diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..2519cacaf88fa8739836719b744fbd82c50c4f55 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +compiled/186a933115232053cdff.neff filter=lfs diff=lfs merge=lfs -text +compiled/540db8b9571300c15792.neff filter=lfs diff=lfs merge=lfs -text +compiled/585a14c8d348e11367d1.neff filter=lfs diff=lfs merge=lfs -text +compiled/6f0431e83e140df0acd9.neff filter=lfs diff=lfs merge=lfs -text +compiled/86a37b8c9f44ef0ad841.neff filter=lfs diff=lfs merge=lfs -text +compiled/c5726de0e8bc3fd6f4c9.neff filter=lfs diff=lfs merge=lfs -text +compiled/e0158d7717a18978a6c7.neff filter=lfs diff=lfs merge=lfs -text +compiled/e87cecd034e5ac4c3f36.neff filter=lfs diff=lfs merge=lfs -text +compiled/ea24e07b03ca7ec5310c.neff filter=lfs diff=lfs merge=lfs -text +compiled/fedc38910ff9aec1ce50.neff filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint/config.json b/checkpoint/config.json new file mode 100644 index 0000000000000000000000000000000000000000..ee733de899e15ef0839d8c816772911c24c53960 --- /dev/null +++ b/checkpoint/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "CodeLlama-7b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 16384, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.33.2", + "use_cache": true, + "vocab_size": 32016 +} diff --git a/checkpoint/generation_config.json b/checkpoint/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..7a03f6daf5b60ad02d8503e1ad01049b2d1935ec --- /dev/null +++ b/checkpoint/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.33.2" +} diff --git a/checkpoint/pytorch_model.bin/key_to_filename.json b/checkpoint/pytorch_model.bin/key_to_filename.json new file mode 100644 index 0000000000000000000000000000000000000000..e2d47876f62bb7f3c02df785d29629d0fffef45f --- /dev/null +++ b/checkpoint/pytorch_model.bin/key_to_filename.json @@ -0,0 +1,293 @@ +{ + "model.embed_tokens.weight": "p0.model.embed_tokens.weight", + "model.layers.0.self_attn.q_proj.weight": "p1.model.layers.0.self_attn.q_proj.weight", + "model.layers.0.self_attn.k_proj.weight": "p2.model.layers.0.self_attn.k_proj.weight", + "model.layers.0.self_attn.v_proj.weight": "p3.model.layers.0.self_attn.v_proj.weight", + "model.layers.0.self_attn.o_proj.weight": "p4.model.layers.0.self_attn.o_proj.weight", + "model.layers.0.mlp.gate_proj.weight": "p5.model.layers.0.mlp.gate_proj.weight", + "model.layers.0.mlp.up_proj.weight": "p6.model.layers.0.mlp.up_proj.weight", + "model.layers.0.mlp.down_proj.weight": "p7.model.layers.0.mlp.down_proj.weight", + "model.layers.0.input_layernorm.weight": "p8.model.layers.0.input_layernorm.weight", + "model.layers.0.post_attention_layernorm.weight": "p9.model.layers.0.post_attention_layernorm.weight", + "model.layers.1.self_attn.q_proj.weight": "p10.model.layers.1.self_attn.q_proj.weight", + "model.layers.1.self_attn.k_proj.weight": "p11.model.layers.1.self_attn.k_proj.weight", + "model.layers.1.self_attn.v_proj.weight": "p12.model.layers.1.self_attn.v_proj.weight", + "model.layers.1.self_attn.o_proj.weight": "p13.model.layers.1.self_attn.o_proj.weight", + "model.layers.1.mlp.gate_proj.weight": "p14.model.layers.1.mlp.gate_proj.weight", + "model.layers.1.mlp.up_proj.weight": "p15.model.layers.1.mlp.up_proj.weight", + "model.layers.1.mlp.down_proj.weight": "p16.model.layers.1.mlp.down_proj.weight", + "model.layers.1.input_layernorm.weight": "p17.model.layers.1.input_layernorm.weight", + "model.layers.1.post_attention_layernorm.weight": "p18.model.layers.1.post_attention_layernorm.weight", + "model.layers.2.self_attn.q_proj.weight": "p19.model.layers.2.self_attn.q_proj.weight", + "model.layers.2.self_attn.k_proj.weight": "p20.model.layers.2.self_attn.k_proj.weight", + "model.layers.2.self_attn.v_proj.weight": "p21.model.layers.2.self_attn.v_proj.weight", + "model.layers.2.self_attn.o_proj.weight": "p22.model.layers.2.self_attn.o_proj.weight", + "model.layers.2.mlp.gate_proj.weight": "p23.model.layers.2.mlp.gate_proj.weight", + "model.layers.2.mlp.up_proj.weight": "p24.model.layers.2.mlp.up_proj.weight", + "model.layers.2.mlp.down_proj.weight": "p25.model.layers.2.mlp.down_proj.weight", + "model.layers.2.input_layernorm.weight": "p26.model.layers.2.input_layernorm.weight", + "model.layers.2.post_attention_layernorm.weight": "p27.model.layers.2.post_attention_layernorm.weight", + "model.layers.3.self_attn.q_proj.weight": "p28.model.layers.3.self_attn.q_proj.weight", + "model.layers.3.self_attn.k_proj.weight": "p29.model.layers.3.self_attn.k_proj.weight", + "model.layers.3.self_attn.v_proj.weight": "p30.model.layers.3.self_attn.v_proj.weight", + "model.layers.3.self_attn.o_proj.weight": "p31.model.layers.3.self_attn.o_proj.weight", + "model.layers.3.mlp.gate_proj.weight": "p32.model.layers.3.mlp.gate_proj.weight", + "model.layers.3.mlp.up_proj.weight": "p33.model.layers.3.mlp.up_proj.weight", + "model.layers.3.mlp.down_proj.weight": "p34.model.layers.3.mlp.down_proj.weight", + "model.layers.3.input_layernorm.weight": "p35.model.layers.3.input_layernorm.weight", + "model.layers.3.post_attention_layernorm.weight": "p36.model.layers.3.post_attention_layernorm.weight", + "model.layers.4.self_attn.q_proj.weight": "p37.model.layers.4.self_attn.q_proj.weight", + "model.layers.4.self_attn.k_proj.weight": "p38.model.layers.4.self_attn.k_proj.weight", + "model.layers.4.self_attn.v_proj.weight": "p39.model.layers.4.self_attn.v_proj.weight", + "model.layers.4.self_attn.o_proj.weight": "p40.model.layers.4.self_attn.o_proj.weight", + "model.layers.4.mlp.gate_proj.weight": "p41.model.layers.4.mlp.gate_proj.weight", + "model.layers.4.mlp.up_proj.weight": "p42.model.layers.4.mlp.up_proj.weight", + "model.layers.4.mlp.down_proj.weight": "p43.model.layers.4.mlp.down_proj.weight", + "model.layers.4.input_layernorm.weight": "p44.model.layers.4.input_layernorm.weight", + "model.layers.4.post_attention_layernorm.weight": "p45.model.layers.4.post_attention_layernorm.weight", + "model.layers.5.self_attn.q_proj.weight": "p46.model.layers.5.self_attn.q_proj.weight", + "model.layers.5.self_attn.k_proj.weight": "p47.model.layers.5.self_attn.k_proj.weight", + "model.layers.5.self_attn.v_proj.weight": "p48.model.layers.5.self_attn.v_proj.weight", + "model.layers.5.self_attn.o_proj.weight": "p49.model.layers.5.self_attn.o_proj.weight", + "model.layers.5.mlp.gate_proj.weight": "p50.model.layers.5.mlp.gate_proj.weight", + "model.layers.5.mlp.up_proj.weight": "p51.model.layers.5.mlp.up_proj.weight", + "model.layers.5.mlp.down_proj.weight": "p52.model.layers.5.mlp.down_proj.weight", + "model.layers.5.input_layernorm.weight": "p53.model.layers.5.input_layernorm.weight", + "model.layers.5.post_attention_layernorm.weight": "p54.model.layers.5.post_attention_layernorm.weight", + "model.layers.6.self_attn.q_proj.weight": "p55.model.layers.6.self_attn.q_proj.weight", + "model.layers.6.self_attn.k_proj.weight": "p56.model.layers.6.self_attn.k_proj.weight", + "model.layers.6.self_attn.v_proj.weight": "p57.model.layers.6.self_attn.v_proj.weight", + "model.layers.6.self_attn.o_proj.weight": "p58.model.layers.6.self_attn.o_proj.weight", + "model.layers.6.mlp.gate_proj.weight": "p59.model.layers.6.mlp.gate_proj.weight", + "model.layers.6.mlp.up_proj.weight": "p60.model.layers.6.mlp.up_proj.weight", + "model.layers.6.mlp.down_proj.weight": "p61.model.layers.6.mlp.down_proj.weight", + "model.layers.6.input_layernorm.weight": "p62.model.layers.6.input_layernorm.weight", + "model.layers.6.post_attention_layernorm.weight": "p63.model.layers.6.post_attention_layernorm.weight", + "model.layers.7.self_attn.q_proj.weight": "p64.model.layers.7.self_attn.q_proj.weight", + "model.layers.7.self_attn.k_proj.weight": "p65.model.layers.7.self_attn.k_proj.weight", + "model.layers.7.self_attn.v_proj.weight": "p66.model.layers.7.self_attn.v_proj.weight", + "model.layers.7.self_attn.o_proj.weight": "p67.model.layers.7.self_attn.o_proj.weight", + "model.layers.7.mlp.gate_proj.weight": "p68.model.layers.7.mlp.gate_proj.weight", + "model.layers.7.mlp.up_proj.weight": "p69.model.layers.7.mlp.up_proj.weight", + "model.layers.7.mlp.down_proj.weight": "p70.model.layers.7.mlp.down_proj.weight", + "model.layers.7.input_layernorm.weight": "p71.model.layers.7.input_layernorm.weight", + "model.layers.7.post_attention_layernorm.weight": "p72.model.layers.7.post_attention_layernorm.weight", + "model.layers.8.self_attn.q_proj.weight": "p73.model.layers.8.self_attn.q_proj.weight", + "model.layers.8.self_attn.k_proj.weight": "p74.model.layers.8.self_attn.k_proj.weight", + "model.layers.8.self_attn.v_proj.weight": "p75.model.layers.8.self_attn.v_proj.weight", + "model.layers.8.self_attn.o_proj.weight": "p76.model.layers.8.self_attn.o_proj.weight", + "model.layers.8.mlp.gate_proj.weight": "p77.model.layers.8.mlp.gate_proj.weight", + "model.layers.8.mlp.up_proj.weight": "p78.model.layers.8.mlp.up_proj.weight", + "model.layers.8.mlp.down_proj.weight": "p79.model.layers.8.mlp.down_proj.weight", + "model.layers.8.input_layernorm.weight": "p80.model.layers.8.input_layernorm.weight", + "model.layers.8.post_attention_layernorm.weight": "p81.model.layers.8.post_attention_layernorm.weight", + "model.layers.9.self_attn.q_proj.weight": "p82.model.layers.9.self_attn.q_proj.weight", + "model.layers.9.self_attn.k_proj.weight": "p83.model.layers.9.self_attn.k_proj.weight", + "model.layers.9.self_attn.v_proj.weight": "p84.model.layers.9.self_attn.v_proj.weight", + "model.layers.9.self_attn.o_proj.weight": "p85.model.layers.9.self_attn.o_proj.weight", + "model.layers.9.mlp.gate_proj.weight": "p86.model.layers.9.mlp.gate_proj.weight", + "model.layers.9.mlp.up_proj.weight": "p87.model.layers.9.mlp.up_proj.weight", + "model.layers.9.mlp.down_proj.weight": "p88.model.layers.9.mlp.down_proj.weight", + "model.layers.9.input_layernorm.weight": "p89.model.layers.9.input_layernorm.weight", + "model.layers.9.post_attention_layernorm.weight": "p90.model.layers.9.post_attention_layernorm.weight", + "model.layers.10.self_attn.q_proj.weight": "p91.model.layers.10.self_attn.q_proj.weight", + "model.layers.10.self_attn.k_proj.weight": "p92.model.layers.10.self_attn.k_proj.weight", + "model.layers.10.self_attn.v_proj.weight": "p93.model.layers.10.self_attn.v_proj.weight", + "model.layers.10.self_attn.o_proj.weight": "p94.model.layers.10.self_attn.o_proj.weight", + "model.layers.10.mlp.gate_proj.weight": "p95.model.layers.10.mlp.gate_proj.weight", + "model.layers.10.mlp.up_proj.weight": "p96.model.layers.10.mlp.up_proj.weight", + "model.layers.10.mlp.down_proj.weight": "p97.model.layers.10.mlp.down_proj.weight", + "model.layers.10.input_layernorm.weight": "p98.model.layers.10.input_layernorm.weight", + "model.layers.10.post_attention_layernorm.weight": "p99.model.layers.10.post_attention_layernorm.weight", + "model.layers.11.self_attn.q_proj.weight": "p100.model.layers.11.self_attn.q_proj.weight", + "model.layers.11.self_attn.k_proj.weight": "p101.model.layers.11.self_attn.k_proj.weight", + "model.layers.11.self_attn.v_proj.weight": "p102.model.layers.11.self_attn.v_proj.weight", + "model.layers.11.self_attn.o_proj.weight": "p103.model.layers.11.self_attn.o_proj.weight", + "model.layers.11.mlp.gate_proj.weight": "p104.model.layers.11.mlp.gate_proj.weight", + "model.layers.11.mlp.up_proj.weight": "p105.model.layers.11.mlp.up_proj.weight", + "model.layers.11.mlp.down_proj.weight": "p106.model.layers.11.mlp.down_proj.weight", + "model.layers.11.input_layernorm.weight": "p107.model.layers.11.input_layernorm.weight", + "model.layers.11.post_attention_layernorm.weight": "p108.model.layers.11.post_attention_layernorm.weight", + "model.layers.12.self_attn.q_proj.weight": "p109.model.layers.12.self_attn.q_proj.weight", + "model.layers.12.self_attn.k_proj.weight": "p110.model.layers.12.self_attn.k_proj.weight", + "model.layers.12.self_attn.v_proj.weight": "p111.model.layers.12.self_attn.v_proj.weight", + "model.layers.12.self_attn.o_proj.weight": "p112.model.layers.12.self_attn.o_proj.weight", + "model.layers.12.mlp.gate_proj.weight": "p113.model.layers.12.mlp.gate_proj.weight", + "model.layers.12.mlp.up_proj.weight": "p114.model.layers.12.mlp.up_proj.weight", + "model.layers.12.mlp.down_proj.weight": "p115.model.layers.12.mlp.down_proj.weight", + "model.layers.12.input_layernorm.weight": "p116.model.layers.12.input_layernorm.weight", + "model.layers.12.post_attention_layernorm.weight": "p117.model.layers.12.post_attention_layernorm.weight", + "model.layers.13.self_attn.q_proj.weight": "p118.model.layers.13.self_attn.q_proj.weight", + "model.layers.13.self_attn.k_proj.weight": "p119.model.layers.13.self_attn.k_proj.weight", + "model.layers.13.self_attn.v_proj.weight": "p120.model.layers.13.self_attn.v_proj.weight", + "model.layers.13.self_attn.o_proj.weight": "p121.model.layers.13.self_attn.o_proj.weight", + "model.layers.13.mlp.gate_proj.weight": "p122.model.layers.13.mlp.gate_proj.weight", + "model.layers.13.mlp.up_proj.weight": "p123.model.layers.13.mlp.up_proj.weight", + "model.layers.13.mlp.down_proj.weight": "p124.model.layers.13.mlp.down_proj.weight", + "model.layers.13.input_layernorm.weight": "p125.model.layers.13.input_layernorm.weight", + "model.layers.13.post_attention_layernorm.weight": "p126.model.layers.13.post_attention_layernorm.weight", + "model.layers.14.self_attn.q_proj.weight": "p127.model.layers.14.self_attn.q_proj.weight", + "model.layers.14.self_attn.k_proj.weight": "p128.model.layers.14.self_attn.k_proj.weight", + "model.layers.14.self_attn.v_proj.weight": "p129.model.layers.14.self_attn.v_proj.weight", + "model.layers.14.self_attn.o_proj.weight": "p130.model.layers.14.self_attn.o_proj.weight", + "model.layers.14.mlp.gate_proj.weight": "p131.model.layers.14.mlp.gate_proj.weight", + "model.layers.14.mlp.up_proj.weight": "p132.model.layers.14.mlp.up_proj.weight", + "model.layers.14.mlp.down_proj.weight": "p133.model.layers.14.mlp.down_proj.weight", + "model.layers.14.input_layernorm.weight": "p134.model.layers.14.input_layernorm.weight", + "model.layers.14.post_attention_layernorm.weight": "p135.model.layers.14.post_attention_layernorm.weight", + "model.layers.15.self_attn.q_proj.weight": "p136.model.layers.15.self_attn.q_proj.weight", + "model.layers.15.self_attn.k_proj.weight": "p137.model.layers.15.self_attn.k_proj.weight", + "model.layers.15.self_attn.v_proj.weight": "p138.model.layers.15.self_attn.v_proj.weight", + "model.layers.15.self_attn.o_proj.weight": "p139.model.layers.15.self_attn.o_proj.weight", + "model.layers.15.mlp.gate_proj.weight": "p140.model.layers.15.mlp.gate_proj.weight", + "model.layers.15.mlp.up_proj.weight": "p141.model.layers.15.mlp.up_proj.weight", + "model.layers.15.mlp.down_proj.weight": "p142.model.layers.15.mlp.down_proj.weight", + "model.layers.15.input_layernorm.weight": "p143.model.layers.15.input_layernorm.weight", + "model.layers.15.post_attention_layernorm.weight": "p144.model.layers.15.post_attention_layernorm.weight", + "model.layers.16.self_attn.q_proj.weight": "p145.model.layers.16.self_attn.q_proj.weight", + "model.layers.16.self_attn.k_proj.weight": "p146.model.layers.16.self_attn.k_proj.weight", + "model.layers.16.self_attn.v_proj.weight": "p147.model.layers.16.self_attn.v_proj.weight", + "model.layers.16.self_attn.o_proj.weight": "p148.model.layers.16.self_attn.o_proj.weight", + "model.layers.16.mlp.gate_proj.weight": "p149.model.layers.16.mlp.gate_proj.weight", + "model.layers.16.mlp.up_proj.weight": "p150.model.layers.16.mlp.up_proj.weight", + "model.layers.16.mlp.down_proj.weight": "p151.model.layers.16.mlp.down_proj.weight", + "model.layers.16.input_layernorm.weight": "p152.model.layers.16.input_layernorm.weight", + "model.layers.16.post_attention_layernorm.weight": "p153.model.layers.16.post_attention_layernorm.weight", + "model.layers.17.self_attn.q_proj.weight": "p154.model.layers.17.self_attn.q_proj.weight", + "model.layers.17.self_attn.k_proj.weight": "p155.model.layers.17.self_attn.k_proj.weight", + "model.layers.17.self_attn.v_proj.weight": "p156.model.layers.17.self_attn.v_proj.weight", + "model.layers.17.self_attn.o_proj.weight": "p157.model.layers.17.self_attn.o_proj.weight", + "model.layers.17.mlp.gate_proj.weight": "p158.model.layers.17.mlp.gate_proj.weight", + "model.layers.17.mlp.up_proj.weight": "p159.model.layers.17.mlp.up_proj.weight", + "model.layers.17.mlp.down_proj.weight": "p160.model.layers.17.mlp.down_proj.weight", + "model.layers.17.input_layernorm.weight": "p161.model.layers.17.input_layernorm.weight", + "model.layers.17.post_attention_layernorm.weight": "p162.model.layers.17.post_attention_layernorm.weight", + "model.layers.18.self_attn.q_proj.weight": "p163.model.layers.18.self_attn.q_proj.weight", + "model.layers.18.self_attn.k_proj.weight": "p164.model.layers.18.self_attn.k_proj.weight", + "model.layers.18.self_attn.v_proj.weight": "p165.model.layers.18.self_attn.v_proj.weight", + "model.layers.18.self_attn.o_proj.weight": "p166.model.layers.18.self_attn.o_proj.weight", + "model.layers.18.mlp.gate_proj.weight": "p167.model.layers.18.mlp.gate_proj.weight", + "model.layers.18.mlp.up_proj.weight": "p168.model.layers.18.mlp.up_proj.weight", + "model.layers.18.mlp.down_proj.weight": "p169.model.layers.18.mlp.down_proj.weight", + "model.layers.18.input_layernorm.weight": "p170.model.layers.18.input_layernorm.weight", + "model.layers.18.post_attention_layernorm.weight": "p171.model.layers.18.post_attention_layernorm.weight", + "model.layers.19.self_attn.q_proj.weight": "p172.model.layers.19.self_attn.q_proj.weight", + "model.layers.19.self_attn.k_proj.weight": "p173.model.layers.19.self_attn.k_proj.weight", + "model.layers.19.self_attn.v_proj.weight": "p174.model.layers.19.self_attn.v_proj.weight", + "model.layers.19.self_attn.o_proj.weight": "p175.model.layers.19.self_attn.o_proj.weight", + "model.layers.19.mlp.gate_proj.weight": "p176.model.layers.19.mlp.gate_proj.weight", + "model.layers.19.mlp.up_proj.weight": "p177.model.layers.19.mlp.up_proj.weight", + "model.layers.19.mlp.down_proj.weight": "p178.model.layers.19.mlp.down_proj.weight", + "model.layers.19.input_layernorm.weight": "p179.model.layers.19.input_layernorm.weight", + "model.layers.19.post_attention_layernorm.weight": "p180.model.layers.19.post_attention_layernorm.weight", + "model.layers.20.self_attn.q_proj.weight": "p181.model.layers.20.self_attn.q_proj.weight", + "model.layers.20.self_attn.k_proj.weight": "p182.model.layers.20.self_attn.k_proj.weight", + "model.layers.20.self_attn.v_proj.weight": "p183.model.layers.20.self_attn.v_proj.weight", + "model.layers.20.self_attn.o_proj.weight": "p184.model.layers.20.self_attn.o_proj.weight", + "model.layers.20.mlp.gate_proj.weight": "p185.model.layers.20.mlp.gate_proj.weight", + "model.layers.20.mlp.up_proj.weight": "p186.model.layers.20.mlp.up_proj.weight", + "model.layers.20.mlp.down_proj.weight": "p187.model.layers.20.mlp.down_proj.weight", + "model.layers.20.input_layernorm.weight": "p188.model.layers.20.input_layernorm.weight", + "model.layers.20.post_attention_layernorm.weight": "p189.model.layers.20.post_attention_layernorm.weight", + "model.layers.21.self_attn.q_proj.weight": "p190.model.layers.21.self_attn.q_proj.weight", + "model.layers.21.self_attn.k_proj.weight": "p191.model.layers.21.self_attn.k_proj.weight", + "model.layers.21.self_attn.v_proj.weight": "p192.model.layers.21.self_attn.v_proj.weight", + "model.layers.21.self_attn.o_proj.weight": "p193.model.layers.21.self_attn.o_proj.weight", + "model.layers.21.mlp.gate_proj.weight": "p194.model.layers.21.mlp.gate_proj.weight", + "model.layers.21.mlp.up_proj.weight": "p195.model.layers.21.mlp.up_proj.weight", + "model.layers.21.mlp.down_proj.weight": "p196.model.layers.21.mlp.down_proj.weight", + "model.layers.21.input_layernorm.weight": "p197.model.layers.21.input_layernorm.weight", + "model.layers.21.post_attention_layernorm.weight": "p198.model.layers.21.post_attention_layernorm.weight", + "model.layers.22.self_attn.q_proj.weight": "p199.model.layers.22.self_attn.q_proj.weight", + "model.layers.22.self_attn.k_proj.weight": "p200.model.layers.22.self_attn.k_proj.weight", + "model.layers.22.self_attn.v_proj.weight": "p201.model.layers.22.self_attn.v_proj.weight", + "model.layers.22.self_attn.o_proj.weight": "p202.model.layers.22.self_attn.o_proj.weight", + "model.layers.22.mlp.gate_proj.weight": "p203.model.layers.22.mlp.gate_proj.weight", + "model.layers.22.mlp.up_proj.weight": "p204.model.layers.22.mlp.up_proj.weight", + "model.layers.22.mlp.down_proj.weight": "p205.model.layers.22.mlp.down_proj.weight", + "model.layers.22.input_layernorm.weight": "p206.model.layers.22.input_layernorm.weight", + "model.layers.22.post_attention_layernorm.weight": "p207.model.layers.22.post_attention_layernorm.weight", + "model.layers.23.self_attn.q_proj.weight": "p208.model.layers.23.self_attn.q_proj.weight", + "model.layers.23.self_attn.k_proj.weight": "p209.model.layers.23.self_attn.k_proj.weight", + "model.layers.23.self_attn.v_proj.weight": "p210.model.layers.23.self_attn.v_proj.weight", + "model.layers.23.self_attn.o_proj.weight": "p211.model.layers.23.self_attn.o_proj.weight", + "model.layers.23.mlp.gate_proj.weight": "p212.model.layers.23.mlp.gate_proj.weight", + "model.layers.23.mlp.up_proj.weight": "p213.model.layers.23.mlp.up_proj.weight", + "model.layers.23.mlp.down_proj.weight": "p214.model.layers.23.mlp.down_proj.weight", + "model.layers.23.input_layernorm.weight": "p215.model.layers.23.input_layernorm.weight", + "model.layers.23.post_attention_layernorm.weight": "p216.model.layers.23.post_attention_layernorm.weight", + "model.layers.24.self_attn.q_proj.weight": "p217.model.layers.24.self_attn.q_proj.weight", + "model.layers.24.self_attn.k_proj.weight": "p218.model.layers.24.self_attn.k_proj.weight", + "model.layers.24.self_attn.v_proj.weight": "p219.model.layers.24.self_attn.v_proj.weight", + "model.layers.24.self_attn.o_proj.weight": "p220.model.layers.24.self_attn.o_proj.weight", + "model.layers.24.mlp.gate_proj.weight": "p221.model.layers.24.mlp.gate_proj.weight", + "model.layers.24.mlp.up_proj.weight": "p222.model.layers.24.mlp.up_proj.weight", + "model.layers.24.mlp.down_proj.weight": "p223.model.layers.24.mlp.down_proj.weight", + "model.layers.24.input_layernorm.weight": "p224.model.layers.24.input_layernorm.weight", + "model.layers.24.post_attention_layernorm.weight": "p225.model.layers.24.post_attention_layernorm.weight", + "model.layers.25.self_attn.q_proj.weight": "p226.model.layers.25.self_attn.q_proj.weight", + "model.layers.25.self_attn.k_proj.weight": "p227.model.layers.25.self_attn.k_proj.weight", + "model.layers.25.self_attn.v_proj.weight": "p228.model.layers.25.self_attn.v_proj.weight", + "model.layers.25.self_attn.o_proj.weight": "p229.model.layers.25.self_attn.o_proj.weight", + "model.layers.25.mlp.gate_proj.weight": "p230.model.layers.25.mlp.gate_proj.weight", + "model.layers.25.mlp.up_proj.weight": "p231.model.layers.25.mlp.up_proj.weight", + "model.layers.25.mlp.down_proj.weight": "p232.model.layers.25.mlp.down_proj.weight", + "model.layers.25.input_layernorm.weight": "p233.model.layers.25.input_layernorm.weight", + "model.layers.25.post_attention_layernorm.weight": "p234.model.layers.25.post_attention_layernorm.weight", + "model.layers.26.self_attn.q_proj.weight": "p235.model.layers.26.self_attn.q_proj.weight", + "model.layers.26.self_attn.k_proj.weight": "p236.model.layers.26.self_attn.k_proj.weight", + "model.layers.26.self_attn.v_proj.weight": "p237.model.layers.26.self_attn.v_proj.weight", + "model.layers.26.self_attn.o_proj.weight": "p238.model.layers.26.self_attn.o_proj.weight", + "model.layers.26.mlp.gate_proj.weight": "p239.model.layers.26.mlp.gate_proj.weight", + "model.layers.26.mlp.up_proj.weight": "p240.model.layers.26.mlp.up_proj.weight", + "model.layers.26.mlp.down_proj.weight": "p241.model.layers.26.mlp.down_proj.weight", + "model.layers.26.input_layernorm.weight": "p242.model.layers.26.input_layernorm.weight", + "model.layers.26.post_attention_layernorm.weight": "p243.model.layers.26.post_attention_layernorm.weight", + "model.layers.27.self_attn.q_proj.weight": "p244.model.layers.27.self_attn.q_proj.weight", + "model.layers.27.self_attn.k_proj.weight": "p245.model.layers.27.self_attn.k_proj.weight", + "model.layers.27.self_attn.v_proj.weight": "p246.model.layers.27.self_attn.v_proj.weight", + "model.layers.27.self_attn.o_proj.weight": "p247.model.layers.27.self_attn.o_proj.weight", + "model.layers.27.mlp.gate_proj.weight": "p248.model.layers.27.mlp.gate_proj.weight", + "model.layers.27.mlp.up_proj.weight": "p249.model.layers.27.mlp.up_proj.weight", + "model.layers.27.mlp.down_proj.weight": "p250.model.layers.27.mlp.down_proj.weight", + "model.layers.27.input_layernorm.weight": "p251.model.layers.27.input_layernorm.weight", + "model.layers.27.post_attention_layernorm.weight": "p252.model.layers.27.post_attention_layernorm.weight", + "model.layers.28.self_attn.q_proj.weight": "p253.model.layers.28.self_attn.q_proj.weight", + "model.layers.28.self_attn.k_proj.weight": "p254.model.layers.28.self_attn.k_proj.weight", + "model.layers.28.self_attn.v_proj.weight": "p255.model.layers.28.self_attn.v_proj.weight", + "model.layers.28.self_attn.o_proj.weight": "p256.model.layers.28.self_attn.o_proj.weight", + "model.layers.28.mlp.gate_proj.weight": "p257.model.layers.28.mlp.gate_proj.weight", + "model.layers.28.mlp.up_proj.weight": "p258.model.layers.28.mlp.up_proj.weight", + "model.layers.28.mlp.down_proj.weight": "p259.model.layers.28.mlp.down_proj.weight", + "model.layers.28.input_layernorm.weight": "p260.model.layers.28.input_layernorm.weight", + "model.layers.28.post_attention_layernorm.weight": "p261.model.layers.28.post_attention_layernorm.weight", + "model.layers.29.self_attn.q_proj.weight": "p262.model.layers.29.self_attn.q_proj.weight", + "model.layers.29.self_attn.k_proj.weight": "p263.model.layers.29.self_attn.k_proj.weight", + "model.layers.29.self_attn.v_proj.weight": "p264.model.layers.29.self_attn.v_proj.weight", + "model.layers.29.self_attn.o_proj.weight": "p265.model.layers.29.self_attn.o_proj.weight", + "model.layers.29.mlp.gate_proj.weight": "p266.model.layers.29.mlp.gate_proj.weight", + "model.layers.29.mlp.up_proj.weight": "p267.model.layers.29.mlp.up_proj.weight", + "model.layers.29.mlp.down_proj.weight": "p268.model.layers.29.mlp.down_proj.weight", + "model.layers.29.input_layernorm.weight": "p269.model.layers.29.input_layernorm.weight", + "model.layers.29.post_attention_layernorm.weight": "p270.model.layers.29.post_attention_layernorm.weight", + "model.layers.30.self_attn.q_proj.weight": "p271.model.layers.30.self_attn.q_proj.weight", + "model.layers.30.self_attn.k_proj.weight": "p272.model.layers.30.self_attn.k_proj.weight", + "model.layers.30.self_attn.v_proj.weight": "p273.model.layers.30.self_attn.v_proj.weight", + "model.layers.30.self_attn.o_proj.weight": "p274.model.layers.30.self_attn.o_proj.weight", + "model.layers.30.mlp.gate_proj.weight": "p275.model.layers.30.mlp.gate_proj.weight", + "model.layers.30.mlp.up_proj.weight": "p276.model.layers.30.mlp.up_proj.weight", + "model.layers.30.mlp.down_proj.weight": "p277.model.layers.30.mlp.down_proj.weight", + "model.layers.30.input_layernorm.weight": "p278.model.layers.30.input_layernorm.weight", + "model.layers.30.post_attention_layernorm.weight": "p279.model.layers.30.post_attention_layernorm.weight", + "model.layers.31.self_attn.q_proj.weight": "p280.model.layers.31.self_attn.q_proj.weight", + "model.layers.31.self_attn.k_proj.weight": "p281.model.layers.31.self_attn.k_proj.weight", + "model.layers.31.self_attn.v_proj.weight": "p282.model.layers.31.self_attn.v_proj.weight", + "model.layers.31.self_attn.o_proj.weight": "p283.model.layers.31.self_attn.o_proj.weight", + "model.layers.31.mlp.gate_proj.weight": "p284.model.layers.31.mlp.gate_proj.weight", + "model.layers.31.mlp.up_proj.weight": "p285.model.layers.31.mlp.up_proj.weight", + "model.layers.31.mlp.down_proj.weight": "p286.model.layers.31.mlp.down_proj.weight", + "model.layers.31.input_layernorm.weight": "p287.model.layers.31.input_layernorm.weight", + "model.layers.31.post_attention_layernorm.weight": "p288.model.layers.31.post_attention_layernorm.weight", + "model.norm.weight": "p289.model.norm.weight", + "lm_head.weight": "p290.lm_head.weight" +} \ No newline at end of file diff --git a/checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight b/checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight new file mode 100644 index 0000000000000000000000000000000000000000..20b258a8f4ed3838ccdf0f2856f394a482bb7271 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02880085a6e38c1508b165e4f9ef3153e547bfb05cbf8f726d19a65e7065f9d4 +size 524550933 diff --git a/checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0c8eb16eed51a54c2635fc4459810a65cab9770e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10221e79b0035ee43cc07cf312bdd69cf881b502237fba732cfd1e9273c3cd28 +size 67109756 diff --git a/checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..27e9f8ae58b22393c7cabbdba3db0ddef127c4ea --- /dev/null +++ b/checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464b67b02acbea78c2340bf435e7474eb44328ed97252bcd020ae489d39fc9d1 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..36db2204b75eb467c35c81bee070a223dbbcdbc0 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53538f84484c9be4371a6264905227458127bee342828873cc424521861ac16e +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..e18edf90d1c4ce006efb60cce580835d2979b517 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6540d8e6f3da9988e96d9a558cee61345de0d4d98aa799f604b614e9d5918062 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..45a68943ad3676bcf48e1c567d3f21f7d1334a85 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203d4ce65a1f37eda88d5a0aac20d068f149be796720fc325da53ce78a303bc9 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..060a661ce866a6b91319cd3246bc60bd39f7742b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8232d382b4395fa60a2da84e490b40c1174631aaed1bd9edeb4cfcc23c828a51 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..9107dda46ef8efa4f1b5bfa4f406580a370f0268 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e18b1d88233f2cfe1c32e2c6c779abb6585fc3ad075e0ede7d6e26cddf152f +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..e3075eb7656891e07f0ae9ece0ca667858b57988 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7fb2bd08b7ebcdb33343dd7a6a20b2d6ca8dcd402ad0b2fc13b92f73303110 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..fd4270c89d186c878419da3f04173343e1ade977 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be48a10aeadc6e2e2dcc80a412d0c5e93b452aeb611bf170ad65925ec7869bcc +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight b/checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..238ee843576326690b9ff92b7d857ddaab8e5a35 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..3c3efdd0816015bfea4f238f019d4ac79a7585f4 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..3a73ca9c73d17fea615b652d0f93e77865e5063f --- /dev/null +++ b/checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:303a5a7f56988887f59e760b46cc518cf78ea3116b90485a35de695c3dee6c9b +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0be3785eca187c156546314cd411c87dc2c1dad1 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e590f20e02bf77acf94cf8abbd5be10ce3f3ef64c1cd1cdb2e6604b0c153145 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..45afa49bc3737dd04235752546f24d3d11e560f1 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9cfa098c7af7a7aa1d3728df317769ff62fa3383344816804b0dfb8ed071cca +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..97a0f440afe11467c5f245916c77a67875d31478 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d533dde9a22ed9dd8c7b6bed804a5e75b945de2daeae015b3f7636c9393e06de +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c556be2db57e2e3839cbfc2654099bf850b7cb27 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f849dafaf04545f7a50b12cee0db9774393390a4749ba82e9f4dd37c71c4ff5 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..028d632a46f3f5d335f1d9ded285bb167a11af52 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ac59ea1df7d7679c9ea168b213484908a4cc658d542bf3bdb7e85e62b3f345 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p114.model.layers.12.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p114.model.layers.12.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..329aecd1a49870835dc11d9afe70ebbf8ad032b8 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p114.model.layers.12.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c58ca63a4e833deea410dfcdf636a7d795efe9b3ade2a84fbe314b2c2a08a78 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p115.model.layers.12.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p115.model.layers.12.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..21b341ab1d1a77726421200924f582fc16471798 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p115.model.layers.12.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5517810f148022484c3a5e7cbb5ffdd55ade0bee4417a0c6b60548b2910e30 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p116.model.layers.12.input_layernorm.weight b/checkpoint/pytorch_model.bin/p116.model.layers.12.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..29168a17c33e455cb0914fc8d176445e690db9cf Binary files /dev/null and b/checkpoint/pytorch_model.bin/p116.model.layers.12.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p117.model.layers.12.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p117.model.layers.12.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..68f0dc760e56d2a45641a3ec19f9c15a8150618e Binary files /dev/null and b/checkpoint/pytorch_model.bin/p117.model.layers.12.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p118.model.layers.13.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p118.model.layers.13.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..71a1270d68e27ed6041b77bc05e1149a5188e1d9 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p118.model.layers.13.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751f5eabcf39fcfdaaf1f3e26c468f60adb0aadb992ce790b223b87a62a0fd5d +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p119.model.layers.13.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p119.model.layers.13.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..67af75415acea99ca6004f008716bfddf0b728ac --- /dev/null +++ b/checkpoint/pytorch_model.bin/p119.model.layers.13.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc3d826e85df7d7ddef3a1cb0cccd2ca1ba321a002890a531daf18ef9e574611 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p12.model.layers.1.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p12.model.layers.1.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5a90a2db6a07c6805853a3eab10e3430c3e8dc9f --- /dev/null +++ b/checkpoint/pytorch_model.bin/p12.model.layers.1.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1565e7bf3d2e0269572c7928a48073b58dbf2518c800ec6d537078152fcbcbf8 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p120.model.layers.13.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p120.model.layers.13.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..23a497a96b43367e5ead1e3d9f592907e015cce9 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p120.model.layers.13.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2096ec196281a355b88ba76a5cccf9b373dec07684844014e5a5d4f04a550cd1 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p121.model.layers.13.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p121.model.layers.13.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c2605ebf65de450ff83ae74336c93a1d57605847 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p121.model.layers.13.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb8f0b0dcecf20df644c5031cb41ea55677e355b7c2b0166927d8fa5221f711 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p122.model.layers.13.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p122.model.layers.13.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..2ba0a521efbb1315b1e932f176fc68fdfa89e808 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p122.model.layers.13.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed320252c8ab6e54e64f0e54fcf5928ba6fa4cf3f4ceffa2a58f15cab1057e5 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p123.model.layers.13.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p123.model.layers.13.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..65a50b1d5d8686252c7f8160da5409feeeffaacc --- /dev/null +++ b/checkpoint/pytorch_model.bin/p123.model.layers.13.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a50aaa02d5693aebe3bf0006628c34929e0222daa9dcfb56c5457693618c189 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p124.model.layers.13.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p124.model.layers.13.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..202705fedf3864ef82802fa28f03d70719fe23a7 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p124.model.layers.13.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f703103d5294a7d996defdfb3d09231448dbb80168ccff74e752e1be31fdca +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p125.model.layers.13.input_layernorm.weight b/checkpoint/pytorch_model.bin/p125.model.layers.13.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..a1a3779d90dd158ce9dca6048b0663a1e4e7b1c0 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p125.model.layers.13.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p126.model.layers.13.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p126.model.layers.13.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..40a57bcbd3746949385c424958085ebf3722d010 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p126.model.layers.13.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p127.model.layers.14.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p127.model.layers.14.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a076a55326e4671fcd840b0f989c6d3c68fccf79 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p127.model.layers.14.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1454785a06a414ab868fa4aa84a3cb49581a1d60c96aecd71ed946315529d6ef +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p128.model.layers.14.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p128.model.layers.14.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..27ae7467c52a04d004c59562708c45ad5c6946a4 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p128.model.layers.14.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d73f85f6ca114d6d5010740e2786c9d5c740482e5b8faef2b015a2e7c874b069 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p129.model.layers.14.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p129.model.layers.14.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b52685f1cf8f28af768437cc735000a05d0555af --- /dev/null +++ b/checkpoint/pytorch_model.bin/p129.model.layers.14.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ed32b03396c84b0a14c087ed783e95e65d1a190dc343bc164c5a62f43655a3 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p13.model.layers.1.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p13.model.layers.1.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b3ae33cfca6aa507799eda659ae03be642354cae --- /dev/null +++ b/checkpoint/pytorch_model.bin/p13.model.layers.1.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36695b7cca0e880130649398e36cd28510e876e09d0d2479b29b20978da482b9 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p130.model.layers.14.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p130.model.layers.14.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..9c458366608c54900283e90644ae7397734b5132 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p130.model.layers.14.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2475fe4fd3c11925aed3f5a36ba59fccd03a3cea41be9e1031e45fdb7d245ea +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p131.model.layers.14.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p131.model.layers.14.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5db30446efe5d98e206079674b24bfb84593f9b2 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p131.model.layers.14.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541f90036057819b4638859b6f4521a017d8c09044686ed7d5b852066943fad6 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p132.model.layers.14.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p132.model.layers.14.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..ff0c56e68301904ef730c440b678df696beb5abd --- /dev/null +++ b/checkpoint/pytorch_model.bin/p132.model.layers.14.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594aaa937f6651909d6a7cd32ef1c5bc64b98e7cea688c1620baa4a17d74916b +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p133.model.layers.14.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p133.model.layers.14.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..9eb6acb58732db3ec2d6848bdbd96350a98d5715 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p133.model.layers.14.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ab861ba93f0be4698b74d77566dd0ad508105ca426c4906186f39e4bdf7b78 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p134.model.layers.14.input_layernorm.weight b/checkpoint/pytorch_model.bin/p134.model.layers.14.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..2e28987f4579cdc99432697b90b2deb458ff64a6 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p134.model.layers.14.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p135.model.layers.14.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p135.model.layers.14.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..b19869d4b200f9a08253f2c4b45b3a4956fd3785 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p135.model.layers.14.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p136.model.layers.15.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p136.model.layers.15.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6d1750754f177e4b422395ae8100811a135234bb --- /dev/null +++ b/checkpoint/pytorch_model.bin/p136.model.layers.15.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c6b114ecc96b11da2432d14be97e7a260f10e15e3901d8e6e06aa11fb8f206 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p137.model.layers.15.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p137.model.layers.15.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5a3b2db2dce0141faf464fee58f864d49ff8773b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p137.model.layers.15.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49bd83781289e7cd642bee7953a3aaf710b68efff593522d49907df7ef7f0725 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p138.model.layers.15.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p138.model.layers.15.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..4d286fe4f228d7d846ffc5773693667a0635b749 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p138.model.layers.15.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d8106c8c7ff26018511db6621c6312d61e3390dbd1466822c503c1659c1f408 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p139.model.layers.15.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p139.model.layers.15.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0a6223acb8ee7cb716e0cb783b57c09c5249fdc6 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p139.model.layers.15.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86069705039441356e06a68ec4b3ac70c31c3961fdb376b7ed40f75ea979529c +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p14.model.layers.1.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p14.model.layers.1.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..57a8687f52cd7375944c92075bfb5f76f8455deb --- /dev/null +++ b/checkpoint/pytorch_model.bin/p14.model.layers.1.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:516353f75d28e04cc7e6613c17e3c90053664d5b69071f729850476749d99925 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p140.model.layers.15.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p140.model.layers.15.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1b527e529b5dc13e8ee19fa7c9a9034c333619bc --- /dev/null +++ b/checkpoint/pytorch_model.bin/p140.model.layers.15.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281d6bc6a99b799684bb3a97e2fadec72bcd652999b9192923d19263cf199971 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p141.model.layers.15.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p141.model.layers.15.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..d92870ed57242b639b03f43318ffdab177d9106a --- /dev/null +++ b/checkpoint/pytorch_model.bin/p141.model.layers.15.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d35730c011aac75cec0a7b61ba23da8343896469a66c04cbf7e77ee71d9103 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p142.model.layers.15.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p142.model.layers.15.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c93840a1a384bd4d0c23d27c074ed9e91aaa7258 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p142.model.layers.15.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b44cd7f2b4863e6408ec28cf44baddae8f5f9e47dcd2499041db940bef3b73 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p143.model.layers.15.input_layernorm.weight b/checkpoint/pytorch_model.bin/p143.model.layers.15.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..2371661aa3915611b244c8c69c742ab99909fc6b Binary files /dev/null and b/checkpoint/pytorch_model.bin/p143.model.layers.15.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p144.model.layers.15.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p144.model.layers.15.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..eb5f7287de4c334eac6523a4c8deacc21b9c5752 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p144.model.layers.15.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p145.model.layers.16.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p145.model.layers.16.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..9237636b314b78d0573fc827bc3f517cbad40bd0 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p145.model.layers.16.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa369828850b08b99289ad6145b84f4b48f3a443d3c3c90e727a8fbec5f36c53 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p146.model.layers.16.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p146.model.layers.16.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..61a6d86f1ffc8254c032a89decdfec36434d0357 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p146.model.layers.16.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4389a25614e68284fd067132da40497497252ccb26bc9e08c7cf81216942950e +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p147.model.layers.16.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p147.model.layers.16.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1916495ed237ecdc3bbf666523390852d4fadd38 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p147.model.layers.16.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deeca9a9f90bca2729bfd077dd355057c700e28a73a6b473ef9b04e2ed869fd7 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p148.model.layers.16.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p148.model.layers.16.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c94a246d2f9e67a1ae3e467c297d4869b8cf2c9d --- /dev/null +++ b/checkpoint/pytorch_model.bin/p148.model.layers.16.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a118bdcb3dc159131ec0107270bdc36e6025506d2a66d3e18edc0ea62149c4e +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p149.model.layers.16.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p149.model.layers.16.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6738da13a7d407c355c84371508bf74596cc2b35 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p149.model.layers.16.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddaac1d3038b6b2d92025380ffe3219c56a6e82444235fcecc0b1c9659ceab96 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p15.model.layers.1.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p15.model.layers.1.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..ab876999771dff48e4abd960f531cbef056debd0 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p15.model.layers.1.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bfb8564d6f1c9da9a30ca6115bfb55e64439df999098031de4f0f98e50a7a4 +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p150.model.layers.16.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p150.model.layers.16.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..e2aa9c5b6b05b610b8da1617d627aba4eb3440d9 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p150.model.layers.16.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63bc92bb9e0e65f51c38666d56f5f7055823bb94efcaa55f21cbef67fcc9b677 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p151.model.layers.16.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p151.model.layers.16.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..7f7717500630ed749aa6ea69a1bd3a0301728650 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p151.model.layers.16.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f707f2e07f65bf939e2851ceabaec0d4dd50b2540af57c2a6a1b8a842e643ecf +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p152.model.layers.16.input_layernorm.weight b/checkpoint/pytorch_model.bin/p152.model.layers.16.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..54722df699743f8f75ce4b33a7733a8d39053304 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p152.model.layers.16.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p153.model.layers.16.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p153.model.layers.16.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..4a69a28955cb1b6c8c6c6acb2b152e3188c243da Binary files /dev/null and b/checkpoint/pytorch_model.bin/p153.model.layers.16.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p154.model.layers.17.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p154.model.layers.17.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6fc4ddacfdec7b08f1f485522293d0b4ad438d10 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p154.model.layers.17.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17fa8ce622f882b063ed4a81cd23d6f69fe190a72e4295aa5fe3d667a0bbae32 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p155.model.layers.17.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p155.model.layers.17.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..705d3de42bf2686ccedc09159409f4d275bc8a12 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p155.model.layers.17.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373d7037068634ddb54ddc3150d9ec2038cee897c38ee9ee4d44702882f534d8 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p156.model.layers.17.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p156.model.layers.17.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a7c8e87ed021d8bc1fd75f8ceab30603639e1d2b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p156.model.layers.17.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14a4074cc4cefa0ca33550e048f9032efacb033e1663353ac75dd13efbf8cf76 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p157.model.layers.17.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p157.model.layers.17.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b7c98ddcf1fb8893cac7010228357ce1915003aa --- /dev/null +++ b/checkpoint/pytorch_model.bin/p157.model.layers.17.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c49455eafd4fafb2c0056f0a18de82a69f8c703b785f718bc8d733e6ea3d05 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p158.model.layers.17.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p158.model.layers.17.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..149e46daf4810e24359cb7bc8f785d6e5e7251b8 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p158.model.layers.17.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a37bd3157d8c7da781894a4ebabd590f0883854a690dfc8fcd42f229b9d75a9 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p159.model.layers.17.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p159.model.layers.17.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..e8c32d413a848daef1c0a996d183158a07e60911 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p159.model.layers.17.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d5d5d9f188e53fefe29b5801b746def85fdbefbfbb86c9ee45748240fc9c6a +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p16.model.layers.1.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p16.model.layers.1.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..d2b8d52e69a8f262f45a6a34e4ee767e19e09838 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p16.model.layers.1.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ced61bc43ac6cd2f94543f14db73b190c165814c60ef798f9a781c8c7b1cdf +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p160.model.layers.17.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p160.model.layers.17.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..174e8d5e78c167735600781ccced487d83b80f86 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p160.model.layers.17.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86190d1a40080403d28eb40a7e96913d9e1e48f4998018b9fa81ddf8288e684e +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p161.model.layers.17.input_layernorm.weight b/checkpoint/pytorch_model.bin/p161.model.layers.17.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..d0e4718b9410aaebc1d84277acf6634f47a6a311 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p161.model.layers.17.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p162.model.layers.17.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p162.model.layers.17.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..1bd0198399cd640ace449e38e9d8e9d67deb7daa Binary files /dev/null and b/checkpoint/pytorch_model.bin/p162.model.layers.17.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p163.model.layers.18.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p163.model.layers.18.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..f5a72e11cfe2328d9d9cad3edc59ed52588f87fc --- /dev/null +++ b/checkpoint/pytorch_model.bin/p163.model.layers.18.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c132d946183131160102f2aade2021a6ec4e9186ae05ee85ce332ca598339619 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p164.model.layers.18.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p164.model.layers.18.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..34421dc0e00054c011c2b6ed2145e8f53254e559 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p164.model.layers.18.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbef6d1f7784bddc0e2322850d67b4726551e8d40c06898621af7150bc644912 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p165.model.layers.18.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p165.model.layers.18.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..d8b22a8d8bc3a8275e18eda67ae19f2cb671f5a2 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p165.model.layers.18.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:216b73287b5827f8ab7a6cd76cfe502206b1559fd6cee7291eb9ecf2cc7fde1d +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p166.model.layers.18.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p166.model.layers.18.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c48ff146c8323d3fda7cf692cc07d8bcddf4ed0f --- /dev/null +++ b/checkpoint/pytorch_model.bin/p166.model.layers.18.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3f1132b3073f58e84b9ebdc1cfb74212a6d44caa67ead1290730cc92691d83 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p167.model.layers.18.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p167.model.layers.18.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..31f2091c0ee5be877260f2efe13bdc44efbd9552 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p167.model.layers.18.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb2be9716f22fc6f073472f3b5ca12fb10cc50fb7139d3b7bcf023afabd43ffb +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p168.model.layers.18.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p168.model.layers.18.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c0f32ac3000b13c2aed03277f1a2d718b4f96385 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p168.model.layers.18.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e3f78334d704fd94e83aeceb09232442615bdd2193d4d45d1fde9fd61e76240 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p169.model.layers.18.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p169.model.layers.18.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5d3b936a6ba6c1625a848554a908a0ef22d437c2 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p169.model.layers.18.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2ea4c034bae3e302c117d7255a8eb977eae06480f7e002881553b02e9268aa +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p17.model.layers.1.input_layernorm.weight b/checkpoint/pytorch_model.bin/p17.model.layers.1.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..0231339ee9f2bee11af5473b5b8a1a787c128da5 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p17.model.layers.1.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p170.model.layers.18.input_layernorm.weight b/checkpoint/pytorch_model.bin/p170.model.layers.18.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..120d03971c351a667e3989f5621859c30f74b929 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p170.model.layers.18.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p171.model.layers.18.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p171.model.layers.18.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..0c7bc24ba1ba2645481f255f741ee29eb8bd8062 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p171.model.layers.18.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p172.model.layers.19.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p172.model.layers.19.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..acacb08fc866ac9a065379220f1ea345f369827d --- /dev/null +++ b/checkpoint/pytorch_model.bin/p172.model.layers.19.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c6bf5226a8eeefdf8557bdaf5323c3f61a44985833d705e3014c37f3bb589d5 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p173.model.layers.19.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p173.model.layers.19.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..f0acb772d57ca87b70378560b1232c64f50e8f6a --- /dev/null +++ b/checkpoint/pytorch_model.bin/p173.model.layers.19.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d373d69e5a7f4f80fb2ab07f921858446d78131a120d1b0b150d2c7265fadaab +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p174.model.layers.19.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p174.model.layers.19.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..93e4191e718b8254fba9eb8e1cfc2a5492936855 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p174.model.layers.19.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f173fdb2cc791a49a4ed918061d4e0fc8590e27a3863556d597f85a9072fa994 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p175.model.layers.19.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p175.model.layers.19.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..998b69c32c2021e8786885755b29f22db0afe0ad --- /dev/null +++ b/checkpoint/pytorch_model.bin/p175.model.layers.19.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4f55b8794763516db442b0414881e09f3f6c7677b4c3b24031e4e7c1135220 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p176.model.layers.19.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p176.model.layers.19.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0556e16e7c5db94eb01e70e89a6a8b02e1a92f32 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p176.model.layers.19.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74aabb9caaa2fd68f349767472cf3ff7d5de514197caf4461ff5cce5de00af66 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p177.model.layers.19.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p177.model.layers.19.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..4ea4e8de9efdc36090e5fa2644e32f2c0225cccb --- /dev/null +++ b/checkpoint/pytorch_model.bin/p177.model.layers.19.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d592f6bf437fc3c414422bc2d2712619cf598388b004e0df864816a929e232e0 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p178.model.layers.19.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p178.model.layers.19.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..afebcaa9e0bfc3ddb816e033b19be08518156bed --- /dev/null +++ b/checkpoint/pytorch_model.bin/p178.model.layers.19.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eac103a44f2cd9cb4c9256ff838f53dfa3e9f1c1686c3e94196d7f01fa98100 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p179.model.layers.19.input_layernorm.weight b/checkpoint/pytorch_model.bin/p179.model.layers.19.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..e0bf26395db0d2e095fdbcc25d9cd1cb94510dd7 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p179.model.layers.19.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p18.model.layers.1.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p18.model.layers.1.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..41c5d3d1ac12c1eacdb6b18505eb2db7514ae367 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p18.model.layers.1.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p180.model.layers.19.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p180.model.layers.19.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..99e72c24c2ceb35bcf9ed52d615729ddd78dfaa3 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p180.model.layers.19.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p181.model.layers.20.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p181.model.layers.20.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..73f3ace941846a861be89d9f18e5c2ea96dd6f2e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p181.model.layers.20.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d64d904bfa924c0e6d79e4c7476a046722157a9d18c9b61f8552d76a37c513e +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p182.model.layers.20.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p182.model.layers.20.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b08deedef2fb712cdf9b834df242efb21ba13169 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p182.model.layers.20.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc57594dfd838b87922cc38edd637b75d1c6e107349577e3df7504a2496aed78 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p183.model.layers.20.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p183.model.layers.20.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..d6c34ff70d3c05a8d1ff80fc39f58983c44cb629 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p183.model.layers.20.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141c672982dc5cc1d127604727b5fe18c57361f01940e6d6217dd6f2515ebe45 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p184.model.layers.20.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p184.model.layers.20.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..2143423ea350b959d1947d4994f486ce03835b04 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p184.model.layers.20.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4474b78f21705d29fe49e2c8e74091cf2193eb9b3b49e31c4c6330ff3a3696fe +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p185.model.layers.20.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p185.model.layers.20.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b8ca7f2d20eb12373834c196d464a2052a35462b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p185.model.layers.20.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879a5499d9efe4d58f70048db559bcc79c5b072b969df8fe8e288ee95a6922a4 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p186.model.layers.20.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p186.model.layers.20.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0973cb8da8108a31ff77fbb5330411bcea11551a --- /dev/null +++ b/checkpoint/pytorch_model.bin/p186.model.layers.20.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351a547f86b3f21cb5973b48f26e64aff03b9f31042d86bc5d5d27732db3946b +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p187.model.layers.20.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p187.model.layers.20.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..d984b48e563d472e1487a9d9307cd842ae187cb2 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p187.model.layers.20.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968017cad844d149320ecc7de0448361a0772ecbcd7a78a1cd550108b7bf5a66 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p188.model.layers.20.input_layernorm.weight b/checkpoint/pytorch_model.bin/p188.model.layers.20.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..88b1212aac7b233c3a44f97194eb4fc85ad92cad Binary files /dev/null and b/checkpoint/pytorch_model.bin/p188.model.layers.20.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p189.model.layers.20.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p189.model.layers.20.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..fae5b193ec286bb36b9e27d80b66d52458795938 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p189.model.layers.20.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p19.model.layers.2.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p19.model.layers.2.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1308334116641d0a07b7f2e4b76cf5def8b13866 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p19.model.layers.2.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b18f55a997a168e5e18015908d13d9356af0790b015d801452b85e71a613d81e +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p190.model.layers.21.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p190.model.layers.21.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..68bd3fdb53f6b1cf6334dc889110481b4c50744e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p190.model.layers.21.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96f7f955f0e069be95c497de0fe5f9aab1720e6cb1fa32173bcb38594189b1d +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p191.model.layers.21.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p191.model.layers.21.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..188451a219bf5e55a5bc2d43611ced37fa71f5de --- /dev/null +++ b/checkpoint/pytorch_model.bin/p191.model.layers.21.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19383336ec0f1d7b78365d9bb08b0f3843515fe65e7ea8e5b08cd501bdad7b0 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p192.model.layers.21.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p192.model.layers.21.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5ee8d4921fcd843b0aa5c3616a3e1ada022a0090 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p192.model.layers.21.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6656a5f2b9d8cdf1b28f3a686a212c99c033af892a8fd25e893344d76d812b32 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p193.model.layers.21.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p193.model.layers.21.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..3f26fbc70722be887fc7312b99a88da1e36bd09a --- /dev/null +++ b/checkpoint/pytorch_model.bin/p193.model.layers.21.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:118e5f360fe3d492d9be5691be2fd923f2524822f67ee3d574d445454d69ca66 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p194.model.layers.21.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p194.model.layers.21.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..92fe6bc003cb88867563bbf75e696f8cf4dc734b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p194.model.layers.21.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e74e4668e10b6c4366a13fe9bef7d5718931103a0d12239ffaf8c40cc912ff +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p195.model.layers.21.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p195.model.layers.21.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..2d140080a43a5d66fd8af2efb8275f27618f4298 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p195.model.layers.21.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47e1de31545969433cdf7663937c96a8169d4a6128696eb7f814b1c6cb59f033 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p196.model.layers.21.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p196.model.layers.21.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..76970f514c94cab0625cffa4f33fcb0791027434 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p196.model.layers.21.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea62c97d63fce41dc0b45d4bf5b10d692962237d589780d8969e8cbce3aec5eb +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p197.model.layers.21.input_layernorm.weight b/checkpoint/pytorch_model.bin/p197.model.layers.21.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..df4b42dd38f8a305e0db9b5ea2082fe235919218 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p197.model.layers.21.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p198.model.layers.21.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p198.model.layers.21.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..89cf2832361d4188cf9f5c9a2f14b525bb90cf90 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p198.model.layers.21.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p199.model.layers.22.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p199.model.layers.22.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..f011db35a8534d88cca2258eddbc48e225421248 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p199.model.layers.22.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91fb8f666e420f0ff831a51382a17446447aca2e06c0dc43271b037419e3e3e +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p2.model.layers.0.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p2.model.layers.0.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..425006d462801db5d2ae80b543835ccf3c89caae --- /dev/null +++ b/checkpoint/pytorch_model.bin/p2.model.layers.0.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630162204c93f7b3bfa770d0a011195660468bc95e341bf3e4642ab9c42897cc +size 67109756 diff --git a/checkpoint/pytorch_model.bin/p20.model.layers.2.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p20.model.layers.2.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..68d644dae9b76eee728da6375a2d5d68d795d56b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p20.model.layers.2.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22cf1146a9f8541413368d540d543c9a1254822eea779768875e7d8f82bff074 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p200.model.layers.22.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p200.model.layers.22.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1bf9a4cd56d987f5306d8d7b1f9d1b88c9d57d7b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p200.model.layers.22.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f212720fab96f4e69ec745ce6c9054267e52c7b0c9db09614e2ae24a107158 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p201.model.layers.22.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p201.model.layers.22.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..ef27b33f491d6216fe36382c64edaf7b545047a9 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p201.model.layers.22.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:638a182a60994abe7a62e83d592f951a9c1c613a317fb81fdbd03be281ebe179 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p202.model.layers.22.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p202.model.layers.22.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5932ca27382fb71673d6821c948b2c565cf3d36e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p202.model.layers.22.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ae582695f7a8eaaa9f734d956dbb33c6133810357d71a0f010b360d94e6550 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p203.model.layers.22.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p203.model.layers.22.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1c1b57f1defd0740c689cb6634f983ee9205ead1 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p203.model.layers.22.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39f8419a06d038a022d52d1023576dc6043c2e9c1b76aa92306087a70a439e08 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p204.model.layers.22.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p204.model.layers.22.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b676ef4f42d3c62da43b4ded2f0dd8ea43549931 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p204.model.layers.22.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39eea1e54cf7b5630d11d21fff294a9c78a73a7b33fc0fb29ce0f30b8958e4ff +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p205.model.layers.22.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p205.model.layers.22.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a5ef16950758b605083bae5ca0e9ce16da64ddea --- /dev/null +++ b/checkpoint/pytorch_model.bin/p205.model.layers.22.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5142450f478bdc82a4428722184677d1caca1b08d13c6ff916fceb0505936e00 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p206.model.layers.22.input_layernorm.weight b/checkpoint/pytorch_model.bin/p206.model.layers.22.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..9294197c478bda504b78fd393dbd6e0840b5289e Binary files /dev/null and b/checkpoint/pytorch_model.bin/p206.model.layers.22.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p207.model.layers.22.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p207.model.layers.22.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..f836711249ca6236a4c786d0d676f03e9cc7a332 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p207.model.layers.22.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p208.model.layers.23.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p208.model.layers.23.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1892ea7e06e96fbe6d34f51ecc0929b5352afa6e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p208.model.layers.23.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd336de7de0c0b2c75379fc382be1f8b910cc1ab8d054740d26f0f939b7e54c +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p209.model.layers.23.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p209.model.layers.23.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..fb6f90b5d805dd01181fae28f66a92f6150519bc --- /dev/null +++ b/checkpoint/pytorch_model.bin/p209.model.layers.23.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2e76f2cf324b211529e5730529d397cd219ee28be29ae66a06e8e0bf61bd0ab +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p21.model.layers.2.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p21.model.layers.2.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5560d1cd584624388c2225358e950199e158f6b9 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p21.model.layers.2.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:073a9d93ee6aa69057419456d8dbb5ddb7cdfd504190f03f2becff3549c81428 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p210.model.layers.23.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p210.model.layers.23.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..ebcc557589e14f011e7315321d345e508ca631cb --- /dev/null +++ b/checkpoint/pytorch_model.bin/p210.model.layers.23.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b5376afdace9f579421acfa771cfa3221d66e9226029a1750d4023026bb5d5 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p211.model.layers.23.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p211.model.layers.23.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a2b6be29ab1decb67d79e084cf5b397b70d5c49c --- /dev/null +++ b/checkpoint/pytorch_model.bin/p211.model.layers.23.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4049afa95b9af27e0c6ac4eb5c8f440faeac592c37e9cf9345dec1de6b2398f4 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p212.model.layers.23.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p212.model.layers.23.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..8a33043cc291fde877fa7230b45590510e713da9 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p212.model.layers.23.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac2a3835c01e13e2a54d5069d9a612625941b6522ff419559dcdc90c426b6a6 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p213.model.layers.23.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p213.model.layers.23.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..4f8da7a1fda9dff11d554247d6b06a0aaf78783e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p213.model.layers.23.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb48ae67d902ac5393e8f3cdc2c72d0012b2217519da613bb9252896464f8d87 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p214.model.layers.23.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p214.model.layers.23.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..20618ff8501e6ca26bae275195e2ce024d00c7c7 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p214.model.layers.23.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d67b3ff3d96bb083005a8816a3c9ce4c8d7988e572334b71a10ee016f2fa9cb +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p215.model.layers.23.input_layernorm.weight b/checkpoint/pytorch_model.bin/p215.model.layers.23.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..5dd4ecfb44c1fe64d45d3eb00780d08a88703bf9 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p215.model.layers.23.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p216.model.layers.23.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p216.model.layers.23.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..3b31c96c0bfa4f586385288dd322408aea2406eb Binary files /dev/null and b/checkpoint/pytorch_model.bin/p216.model.layers.23.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p217.model.layers.24.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p217.model.layers.24.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5fb6e29a2622b16da39128fde2bd885e87283088 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p217.model.layers.24.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fade3403cbe8c70787b950b80ab964360f9c099ea654f1687d3c1786ec670a0c +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p218.model.layers.24.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p218.model.layers.24.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..036de867c8d1b6e1dc28acc60f6fbe92cef36e7b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p218.model.layers.24.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d72fe6b3600c4e850ebbe420ce7e73d41cdf0d2c08f9e52334e7a016e09c91d +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p219.model.layers.24.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p219.model.layers.24.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..98097bdb8b604d5bc3fa3d32d93780c8a11159d8 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p219.model.layers.24.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e01d2e2cfcf511dc0d69f58f011b09f1e83391c7644a126c55705d6f7cabb961 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p22.model.layers.2.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p22.model.layers.2.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6a834a5a0badd58cbc8832be861ea6df9fec1ba3 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p22.model.layers.2.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e683d8a1a9e6fd659312293fee8c872ea01dba466a816c9a05af1df66fc7df +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p220.model.layers.24.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p220.model.layers.24.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..3922187f34c41edaa516d4aefeab7f7afaba5cba --- /dev/null +++ b/checkpoint/pytorch_model.bin/p220.model.layers.24.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c12cae15d381894c2c55e00d761c63d2025cb78af74b793cd9d971afc3c244ca +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p221.model.layers.24.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p221.model.layers.24.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..120c8d3171ee648a3d389997a6906d3d66cbcc0f --- /dev/null +++ b/checkpoint/pytorch_model.bin/p221.model.layers.24.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95cf2660a6535d005204dc8f22bd3d90c429bd434a808c73bc202242fd044885 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p222.model.layers.24.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p222.model.layers.24.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..d615c4a58acf64fc52bf0f29f9f414fdc038c788 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p222.model.layers.24.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d5def0353de9c293f2cfdc3a20a5b870722c2055817f209ef2a36c3772c698 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p223.model.layers.24.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p223.model.layers.24.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a7aecab6d6f3e0639b1afef579838c55c1e57c85 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p223.model.layers.24.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c00425ba5583086bb4f5b2bb9069a6d6e6b6fc4ceadf84b5864611128277944 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p224.model.layers.24.input_layernorm.weight b/checkpoint/pytorch_model.bin/p224.model.layers.24.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..f9a26c23dc941d3b1769376d58e036760cd6d2df Binary files /dev/null and b/checkpoint/pytorch_model.bin/p224.model.layers.24.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p225.model.layers.24.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p225.model.layers.24.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..459625b4d7f5cdf03cf98e25dc2dc09780e8f0af Binary files /dev/null and b/checkpoint/pytorch_model.bin/p225.model.layers.24.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p226.model.layers.25.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p226.model.layers.25.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6cce5696b626a7018aeb7904dcc4418b9f866e65 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p226.model.layers.25.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4192a8c286f9b29e1e073d21e9c2d8314904690ec2ff8d3da6af80531f6c89d0 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p227.model.layers.25.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p227.model.layers.25.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..ad51e2f10369fe7e99315be16e6b5227bd04f03c --- /dev/null +++ b/checkpoint/pytorch_model.bin/p227.model.layers.25.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:471d26db2975c320ba0708d408c69eae38008a469227fd68cd70b73e183a1822 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p228.model.layers.25.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p228.model.layers.25.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b265873192c5e6842312692851f7d2b1adf26b71 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p228.model.layers.25.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c152821ea0c13b3ed58291beae295936cf05f7179dab973ef0ce273fba7bdda2 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p229.model.layers.25.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p229.model.layers.25.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..f551bf57f35b96ff6d1fd496ed14ef821ec9afb2 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p229.model.layers.25.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f76ff70202e35818493efadc900c75d93d5c41cd0f947faa1a2870f2b3d9ac2d +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p23.model.layers.2.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p23.model.layers.2.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..110f425ea428c5578635664bbf1b1f8df5f4da08 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p23.model.layers.2.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45af21eb996b211e3fb7794b78a7503ab054a5af5857ceaf9a54a5f9c95f1883 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p230.model.layers.25.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p230.model.layers.25.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c3fd9e08011c91258199b9917956da831d582e1c --- /dev/null +++ b/checkpoint/pytorch_model.bin/p230.model.layers.25.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda9893eb150d26991faa0b3222a2f01b99f82a623ebd1f9bcc45dbd390915ae +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p231.model.layers.25.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p231.model.layers.25.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..7161496105a363522156b761f5535ea3068a3ed1 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p231.model.layers.25.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb5ef10235b6192fba54b64fccacff17ae73fe9409c7375d7ab995a31731222 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p232.model.layers.25.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p232.model.layers.25.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..15c3116d3f6102c4d5037e76b13a2036bb4bdebe --- /dev/null +++ b/checkpoint/pytorch_model.bin/p232.model.layers.25.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d985c0273d4f145623f974d47777b2e2314296571b520991289a4fc3941a4c6e +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p233.model.layers.25.input_layernorm.weight b/checkpoint/pytorch_model.bin/p233.model.layers.25.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..5b0f1d6a1dfb8e33699422fd4b189e2cc543817c Binary files /dev/null and b/checkpoint/pytorch_model.bin/p233.model.layers.25.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p234.model.layers.25.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p234.model.layers.25.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..c3145481ad873fc572ae8b6788b0020e559c82b0 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p234.model.layers.25.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p235.model.layers.26.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p235.model.layers.26.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..860e5350cd10dbafde59809d365434d2b1716153 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p235.model.layers.26.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87ef2ac3518810fdee9cd43150ab2857b7d5f7e5425b0da2fec0c5119d1b7626 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p236.model.layers.26.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p236.model.layers.26.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b4aa30f26209b6889750ee0b429f9afad6877fbc --- /dev/null +++ b/checkpoint/pytorch_model.bin/p236.model.layers.26.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2d0e2c2c40901ec7044e8b9589fa680b6576b6fb9cd26943771fd1db782830d +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p237.model.layers.26.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p237.model.layers.26.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..8a9f3063a7108664f71e45870b921fcd3100f36f --- /dev/null +++ b/checkpoint/pytorch_model.bin/p237.model.layers.26.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8d7a2940e651a8a323a8872f615ae8f81d286bcec10fd821666e8f915e82b4 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p238.model.layers.26.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p238.model.layers.26.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..011d2ee939a782ee686b95807bd6841e874d5909 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p238.model.layers.26.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becb9e6c87d3b90c0f0ebdd3b6d1d04ac751f8941f8be9d8cf1848cd9421ebfd +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p239.model.layers.26.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p239.model.layers.26.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c5f4f31d00e950bcf2514955996765174438fae5 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p239.model.layers.26.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1261a5d9601a34d0b29e3834b00a8a6cbae26cf0b69e891edd49c1ea6bc72be9 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p24.model.layers.2.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p24.model.layers.2.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c883f5889d36974c0d4bac80927a30d1b2c5b7b1 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p24.model.layers.2.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba93a1a9d1c73723c8940ad779084385c9e1769646d480fca73c16f205f97caf +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p240.model.layers.26.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p240.model.layers.26.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..cc04e8f53f6e83cf89494d9d896e39a80dcb7283 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p240.model.layers.26.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe32da0dd6520859a5b13e02217ab07149216eacfa9cc992c712d3d47f8061c2 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p241.model.layers.26.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p241.model.layers.26.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a34752f1039503dc3a37fba3504577d52ed4d10c --- /dev/null +++ b/checkpoint/pytorch_model.bin/p241.model.layers.26.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a09256c2b3fec284d269129cc3665534eabc0d5a780a68a3b63b5164ef7e6d +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p242.model.layers.26.input_layernorm.weight b/checkpoint/pytorch_model.bin/p242.model.layers.26.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..25e09083460e1b0ad1545441ddb63fab26747e49 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p242.model.layers.26.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p243.model.layers.26.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p243.model.layers.26.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..90704a261d90f9ad0e911e00c4cafb182ca3f1a1 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p243.model.layers.26.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p244.model.layers.27.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p244.model.layers.27.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1c2c8eabf6b73efb30fab2099ef66913e5d37f22 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p244.model.layers.27.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b2bc27e7b061460dc9cdf59ece2675489251eb1e242a81da377b78e6d4562e5 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p245.model.layers.27.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p245.model.layers.27.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1a219376e393f3980e08e8317d3f924d70f01412 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p245.model.layers.27.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce8fe097a22a145476de5e47fa51b5546c07c4b7d84cadd94d12989d12adc55 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p246.model.layers.27.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p246.model.layers.27.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..d43f0dd639e6c6546e9adc9ac9c1048452db01e8 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p246.model.layers.27.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0c7443175e9242e3dda91b7310276269f057e09d50b038de84ce6068f0e83f +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p247.model.layers.27.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p247.model.layers.27.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c0a0d4393fd040c2fe1e5c2ea4cfb8de0c76f11a --- /dev/null +++ b/checkpoint/pytorch_model.bin/p247.model.layers.27.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10afcd16bda7eedc0b8e26b48d317ffe7c8ff6e8cc9ce32c7be4516cef4360d9 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p248.model.layers.27.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p248.model.layers.27.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..fd2e009cb9dbdb3b23c973cf54dd4ff1fe005f09 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p248.model.layers.27.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:038cc46142d72b0e8706e772e561c50bea101c15f0319e563c0b6cdcb7549472 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p249.model.layers.27.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p249.model.layers.27.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b3149151a35d73d29f3618c202c930540f82236b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p249.model.layers.27.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac31d8ffc24b37fbce91c9571e6686a12721d1578acd483618552fed8618e04 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p25.model.layers.2.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p25.model.layers.2.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0b078c16cba1efea43fe692f2277974b9945ae93 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p25.model.layers.2.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11414811f81be8d576098c1efc3f50cc37588af6eeb098cdd1e612fb76e74ca +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p250.model.layers.27.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p250.model.layers.27.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b7db76a2d4c8b1119ae57404ac0212f8620d16e7 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p250.model.layers.27.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d746fd5d034f32ce21032f3f94b7acb096dcac4bbc997ac3727ba1bf057d19bf +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p251.model.layers.27.input_layernorm.weight b/checkpoint/pytorch_model.bin/p251.model.layers.27.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..2c0d84e04475eaa4910231570a89c1402c85aa3f Binary files /dev/null and b/checkpoint/pytorch_model.bin/p251.model.layers.27.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p252.model.layers.27.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p252.model.layers.27.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..7f3a3f126c7f1baa75480f61c21bd7a121ef17a3 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p252.model.layers.27.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p253.model.layers.28.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p253.model.layers.28.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0b89707daa543a8698f8d234ea05d7097d9a334c --- /dev/null +++ b/checkpoint/pytorch_model.bin/p253.model.layers.28.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee1c316dc190ed591d0b8066916cd68c7ed7177eba6a88c0b565e8c90fa4e2b8 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p254.model.layers.28.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p254.model.layers.28.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b21d749c5dee2198f6480eff97e92bb0ec231e8e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p254.model.layers.28.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c4f81dad8e37da0107090061ad4753f1f0f3a7d123b744816d2ca4e2c30b7c +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p255.model.layers.28.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p255.model.layers.28.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c53550256cb93c20f2c310524456dc464ec98ed0 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p255.model.layers.28.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:813d861e16a035a2ffe4ed17fe2ecf7c4d10e70d112c2c05940acf5ad16fc399 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p256.model.layers.28.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p256.model.layers.28.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..265b576c29c807600f87db9bf11ffd765d8a0b6c --- /dev/null +++ b/checkpoint/pytorch_model.bin/p256.model.layers.28.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb83f8ab3af06560af0422fea0c90be26e2f1338313babda9b77f3cb559c133d +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p257.model.layers.28.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p257.model.layers.28.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5234faa5a03265184556c7772569f67f461e63c4 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p257.model.layers.28.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff176fe384f7b5ce2c7c3ecf61e7e1e8aa259d3fdc5c5fc826614302bd5a6f5 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p258.model.layers.28.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p258.model.layers.28.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..518093ac16f7a2929024f449afed2999e9dc6443 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p258.model.layers.28.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4552bbcd35a668e0d4bdec61b60f69ab1ca2919ca32511566a372101b4f5331 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p259.model.layers.28.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p259.model.layers.28.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..72dd5c63dfc006394a775c058d61030731e93880 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p259.model.layers.28.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2e9f3e4f77188bcffb41c16edc71f347c1e2c067bbb8174c041f3e52fd88cd +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p26.model.layers.2.input_layernorm.weight b/checkpoint/pytorch_model.bin/p26.model.layers.2.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..d8597e715ba9b629744295571049bbd3d15b8908 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p26.model.layers.2.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p260.model.layers.28.input_layernorm.weight b/checkpoint/pytorch_model.bin/p260.model.layers.28.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..cf3c2f51e9fdc19804dc892064facfc6422c9b0b Binary files /dev/null and b/checkpoint/pytorch_model.bin/p260.model.layers.28.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p261.model.layers.28.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p261.model.layers.28.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..1c204794fa76efcfa964fb820e9966267c2ec8d6 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p261.model.layers.28.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p262.model.layers.29.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p262.model.layers.29.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6ac2693c5d1dd191d8879d7e0c097e1b2fdece88 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p262.model.layers.29.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be570d179045ba344f6f45258576733aa7df187d5557db973f4b11a8b3205599 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p263.model.layers.29.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p263.model.layers.29.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..2f70cbff75f59babc0c0676553de664c6067d434 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p263.model.layers.29.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7ece8858c13644ea983c8927d352a451dccd05d930a8f7d5be0773e7d5ff8a +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p264.model.layers.29.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p264.model.layers.29.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..e5ec918b27c2cbf2f1aa2c7754f2b51bf14baef6 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p264.model.layers.29.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ece12e729ef23392525eda319fc8da3381d3992def627c7d756fb66ce3f1f7 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p265.model.layers.29.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p265.model.layers.29.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..bd27c0b63954e7a8f4bbdd0b8f28a90c61ca8591 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p265.model.layers.29.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2caeb8dfca0167ec1e99f919466a78811a6f700babe681f50bd5ab15d1d214b +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p266.model.layers.29.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p266.model.layers.29.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..025df994600ce511f53d10e7e9059cb7a225bf33 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p266.model.layers.29.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0bfb0cb047752f9218ede87e5cba4cf1b012261c387ebfa7aa9c0c9692ce931 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p267.model.layers.29.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p267.model.layers.29.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..3c34beacee9bee6269798d1f2ccfe3b34839c64f --- /dev/null +++ b/checkpoint/pytorch_model.bin/p267.model.layers.29.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d380266d4ff687d39cddb2a16571c11c10420dcb5a97aaca7db6d7984b8253a9 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p268.model.layers.29.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p268.model.layers.29.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..698f02cf837e8fcd77c808b80de5b5a6902e8975 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p268.model.layers.29.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea294126a615fdfaae76ed77b677a8723a95b1725af73c66119f1a0d0c3be1f +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p269.model.layers.29.input_layernorm.weight b/checkpoint/pytorch_model.bin/p269.model.layers.29.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..aff6f4a3374f4ea85d4b5b408fb7ae9aca71d14d Binary files /dev/null and b/checkpoint/pytorch_model.bin/p269.model.layers.29.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p27.model.layers.2.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p27.model.layers.2.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..dd5bca7f5a018de0fd5ab5dfc306c13be302c6db Binary files /dev/null and b/checkpoint/pytorch_model.bin/p27.model.layers.2.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p270.model.layers.29.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p270.model.layers.29.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..76ea228d3edcbd916d4c992492aeb4aea452cc93 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p270.model.layers.29.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p271.model.layers.30.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p271.model.layers.30.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b19d023fec1baefe8fa0e3a05c5def3033d28f12 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p271.model.layers.30.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bceb618e8d770d9725c673d3df6b05f0cc797c3a8b9266a4f1703813e174bd7 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p272.model.layers.30.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p272.model.layers.30.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a277122cf116e0c17fd9592d2b7a6ef084a09f6e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p272.model.layers.30.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd45e6fd42c91b11e30b2567c76986ca8a5fe55ae3dd37eaf26edc84a40b0d6c +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p273.model.layers.30.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p273.model.layers.30.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..ae8d30b14c6281d91b2b188c1e362bd6268739f1 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p273.model.layers.30.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02848d1ab5e3ea17743f74270e6f87c0a30f962328fa44011cbc65611bb77725 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p274.model.layers.30.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p274.model.layers.30.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..d03af7fe900e126e0e8c4180f33d1a8932b840ce --- /dev/null +++ b/checkpoint/pytorch_model.bin/p274.model.layers.30.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:921c53531f90eb583c04bf5d24379b0beb14eabf746c76d4f5eb9d09d40379d6 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p275.model.layers.30.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p275.model.layers.30.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0d14aca2c40709b033b8f1b6991c4bab924055dc --- /dev/null +++ b/checkpoint/pytorch_model.bin/p275.model.layers.30.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9971731580a321abb137729a8898e777ec3c923ef9d4025bd22a4d66abbb4c73 +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p276.model.layers.30.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p276.model.layers.30.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a152836e44496bb34dc98e0facfcd7573ecba6d8 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p276.model.layers.30.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06dbbec996653277d2817ae47ce3a7577fbabca1d4ff0bb08b94fd77951ac2eb +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p277.model.layers.30.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p277.model.layers.30.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0d2fee6a962fa604479588492954fdf6075d61d4 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p277.model.layers.30.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac43ce16ef6720fdac5ad736c64f7612671ceff45a63cc49c7fc6fa2148d90a +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p278.model.layers.30.input_layernorm.weight b/checkpoint/pytorch_model.bin/p278.model.layers.30.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..4d8f620029de2c977350c309d628c4cd5b31400f Binary files /dev/null and b/checkpoint/pytorch_model.bin/p278.model.layers.30.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p279.model.layers.30.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p279.model.layers.30.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..4cc09009162259c63c71034630e328538b9c2dbb Binary files /dev/null and b/checkpoint/pytorch_model.bin/p279.model.layers.30.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p28.model.layers.3.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p28.model.layers.3.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..105010c8c3f79b6d97d5fa931f91059655c4eeb7 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p28.model.layers.3.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b525a770150317174677492109084700667780f95f42670fc8f4a80bedcda12 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p280.model.layers.31.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p280.model.layers.31.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..58bb7ccd9f9f6a2160fed35424693cdb77e9ed91 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p280.model.layers.31.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af8615d6b7c2b6793bd83d369d133efb798e8b642127e39d43f6779973abb52f +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p281.model.layers.31.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p281.model.layers.31.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..589fa6481e27e2366646acb5e0568ab488866b7a --- /dev/null +++ b/checkpoint/pytorch_model.bin/p281.model.layers.31.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d37cb5b43d8ea05ddff23d504da857501236b4f615e7ca9c755b72d650cccf +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p282.model.layers.31.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p282.model.layers.31.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..f898cdf3af6ed9273e788ea96bcd82e72c743038 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p282.model.layers.31.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60dad831de85670c5d915d03fec744e5008b59fabab0db0646f125408931cf20 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p283.model.layers.31.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p283.model.layers.31.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..85aeb47c4ed60eb64bec4f533c6f32bf67527405 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p283.model.layers.31.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76789e115e4cc997ed1341ffa02d540057c6bf7fd0491295b92e23357cc00925 +size 67109765 diff --git a/checkpoint/pytorch_model.bin/p284.model.layers.31.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p284.model.layers.31.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c57ccbda244b0aa6dd5770a68878dd9f4b463e2f --- /dev/null +++ b/checkpoint/pytorch_model.bin/p284.model.layers.31.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379b44da57ef05321f50230532dd4fe5a0fea732c569a7a2237f62ae182240ca +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p285.model.layers.31.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p285.model.layers.31.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6e20da7f91bcb88c39ac09ecf99ab8d36ccc3648 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p285.model.layers.31.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb02ef50553089706bd188de182d629d9bfc964ffb25ff210389e140f6fd6e14 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p286.model.layers.31.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p286.model.layers.31.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..9418a4aed0ab43bb7fb18b6a58552f5c5a050a4d --- /dev/null +++ b/checkpoint/pytorch_model.bin/p286.model.layers.31.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a527c7e78322a261a117bb7a00906b254929c308a6af28701cca5f8e621d32cc +size 180355964 diff --git a/checkpoint/pytorch_model.bin/p287.model.layers.31.input_layernorm.weight b/checkpoint/pytorch_model.bin/p287.model.layers.31.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..3fd723f8da91cdc17ef77aa4e6b466221ba35557 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p287.model.layers.31.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p288.model.layers.31.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p288.model.layers.31.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..882a34ec108e84aa6a87efce87c7c3e20f071d21 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p288.model.layers.31.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p289.model.norm.weight b/checkpoint/pytorch_model.bin/p289.model.norm.weight new file mode 100644 index 0000000000000000000000000000000000000000..78b01179a0aef0854fce43b55d661309ad425184 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p289.model.norm.weight differ diff --git a/checkpoint/pytorch_model.bin/p29.model.layers.3.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p29.model.layers.3.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..42545aced6692b4669e1c1cd0f893793b9d78441 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p29.model.layers.3.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3e84ce00fdc744746ddb464ab03334f5c7f347edc89679bf8243d90cb68ae1 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p290.lm_head.weight b/checkpoint/pytorch_model.bin/p290.lm_head.weight new file mode 100644 index 0000000000000000000000000000000000000000..5a86889a1fbf4a10765d3c7b2365ed5b6c6db555 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p290.lm_head.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c903141ddc191c8361a6cbac9708cce3fe4a4ae6d3fe8c18f351318c3a41223 +size 524550906 diff --git a/checkpoint/pytorch_model.bin/p3.model.layers.0.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p3.model.layers.0.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..9bbcbdaad059f79e35e768b83a973e33f7b3b73d --- /dev/null +++ b/checkpoint/pytorch_model.bin/p3.model.layers.0.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54dcbbd02e2cd2b2e2cb4be4ba52edf6e5d0c599a8b8bce101d0dcd8916ddaf +size 67109756 diff --git a/checkpoint/pytorch_model.bin/p30.model.layers.3.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p30.model.layers.3.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1dcea2b73cd76464817b677c8481175efc0c0daa --- /dev/null +++ b/checkpoint/pytorch_model.bin/p30.model.layers.3.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39035281f4324edf9a07718ca8cc0b2a6c8953f3536d5c5d7e98370160f57ec3 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p31.model.layers.3.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p31.model.layers.3.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..29a105ed7b0c2c26645ab24f233d5d0656d02836 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p31.model.layers.3.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d93dab55edb59f17b17848c7f26cb73406544469634792b482ed36fc8c074e4 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p32.model.layers.3.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p32.model.layers.3.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..41fb075c5005a42ac0e74274911f567ce682d729 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p32.model.layers.3.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aba4b27138840144acf706ace5d4e7703516d237507c7d4faf56b025f837d04c +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p33.model.layers.3.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p33.model.layers.3.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..a686bf999e9d3cea9fd5dc9a4768cfbc05daab3b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p33.model.layers.3.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9938a0dfdd45427682020016b15af75a125ed2d0459ff4f3f353b2406ba330 +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p34.model.layers.3.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p34.model.layers.3.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..7922bad8cb0fb20836aceba46c2cab6ccd140ce5 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p34.model.layers.3.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7d17292da72d113e3ff8d2a7b47561c6342edb447a717bc45b827d8448f662 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p35.model.layers.3.input_layernorm.weight b/checkpoint/pytorch_model.bin/p35.model.layers.3.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..e650c6efce3e33822e550169aa1192089f88a784 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p35.model.layers.3.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p36.model.layers.3.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p36.model.layers.3.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..17b7abd8f2024b655dbecc6feac9d71376d1c084 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p36.model.layers.3.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p37.model.layers.4.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p37.model.layers.4.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..7c324f241886dbb6cf5097bf8e292f194601aa13 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p37.model.layers.4.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f87cee416fc71ade97acc22e59b7601fd9277018e2e23aa998a2dd05422ec201 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p38.model.layers.4.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p38.model.layers.4.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..146b8005ff8d543093365c07dd0e9708286d3aa6 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p38.model.layers.4.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b438be18c39bf8efbb7d22fd616186c814d8e5df39180bb3fddff3750ea5008 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p39.model.layers.4.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p39.model.layers.4.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..264988e037569188147aaaeb3b6cb2f50e6c0e7b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p39.model.layers.4.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b228891d97197619389460d64d4a04f9fbfe354851a6f7fa1ac0b8d391a3b396 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p4.model.layers.0.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p4.model.layers.0.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..33e3676750ad1f93838bbdc8c2932bb5686c4232 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p4.model.layers.0.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2716f85fbda76b3711dd9f7e1dcc362c626eaa460a10acace6b0d971bfc97c91 +size 67109756 diff --git a/checkpoint/pytorch_model.bin/p40.model.layers.4.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p40.model.layers.4.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..2b6be55ecc7f665582f5cddd2fec2967af273912 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p40.model.layers.4.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d37b39139ba324e2b950d43e60aebbeb96cd36b89d28a8e2ef0e728d2a59f07b +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p41.model.layers.4.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p41.model.layers.4.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5445458f95b3112fd334307e14cdb60e566604d1 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p41.model.layers.4.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5479424e7dc5f5d045487b87d6aa648231002323ef532be2d521d5fab30c6698 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p42.model.layers.4.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p42.model.layers.4.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..78f535a21cf3b222b1200b9ac5eb168c25e460c5 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p42.model.layers.4.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1d213513b699b0c6cdb06628ead920eee593975e29a383f5a401c612d4ad79 +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p43.model.layers.4.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p43.model.layers.4.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..19b3300eced4775d915c4b29c19ef1395169dddf --- /dev/null +++ b/checkpoint/pytorch_model.bin/p43.model.layers.4.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cdc9832041c13589607d27522bbe9371164ef21f49acea25acd874df93bac5b +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p44.model.layers.4.input_layernorm.weight b/checkpoint/pytorch_model.bin/p44.model.layers.4.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..aae53cd36e14a0fb281aba789c6b30685c006a22 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p44.model.layers.4.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p45.model.layers.4.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p45.model.layers.4.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..c97f48577d25cd904f81044a6173085748778d74 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p45.model.layers.4.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p46.model.layers.5.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p46.model.layers.5.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..5e03148c429aed2369983e7ca881ebade032f41d --- /dev/null +++ b/checkpoint/pytorch_model.bin/p46.model.layers.5.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:653a62d11e89f4df8de6147beb78f697f0c5f1292814d95cdcdc0ab86e68e751 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p47.model.layers.5.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p47.model.layers.5.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..8c70a090b73070261701055df5f696b3714e5a8d --- /dev/null +++ b/checkpoint/pytorch_model.bin/p47.model.layers.5.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b533b80f9ec6f5dfa81a02607ae6a4e904f7e239b8df5f0244c0cfcf68e1e5c9 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p48.model.layers.5.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p48.model.layers.5.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..43119b9ba228987d6ab5025e9513d3645e9f6096 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p48.model.layers.5.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7609be4d1528013ace35a4a2101bb44066b39d11d2a0ffb70b6095fee10693 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p49.model.layers.5.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p49.model.layers.5.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..4054e606aa440b2150987f920cd2e26ecce6d03b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p49.model.layers.5.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:403bd1abd746c73458080fd9a3a374a0be545f190c29a453ddcee068d33cee2a +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p5.model.layers.0.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p5.model.layers.0.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..2eae0428d9719bb8ecf5f9f07ffc33754f49cd03 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p5.model.layers.0.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ca8121777ce0782bbf8dd42867bdefe3b50d6225ba40d0f69ee0b4c9e309b0 +size 180355955 diff --git a/checkpoint/pytorch_model.bin/p50.model.layers.5.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p50.model.layers.5.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6b6ac32c38a142236653b5ab7ffa63181cdcf22c --- /dev/null +++ b/checkpoint/pytorch_model.bin/p50.model.layers.5.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b6903cbd16d14276c316f780a8c9d7ee59e025011131ed23a92b679d9510a8 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p51.model.layers.5.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p51.model.layers.5.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6edc0ffdc93ca27c90ace67453abdba2f6075d23 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p51.model.layers.5.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dd87c614863a30ffaec10c24235a51c9c444324d4af73ccb9ef515509a29fab +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p52.model.layers.5.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p52.model.layers.5.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..2c3c87c13dcd1cc435dcda6b167ab6da68198ed1 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p52.model.layers.5.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f154e4ec4df22ffb5198d67d2d115ac47d3aa809c1b9fc942b2ef42f241b4f3e +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p53.model.layers.5.input_layernorm.weight b/checkpoint/pytorch_model.bin/p53.model.layers.5.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..d867506222a7e6cc390119483b76e7811d5a681d Binary files /dev/null and b/checkpoint/pytorch_model.bin/p53.model.layers.5.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p54.model.layers.5.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p54.model.layers.5.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..83c0c41df98980b62f28e77788613c87f0fa2e91 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p54.model.layers.5.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p55.model.layers.6.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p55.model.layers.6.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b42938ef73f07496206036bad5242cc42c6938c5 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p55.model.layers.6.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b52011c50a57fb1e2f34fbc8161bcdf26ab17df0ad62acda96f7a21377405c +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p56.model.layers.6.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p56.model.layers.6.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..779414891d7a3abdf408c8256a7282a51bc2c9a6 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p56.model.layers.6.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1defb6e6df98cd8099365b923904c1dda525d9ab8aa049ba60eb473b4de7e2c4 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p57.model.layers.6.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p57.model.layers.6.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..eda2638c97a196579790934968c42a6eb62bb1aa --- /dev/null +++ b/checkpoint/pytorch_model.bin/p57.model.layers.6.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e1831d78f70869b1be015c8a67eaf26773855a0b2270094c399995eb72e2e0 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p58.model.layers.6.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p58.model.layers.6.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..e4d214f6e281b06b85f265161d63d7a2fd80bdd2 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p58.model.layers.6.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62386f968a2db3f9aa9b6e42b0d5ce3ab4f7cf2401f0d1e4938a36eecd97f5bd +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p59.model.layers.6.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p59.model.layers.6.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..9004fcf3da2347257c5f8227c8fda95ac8776d21 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p59.model.layers.6.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cae29799ca109aa4e79cbb50e00e8d987f667f05cf47acc07efdc792b0a82e5 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p6.model.layers.0.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p6.model.layers.0.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..7c25c653c0b8924ce5d76b47b049bfa522d513e6 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p6.model.layers.0.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b108c5d73271119eef880f751c2b1eb7f97d9471fe03a7b81a4b9d3b5790c2 +size 180355949 diff --git a/checkpoint/pytorch_model.bin/p60.model.layers.6.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p60.model.layers.6.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..8011970981c4ea503a2f87f1b9f7983fbbe471eb --- /dev/null +++ b/checkpoint/pytorch_model.bin/p60.model.layers.6.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d327511cb006de59330f2a254b6fc0c463756a31709eea611786f1fbbf4ca7 +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p61.model.layers.6.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p61.model.layers.6.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..357bc6fc6345494ec21159d37f0862a2580e86c4 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p61.model.layers.6.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b71fb24ffda2a6811858e2c625eefb8c59f9ce8fdf528420210c3e75597ff466 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p62.model.layers.6.input_layernorm.weight b/checkpoint/pytorch_model.bin/p62.model.layers.6.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..972f0a7059eb41b25ba910945bfc86d00ca5a839 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p62.model.layers.6.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p63.model.layers.6.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p63.model.layers.6.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..12689292a3c8e6e47768204f18a7f9f11e63ad10 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p63.model.layers.6.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p64.model.layers.7.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p64.model.layers.7.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..80010aba6964cfc01b8b99fa39692897096a9c84 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p64.model.layers.7.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a9a411ba1fb5e6817917ff668abc43bb5844f1b4d2020f3f36e36925a6110fd +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p65.model.layers.7.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p65.model.layers.7.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..00893e4321ac3319d9667c993c17b846722b6840 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p65.model.layers.7.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21311a7dfd1a011736cadc122b7fc310f968aa11847809259c69b5afd548b877 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p66.model.layers.7.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p66.model.layers.7.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..03ed8edc0cc9204325884d8f19bb8fac7fec6cb8 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p66.model.layers.7.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5bb707481c7f8a67b3679a9ea4e7ceccc3033c633bac4bf0647b89b9fb6ab1 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p67.model.layers.7.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p67.model.layers.7.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..883a6cee5230307e469295df4010bd038a24ce98 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p67.model.layers.7.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe98a13888d86285af335994c91cc84dea988f572119d65bf189115da7487dd +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p68.model.layers.7.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p68.model.layers.7.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..eb38081ed27e2ed1930c296de2019d2f2d047fbd --- /dev/null +++ b/checkpoint/pytorch_model.bin/p68.model.layers.7.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4458a8a6334c874f972ebe804dd92324a629d6a81b268af7735e58e94780d4f0 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p69.model.layers.7.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p69.model.layers.7.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..68efe1dfa145d68673cd5a717f0a27dd8e4d337b --- /dev/null +++ b/checkpoint/pytorch_model.bin/p69.model.layers.7.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b182540467a1d177d2b37b0941e1c3b1ba558735ab05b033da5a0ae73ad7cba +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p7.model.layers.0.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p7.model.layers.0.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..8f3a14ebaf5318b647184d7d85cbf0963edad0ab --- /dev/null +++ b/checkpoint/pytorch_model.bin/p7.model.layers.0.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807d73fa061a8df429583d2a88c19998be0756963a6fcabae683c5985fe32b30 +size 180355955 diff --git a/checkpoint/pytorch_model.bin/p70.model.layers.7.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p70.model.layers.7.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..516e47ef8accd839ae27668f2fdfdebb4973a0ed --- /dev/null +++ b/checkpoint/pytorch_model.bin/p70.model.layers.7.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b009c9d76504e78876d0ebafcc89d8b7fe2c94e3f0f3fdccc8f1f1452f0088e7 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p71.model.layers.7.input_layernorm.weight b/checkpoint/pytorch_model.bin/p71.model.layers.7.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..98a25dd3fc3e5cc4a4d0cba7d76f93252d1d15d4 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p71.model.layers.7.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p72.model.layers.7.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p72.model.layers.7.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..322b21cac3b7136f15129c870f3d262fe818ada8 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p72.model.layers.7.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p73.model.layers.8.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p73.model.layers.8.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..6aa679d82e465b6ba4006d76c9ae6e293285a437 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p73.model.layers.8.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:518384d0c0662af785e4abf956580fe22cf3fb86883ef8cf6fb9b765905f6a6b +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p74.model.layers.8.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p74.model.layers.8.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..2d4622c8e6b52db0a950a335ea2ab5dba8817470 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p74.model.layers.8.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c08e1057b7fdb2c9f1a9c8cbd030c33b3c4af61d4b92fde2ad63461fb8e04a1 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p75.model.layers.8.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p75.model.layers.8.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..38697e3117921397438cf70c1fb6372ada9cacd3 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p75.model.layers.8.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cba929013914f5e4ceb99714a286ffafaf85dc2db3a67ac4731c8835d58e5b05 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p76.model.layers.8.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p76.model.layers.8.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..b7f99df7d19981be2f1831d99a66fb912d1bfb1d --- /dev/null +++ b/checkpoint/pytorch_model.bin/p76.model.layers.8.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca910b8d7ebc9c69fa5fbf5a20d861851422ea80df65515faf890c1f7a74f907 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p77.model.layers.8.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p77.model.layers.8.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..11b21cef57ca135f66c1c805408c530e0b3a38bc --- /dev/null +++ b/checkpoint/pytorch_model.bin/p77.model.layers.8.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2eb79c5688516e59a8bf7aeca986828803d3067e3d18d2f672e961aaf8ea45d +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p78.model.layers.8.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p78.model.layers.8.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..c1f6f795f6ea0d61ed86be028b0ad839b91e09c4 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p78.model.layers.8.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df91db23178ad7d140673d1e68aa785cac6301b42b90e6fb2108023270d5e9f +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p79.model.layers.8.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p79.model.layers.8.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..ac4c8780669305f3ffaa094d347513ef6972db61 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p79.model.layers.8.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a76cb2351e879013b5270422b132692bb9bef09c81619173cf607d15dab64090 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p8.model.layers.0.input_layernorm.weight b/checkpoint/pytorch_model.bin/p8.model.layers.0.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..ffc0595a75d0f1a16ff18181dc8a470a31dcd149 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p8.model.layers.0.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p80.model.layers.8.input_layernorm.weight b/checkpoint/pytorch_model.bin/p80.model.layers.8.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..6ccb2b78287943bf8482cf512e7fc4e34892c06b Binary files /dev/null and b/checkpoint/pytorch_model.bin/p80.model.layers.8.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p81.model.layers.8.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p81.model.layers.8.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..adaaffff62b4fd40383196afa862c59e3c568949 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p81.model.layers.8.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p82.model.layers.9.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p82.model.layers.9.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..71ea9b900dcd9fec11b0365cd9543bd765da3a5e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p82.model.layers.9.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0be243fe5313ab67902129ab5a36491174c49236a2f4b1924547ad33b2021ae +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p83.model.layers.9.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p83.model.layers.9.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..55155d98237b8d720b317381c4550016f9f9994e --- /dev/null +++ b/checkpoint/pytorch_model.bin/p83.model.layers.9.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512e4254d68acda50b38fd6f1a0aa678549cd85894f26b4d7d9d9531e20dad20 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p84.model.layers.9.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p84.model.layers.9.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..386bc5092ddb5bb7f2b5745261d757b38c4478f4 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p84.model.layers.9.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8553f1a126ebb981b4098f6e8fd6af44f39b7bcac660d8c72f2822cba3f2b7b +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p85.model.layers.9.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p85.model.layers.9.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..f498ab5b6e1e615ca3aca7aff2dba7007eec1d79 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p85.model.layers.9.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b8ee100c332c6891c2c412eca8cdde2b3a82903da2bb129a6bb32686975428 +size 67109759 diff --git a/checkpoint/pytorch_model.bin/p86.model.layers.9.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p86.model.layers.9.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..ad51cdeda5b2d852d71cfaafbfecb27e3928f95c --- /dev/null +++ b/checkpoint/pytorch_model.bin/p86.model.layers.9.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481983f1c92c3f37115529b5e28aa5f43dc7d17b096905b830207cb555250832 +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p87.model.layers.9.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p87.model.layers.9.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..7ab8c0484e11554ef20ed58068fd2bf6827554f9 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p87.model.layers.9.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75be9ec92c062d1e057a4cffa4173f92b702f5695a6b5cce60b7dee0a50cc1cd +size 180355952 diff --git a/checkpoint/pytorch_model.bin/p88.model.layers.9.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p88.model.layers.9.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..441a540ee13798723407ad4c02d7973d160334d8 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p88.model.layers.9.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983f3823e73a8c028cce7f73e64ded188b13cbac17575c89cb8e7acbb4044a8c +size 180355958 diff --git a/checkpoint/pytorch_model.bin/p89.model.layers.9.input_layernorm.weight b/checkpoint/pytorch_model.bin/p89.model.layers.9.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..7731f0b6e8aacb6e340a9a6ef48b31a4ff7b2404 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p89.model.layers.9.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p9.model.layers.0.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p9.model.layers.0.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..4c85c22a4c7b06713dd439bb72fca4c1bcbf6d42 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p9.model.layers.0.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p90.model.layers.9.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p90.model.layers.9.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..a18919a9267292cfd1037dae273eca97222e2b0d Binary files /dev/null and b/checkpoint/pytorch_model.bin/p90.model.layers.9.post_attention_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p91.model.layers.10.self_attn.q_proj.weight b/checkpoint/pytorch_model.bin/p91.model.layers.10.self_attn.q_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..e5fbe9443a039c3f977a7c84ba24a638fdd16a76 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p91.model.layers.10.self_attn.q_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57ed1334001ac929d46359e046b8a73ee658b58ec33defa6d74583d5877c369e +size 67109762 diff --git a/checkpoint/pytorch_model.bin/p92.model.layers.10.self_attn.k_proj.weight b/checkpoint/pytorch_model.bin/p92.model.layers.10.self_attn.k_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..8d2cf8e57081512e8266c7d77982192d9641d6e9 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p92.model.layers.10.self_attn.k_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5e4a7ccf42db6ae0a2b7f24cba55425b4b2625c147158450a6c8be4595bc42 +size 67109762 diff --git a/checkpoint/pytorch_model.bin/p93.model.layers.10.self_attn.v_proj.weight b/checkpoint/pytorch_model.bin/p93.model.layers.10.self_attn.v_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..53e88580e20f8e197ca2b9db0f0d5d3008e17fbb --- /dev/null +++ b/checkpoint/pytorch_model.bin/p93.model.layers.10.self_attn.v_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c18af17e6cc2fad79d6248f96e4311bc163c4f42437d5935ca0e28610cf2f0c8 +size 67109762 diff --git a/checkpoint/pytorch_model.bin/p94.model.layers.10.self_attn.o_proj.weight b/checkpoint/pytorch_model.bin/p94.model.layers.10.self_attn.o_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..9b7feb84e08b1f4bd1176232d81f722ea00f7774 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p94.model.layers.10.self_attn.o_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6adb7b06afc8e7f91a2bf9455a28446f921f0f7185d1416c8ba6f7479f7835e3 +size 67109762 diff --git a/checkpoint/pytorch_model.bin/p95.model.layers.10.mlp.gate_proj.weight b/checkpoint/pytorch_model.bin/p95.model.layers.10.mlp.gate_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..1d4d8e3d5e90c8e633f5f9eb660af623076f51b4 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p95.model.layers.10.mlp.gate_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7730a47ebeb2948e5ab10a4535d322957e60cee3aec4e2f3f0de57b097d315a0 +size 180355961 diff --git a/checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight b/checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..cfa5b628aaf9fb133c257c216c370d2179475c67 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4dbccf0a6f39df713c81e7a47954e0f65489bded2b70d61464601aae1e1fd34 +size 180355955 diff --git a/checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight b/checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight new file mode 100644 index 0000000000000000000000000000000000000000..0cf0d4c22de576673774325bef9361ad54135a96 --- /dev/null +++ b/checkpoint/pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b4ee604e7d7e179f251f097927f0eafc5fc52df7a9ec65044c33abf2bcf7f5 +size 180355961 diff --git a/checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight b/checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..fe684889113b0da614028254c61e999d347da6d6 Binary files /dev/null and b/checkpoint/pytorch_model.bin/p98.model.layers.10.input_layernorm.weight differ diff --git a/checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight b/checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight new file mode 100644 index 0000000000000000000000000000000000000000..54d4589f52049f0e245d6cd09e254e2ca6b7185c Binary files /dev/null and b/checkpoint/pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight differ diff --git a/compiled/186a933115232053cdff.neff b/compiled/186a933115232053cdff.neff new file mode 100644 index 0000000000000000000000000000000000000000..11a80b6dd759fe50fad47cabbfe6e8bd0ceec793 --- /dev/null +++ b/compiled/186a933115232053cdff.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69160786da7d64456c462d627ea538b521c1e205e652ac626272bd9fca90e8f +size 2089984 diff --git a/compiled/540db8b9571300c15792.neff b/compiled/540db8b9571300c15792.neff new file mode 100644 index 0000000000000000000000000000000000000000..56e9f68127452a261b252ed4c02afbd95223ddb4 --- /dev/null +++ b/compiled/540db8b9571300c15792.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a84bfb02bd9717e3a69b68f152691ef81c7043b5db38f39c7e6b00e9123fbf +size 6063104 diff --git a/compiled/585a14c8d348e11367d1.neff b/compiled/585a14c8d348e11367d1.neff new file mode 100644 index 0000000000000000000000000000000000000000..2e915c3b78770a49695cecde60f90c0a1020d99a --- /dev/null +++ b/compiled/585a14c8d348e11367d1.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fbc0b5edd574f055c3f5803e83af7f4e97915cf00a1d8a3b8d9a685a05b0fc2 +size 2540544 diff --git a/compiled/6f0431e83e140df0acd9.neff b/compiled/6f0431e83e140df0acd9.neff new file mode 100644 index 0000000000000000000000000000000000000000..ab1cab6903cbcc2aa08ffa41f48d164d6dcf9ed5 --- /dev/null +++ b/compiled/6f0431e83e140df0acd9.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb2ef439563483fc3b4211c0845e803b09bf5e895f6e80ab70f0b54af2e5072 +size 1926144 diff --git a/compiled/86a37b8c9f44ef0ad841.neff b/compiled/86a37b8c9f44ef0ad841.neff new file mode 100644 index 0000000000000000000000000000000000000000..7df471a66bdf2db2eefeb3b73cde4fe0ad71f38f --- /dev/null +++ b/compiled/86a37b8c9f44ef0ad841.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119e92e72b33584291189b6fce4a3b79a26a6255e83f4d5594231d5a70474afc +size 2325504 diff --git a/compiled/c5726de0e8bc3fd6f4c9.neff b/compiled/c5726de0e8bc3fd6f4c9.neff new file mode 100644 index 0000000000000000000000000000000000000000..618e5e79133726d338747d264ffc9c357eadd8e3 --- /dev/null +++ b/compiled/c5726de0e8bc3fd6f4c9.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efa15e75ba5f483fb9971a39a5131e3297f269070cddebdec54e812be1959b3 +size 1956864 diff --git a/compiled/e0158d7717a18978a6c7.neff b/compiled/e0158d7717a18978a6c7.neff new file mode 100644 index 0000000000000000000000000000000000000000..ea4313ec140a1d95a65bd797617c9ce90d3eec40 --- /dev/null +++ b/compiled/e0158d7717a18978a6c7.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b544ef3fc52e2f08e060887b57f3a9fb2164e75892e284d18b207b9f66a208b +size 2110464 diff --git a/compiled/e87cecd034e5ac4c3f36.neff b/compiled/e87cecd034e5ac4c3f36.neff new file mode 100644 index 0000000000000000000000000000000000000000..63fc52e4cb9700a0736efa32a08c204e2129230d --- /dev/null +++ b/compiled/e87cecd034e5ac4c3f36.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4388c145d3a889fdbb1471239d43009f68cf5674d849cd4b7793861b2ff6c7ed +size 2008064 diff --git a/compiled/ea24e07b03ca7ec5310c.neff b/compiled/ea24e07b03ca7ec5310c.neff new file mode 100644 index 0000000000000000000000000000000000000000..262dcd974604babc3eb07d9ea57fc65058524737 --- /dev/null +++ b/compiled/ea24e07b03ca7ec5310c.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cecce50f04ef6df235609bc58c4cb3405200cd55213e47c403e2ca99b2e5002a +size 2018304 diff --git a/compiled/fedc38910ff9aec1ce50.neff b/compiled/fedc38910ff9aec1ce50.neff new file mode 100644 index 0000000000000000000000000000000000000000..13854ecaa80e59a803e3b5fbf912c5945d029a9a --- /dev/null +++ b/compiled/fedc38910ff9aec1ce50.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1d80b55a30d51e1d7844e35c009d8af2055e360a8c555c99fc55d75362a5e1 +size 2284544 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..6ad4b60295f70a0b5b6d26f84bd870969ab04c63 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "_name_or_path": "CodeLlama-7b-hf/config.json", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 16384, + "model_type": "llama", + "neuron": { + "auto_cast_type": "fp16", + "batch_size": 1, + "compiler_type": "neuronx-cc", + "compiler_version": "2.11.0.34+c5231f848", + "num_cores": 12, + "sequence_length": 2048, + "task": "text-generation" + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.33.2", + "use_cache": true, + "vocab_size": 32016 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..7a03f6daf5b60ad02d8503e1ad01049b2d1935ec --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.33.2" +}