shisa-ai/ablation-145-a128.dpo.armorm.rp.tl.8e7-shisa-v2-llama-3.1-8b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: shisa-ai/ablation-145-a128.dpo.armorm.rp.tl.8e7-shisa-v2-llama-3.1-8b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-20 00:47:07 +08:00
commit 71cf44d51f
348 changed files with 86062 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
checkpoint-2445/config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128009,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": false,
"vocab_size": 128256
}

12
checkpoint-2445/generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.50.0"
}

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:495b64ae222376985389064ae6f6b06637173b40c94ed875daf1664deae96fb4
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c48f900c9f1a5b0fea1cdc963a5188912f27efced260fdf803d2adf6e45b1e0f
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d14804c211f485c36f77484d777a430c3b914c9303d7598836e73603c83f8c5b
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46b64c55ae2fc10c4467c498428ca4afe658c1cedb68886199b0b812d275a3d2
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2797d8bb4c99d8a8170c51efa27de192ed8e291be1a87a12db4f7fdd2f0c790b
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:96797925ddfa0ea84ac16ed0173c0c9b2846ae8652528912ce7c01bd66b4eabf
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17653d591b10611c3a48f9898681b89d76acce5196378deb99be2f6fc82dc802
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:29919fd74e9c00732b05652e3d468a9b4b12e75b2982953ff9421e86d44ba410
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40a1f9b7c30f57e6b4b5419eb921940da7371bc7489c018ad69d2399357d3fd3
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:83da36339302cf9622dbfd31d150306001dc4b34b06969d04a7894565f6bc283
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14f78f053ecfb35f93e9a2cd96435c3766d3aa6003d97fd8304e89d601255154
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c135a23aa558c1691e470bd51a863e81ecdf2eba55374dfcad97b0d206009ea6
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad00b2188240966d60649e54cb31cab58aff00444aa9d4ae71734d26421e9522
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:19c8b2c5ec9dec7c225444d2c24ff8d45fbab0f8dc27b413f733c7f95ac0ca90
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f87432df5d6abf2ee643941560d13e13971e35b00adbd47230ff83695e04bada
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5149802f91eb49cd70b715d82f1ead4818043a739e3fdd6fc632b54e0a68cd7
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:74db9146e3af5c2ebe40f9d6231796c3e87726971b6f90d3153a909a23b4e30d
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94f7b79fef776a4a020982048223cdc8c0b36451e740a48e4bdcc04a33be9bf4
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4c453d87bc26655c21be52200bd9bd74b6b71cf7172e74dc67814ac877bf3013
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:07cbffb47ac817fd1da3ef0ff336f185e32156f227633704a4a92a2eee7b650c
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dcdd1c877bdb007a298f96750d28124df2ddbf4a6dee76afb1f27023e1555768
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:34969048c56cf1f41988dd4e262a28414cff85c9b24539405899fb78e2cc1bcc
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:900395bb0c73a7d72157056a57cb776914321ad930764a44736d571654b76aaf
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67c6d6c3dcd2354edde1390a61f3536e84739af12933dca3079872beaabe8b34
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5807e6a8f5c4ae8ce895422f16847f9d6440772efa66a835a42f1adfd57a5029
size 1514016442

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38f9417b1e966cbeb5ae7cfe1176bc63bd4415cdfac0f90055548ed97bf4e69f
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9be923b473f71e01d20546bf68436e05627238c56234a1eac5d38cfb5b4c4f53
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b1bf6b5eb7e325e0003fe2837d6237bed34b0760a6ec99a23200ee8e83246d5c
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2fbe32130c2999aea0d8c22861891be926cdfbb73d2f293d5769e636a3ed5884
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a7178ddd81b5c0ee0a1e0173473de0429da23e0e72c278acc1acc12e4709db6a
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:79a3e125a80f9c1261b62944cd57b612d97abc91ad1d31f9ed4439f9816ffe35
size 1514015111

3
checkpoint-2445/global_step2445/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:458bb1945f4ebfdc8a7f65a389f4530be514113b740ac0eef27e9bd72a97974c
size 1514015111

3
checkpoint-2445/global_step2445/zero_pp_rank_0_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ffe2ec38edbe0b5d6e6150e6e9c4874bad566b9a275825fae36b115dfb705507
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_10_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c4e658b292c123f55b3d55c45e964bd863e856250b17842c831ffef0c85f16a1
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_11_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9fecdf063c4da0cf60d7f6b35ac9ea6a055abe701f722bc2c3d2bb7b044c2ea1
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_12_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bfc82216501ff83ea47d43f9f20b16bc0d56eb698d65763fa53af58261283b40
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_13_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5ca14f3ce2aa6e8432025d9bcfae023f4028772903aedf27251a73ee89d9d9c
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_14_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b499c7332ae7a32106b346ae639177132aedc19afabb2738ca0e64bc3d7de2c1
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_15_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:329e41b68c60e83e871a716f6082a4be3c906e00da7ae73e051bd4337426c778
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_16_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2100aeaab7b7a3f79e3a5f65f4b0921ccb135f81fa1e051446156c3a3bfd73bb
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_17_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e2fbc8d92199cf5ea2edfdebf931db8adfe2a5f8765c18e9d8179778be59c539
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_18_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3db66e4fe950e5c4b5246e87074224980c95347d1ba107cbfc86679f6d97445d
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_19_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8fb63cd572f258454684e6ca311b00501e7d86139f94138968c00257036fa155
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_1_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bae542fcea121575e03aef13180259386db45d8338cfb8e170c1b1e936f07f56
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_20_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5868fd1a75aa1dd0d95ee8c620b62c2278b143828cbebe4eccd1407be9677f7b
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_21_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9ddc82f8cf5a751cf0e3262640ed49766df68af472a6d4814e51dac88862d27d
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_22_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:12f2337e40e00274ed590c1fe24b40149ea7e94cffbef40a7cbf47645389cb3f
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_23_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d4886a3dfdec0f0415d38692a739a753ab7e29dc88fa108e8b6fe42625ef192
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_24_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a5fb4ecdb0b270ff0eced437c781d31b0cb014809d32917e168940877bfb03f4
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_25_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0901e901fe596b3138d2ccc32204539f794ef6f279c6b42be27a40c895c787d3
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_26_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f207ac4a816c43bf844c2c8c80644cbc46e16a4111a38c58827903cf3d4bcdd
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_27_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bd23381e14373662f70a9dce1c0eeb15924cb8077c967ddc0e6d1e1a572ce43c
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_28_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:059bf1ba37ee92ccca47187fded153a9af22ee7044a0cee33b17a8c25c31b2c1
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_29_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f3f05ba702f76a781cc0cca9f4d3fab13ea3f597fc2ea91a5201fba24d0419b0
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_2_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0bf6f1b5fd7f395e28561eb3210bc8f3fa0d6cb589439ed820880d6b6a48bd6b
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_30_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:60601369222e025ec7ace86e4faa98f72f42033dbddedc18dcc9e4a05d45b2c3
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_31_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6cf71cecae2998dfe48359806530fde46071708a330bf5da58ac545c673467de
size 150540

3
checkpoint-2445/global_step2445/zero_pp_rank_3_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e70e74735403d741bd55d1ece22450b62be54ef37652769657aa404eed47d2ee
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_4_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4991f0ead2f78d5715727716ecf7bfe732ecfd7ab68f34f25f15fcc68c5a6267
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_5_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c5497e5c0a1f39abf9e032be83d4142aaca609dcce04ee031ffb3d11fd1e3c1a
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_6_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5b97d0b7bc65b7c10b9af30baaecc9e58d79b2cb0861ae27187b4b0b3ba2674b
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_7_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1e2de5673e2d582e3de81f7b93016335f067b70ac5717d7651cb85afa1756486
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_8_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d89c67316075467476c1eb25aa00637bc97f5c0b241d464e6ad18d5544dc314b
size 150245

3
checkpoint-2445/global_step2445/zero_pp_rank_9_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:909fce6df9e30ff0e3b1913a1313d8414cff3352514e4d46eb424a280c594a27
size 150245

1
checkpoint-2445/latest Normal file
View File

@@ -0,0 +1 @@
global_step2445

3
checkpoint-2445/model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:45f844c7bcec934a51bb941e54d30a655fc8db45dd739d36738f2fa4ce1de909
size 4976698672

3
checkpoint-2445/model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e194d3a55358b5c5d86589c20ee9b494530bf727cc1955b7907610cd4b044682
size 4999802720

3
checkpoint-2445/model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:774b89d412ab7fd49b257aa6ea2b15450e5a7caaff911791ce76707c059730b3
size 4915916176

3
checkpoint-2445/model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:933eca7410a1d89ab7601cb2b6a52d50488ac67c7c5bd30235b9802488e85d19
size 1168138808

298
checkpoint-2445/model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 16060522496
},
"weight_map": {
"lm_head.weight": "model-00004-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}

3
checkpoint-2445/rng_state_0.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:08282b46825aa78d10fe10e3fea89555c5b5a691b261a3ddfd58fcb58370edff
size 15984

3
checkpoint-2445/rng_state_1.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dbab71d98a3a9a92df82a6bba463947327c3a1bcf35cd9f4f46114641fc42dd9
size 15984

3
checkpoint-2445/rng_state_10.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54e5c2d65c14df39137f6a3bd8314f534dad93d72efe8e40e23a61187ba74ce8
size 15997

3
checkpoint-2445/rng_state_11.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f578146bcaaed333cf4637aa3b454e2f6238e691e45b4160001b63b4f8b5ce4e
size 15997

3
checkpoint-2445/rng_state_12.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8463662162a837871bb50af43a407175ca95f3f364bc13c7d065e8b6929bad11
size 15997

3
checkpoint-2445/rng_state_13.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fe9bafd75244b907f13aa5b102963f4d018d7b80b94ddb0262313774362d9305
size 15997

3
checkpoint-2445/rng_state_14.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c5e353c1ca54c464e3464d695507da7da6c134e4ad9d6acab6f72e52d5bf13c7
size 15997

3
checkpoint-2445/rng_state_15.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24f1ef20cfc904ac8f811ceffab91f00cccadca0e878c8ef8a7335e83ef9513f
size 15997

3
checkpoint-2445/rng_state_16.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cecf995eb1b13a85a673384ed67c75acc989e9d373ac7da2d90cbc7af2c1b4a7
size 15997

3
checkpoint-2445/rng_state_17.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:375986c2a348f319aeed3322fcf23be7787f801c585046ff217d7855463fbc0d
size 15997

3
checkpoint-2445/rng_state_18.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a50dfdcb902d78e55850cabc410552a4e651090792c2e086926cbda383b4f35f
size 15997

3
checkpoint-2445/rng_state_19.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:79850d41cfed8d83ef96222b2b956a0ec273b7fa78630d3cb0e86f2ab29bb934
size 15997

3
checkpoint-2445/rng_state_2.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:caac82d57d878d30219a4f9ec289a97ff90c53afc160b968f251b3fd3454b8d8
size 15984

3
checkpoint-2445/rng_state_20.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:60201c3050f5fddd8ba67c9cc8ea589b8296872acef041a46972a75489ba48f2
size 15997

3
checkpoint-2445/rng_state_21.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9b45ccf4c1d4fa82ab73d5b1084c8895bb7a843bb65c39bb0b2bb2a6192e6df3
size 15997

3
checkpoint-2445/rng_state_22.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54521e12e4ad123a5cdba9d3c092e63ee37b099ff802bbe417dfb47861244ab9
size 15997

3
checkpoint-2445/rng_state_23.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4917fcd537e822a9012f654e3131d5dbd358e1916dec368f464d89c1223a2e5
size 15997

3
checkpoint-2445/rng_state_24.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e6b078914d8fc5b3568727c1679a97889d10f35460aaa0147c1ab343e0a8576f
size 15997

3
checkpoint-2445/rng_state_25.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:58235624c008372a4489d1dc4d4a5d582e83b5954529d532a8ac9e27cc1117eb
size 15997

3
checkpoint-2445/rng_state_26.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d0a9e394ce0c35df215df576763794e20589536fd7d2e8aae0d2bfaac14eb95
size 15997

3
checkpoint-2445/rng_state_27.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5a40fc515e550756e1b3497c9e62fa179918e76adb87ab3233db714b992268c8
size 15997

3
checkpoint-2445/rng_state_28.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6dadf1f4ae507c5e5ab940441273a3552a7e59fcc516e7dfddd1956d1c5c5a3d
size 15997

3
checkpoint-2445/rng_state_29.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:73dfc967a343045291988f3bcbbdee93e0877bb869db48fd675e9946c2c43507
size 15997

3
checkpoint-2445/rng_state_3.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:19762d2d370222b01817da11bbaa6665d542293373186d66f754e7246bb861ed
size 15984

3
checkpoint-2445/rng_state_30.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6890d56ed291634fd39a3901c77e10c249a355684a11b3e34af07a400ff9189c
size 15997

3
checkpoint-2445/rng_state_31.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:25d52ac86e2e15b3ec76429e008562b498d6431769f7f3ad24c182d032f7701b
size 15997

3
checkpoint-2445/rng_state_4.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:00c7508b346a7d3c5c23392845f1d013331114ade778794b76e919cb3ed5d33e
size 15984

3
checkpoint-2445/rng_state_5.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b89de7d14dd20a191f56b74c816ef8b7fe5c171e31efbeadbf321c4539ed68c3
size 15984

Some files were not shown because too many files have changed in this diff Show More