002670288086,
16.790002822875977,
16.800003051757812,
16.800003051757812,
17.01000213623047
],
"original_max_position_embeddings": 8192,
"rope_type": "longrope",
"short_factor": [
1.0700000524520874,
1.100000023841858,
1.1399999856948853,
1.1399999856948853,
1.149999976158142,
1.159999966621399,
1.159999966621399,
1.1799999475479126,
1.1799999475479126,
1.1899999380111694,
1.2299998998641968,
1.2299998998641968,
1.2999998331069946,
1.3799998760223389,
1.429999828338623,
1.4399996995925903,
1.869999647140503,
1.9199997186660767,
1.9399996995925903,
2.3799996376037598,
2.4599997997283936,
2.499999761581421,
2.9099998474121094,
3.2799994945526123,
3.8399994373321533,
4.589999198913574,
4.739999771118164,
4.800000190734863,
5.260000228881836,
5.260000228881836,
6.310000419616699,
8.330000877380371,
9.209999084472656,
9.889999389648438,
10.729999542236328,
11.369999885559082,
13.589999198913574,
13.589999198913574,
15.479998588562012,
15.479998588562012,
15.489999771118164,
15.899998664855957,
15.989998817443848,
16.049999237060547,
16.10999870300293,
16.10999870300293,
16.1299991607666,
16.170000076293945,
16.190000534057617,
16.200000762939453,
16.200000762939453,
16.30000114440918,
16.329999923706055,
16.329999923706055,
16.34000015258789,
16.530000686645508,
16.64000129699707,
16.68000030517578,
16.700000762939453,
16.700002670288086,
16.790002822875977,
16.800003051757812,
16.800003051757812,
17.01000213623047
],
"type": "longrope"
},
"rope_theta": 500000,
"torch_dtype": "bfloat16"
}