Upload folder using huggingface_hub

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-33b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 19200,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32256
+}

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.40.0.dev0"
+}

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c018ce50f5451f852639108b71f0c7757414d94430d575e8fbff134b774d56e6
+size 4616939328

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9764ae1c6a9dc31777d16d81a16f90058309923c3c34697c72716c968e44e4c
+size 4998736368

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55936f6f6c252b55f0eb16a048add609a22d6185f6ee9839c51475d3d5636a29
+size 4506896776

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5c9c77a500231a1bcb3b791d445499d5896f728609cf872936ef8a415eeb98
+size 4793157784

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe6b3f8f2dd59aaf7b6ffdaf57a242ef440b34e431a72957736c8ee898437d9
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e36915fb3d0ef9f02dfe9fc8688d7f204f7b426cc3c82d9cd9244be7bd7207d
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:411aa077abf55288a8cad7bd018dee26b67170c9d1385926c0e473d733f9b1d7
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b97cb258f771882ed00a8eeda35ac078ef58484c8e679b90acf0b166c8bb008
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d62abaa4a59455b299f030cf8c74c2c4db8d84284d31e3ccec0187e01802c16
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044329957ae4aa6ac79466d88e26024cc0287fda06c1cad3bed97553c50ab874
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dbab1bfc07de80eb3baeb203fe03169d0bda86481050aa7eb1a2fc14693244e
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3174a86e15e9a6431377bb249f1a323cae1eaf4a666f20c62d89ab4cd50d77
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf250e6fd43969ab1f5b6d404abc1f188d54eb0033234a03016ec51ded02f07
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c59ca809c68ce1464f644013546ba318b292acd53ef53e4789b2328046a104
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0473915da67ac61cebdf9087242d1f33f1b2963082725947702855541d59a91a
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0bb09c3d041079fc23e4603f3c8e871f101b3dc5b8431a4d78b402572825b8
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd54c85f93ec32a4257529568a4dce4509286c7f48edc102269374a29194a1c
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78146101ecac4eee8190ba0183b012e21b2bf4539b710ea0a8ef495e5f7b555f
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98a525b9797f7cb6f43bc76b2cf22b34eec8f990b06b114419bf6e152bb5381
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfab2cd1e7c19c092fb516a3f6fb265a9faf9a8ab7135dddb8f5e0b8b94fb572
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7f0800c7cb5fe5992794da04d123485aec2f3b1b025e2a871e21af484c6a9f
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a70eb66daaa7466a3f54986d2d33d3ef3575553ca24d417eccc3780ab63827
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0194245df9ee933e2a0bbefbe702d81f37aea66843c1dbe4f94f0280ed66ca
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550e41f109b4a445c75d82d9234d37562a296b607b2cbe1a2c0e740a7e10ac48
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307a0ca0cbea8e7f39cb3f2baaf386634fd47f55577759e43705dfb748abc3b9
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68dcfbb0b0e52f4772d34a7d95a735fc0f89b2f327160bdc652651feeb86cb66
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0002a24335d960dca50744c0ecef40f4016a2a32e8fbded8cc5611d5c8845b9c
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e5c28b8cca86c52e1ed4bb2d9042e6ea80605eba1128cd5cf40fccfc03e8fd
+size 4697765672

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/model.safetensors.index.json

@@ -0,0 +1,568 @@
+{
+  "metadata": {
+    "total_size": 133371965440
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00028-of-00028.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.norm.weight": "model-00028-of-00028.safetensors"
+  }
+}

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_512_r_512_merged/tokenizer_config.json

@@ -0,0 +1,193 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}