Upload folder using huggingface_hub

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_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_1024_r_1024_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_1024_r_1024_merged/model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df379c2f901a99d93e9aa521c9abea6ba64043b1ee2d4ff3b2b57e17c13348b
+size 4616939328

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e559839de8658475b29b6669396da6d9483d621cc0df377937038565630a08
+size 4998736368

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c06be20aa00003d736861d0d17c3d5440bb90d40b7f08e296ed53f8a025eaa5
+size 4506896776

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fee86e40f44420a96776665f9fdc7f4838d7f368fe7a1644492b8d6c208eba4
+size 4793157784

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52df7be8112eb640995378f4c0f27630895e592a02a3e5678ac69261839e1f8
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72dde029b0c7583df8186912ace960b63d680eb08d994eabb4166a11b50f685
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce595172d09d2a4a5c26d0c8927fe15f93efedb8287eaea88c0df9e07f948ce7
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004a13704fc6099ab59618033bec782889145255970285a6259468a2b599150d
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0d4f56f12ef490bde0f6b60e357e07ab9970f94d993624de55af3dd1da8648
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dab12f354849b5cbf0fc9eb95bc1d1a1a37884ffe855b0741c1b9d45e3f680a
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e5df5c0ff7d83074a3fee11518bcb1f25bc58843889c60ab7c28a48a855416
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081aacd4e4e6210659233b225de187dd295413729b24cc574d9787ed30a6a22a
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b01c4e706771251b99b06199206ca2efe824942d3b4421dc84691548ed5dc0b
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7565328686ad72ec4762f843531a9e960bcb3b0f86788a016a0e5bc9778dcd6
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fd25a9f570f8e685d8b80303043312ee66edbd8b40f39ac4d9e7916b3bc14f
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80354bf2d20dc05ec0e223d2de7f48e5044d9b6b9fdb9490646aea6f4f0e2ffe
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3475f6402c1050d4c7913c5218bb23a6de74e55150aa85b4d48f20ffffae93
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416df8ebed43128bbf3ca68aac6df7b189acfd860fb4084b3d75493881ac1db1
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8aae35ae0dcaab07e9a6c78e0ea684cae5cd36382151054baa144712a0f629
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f59456b99ad9c8fbbb26ecf97309d9735b2d89a459d85ae68716ab50fb29ca
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e7ae8810e61a488adc12928d423edde88b544c29481e57dc7f4cc619ed05e6
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba6fcdfeb64b74bb6da8199a8bf031a19cf8a1bd2017a0f214b5e60283f6bc4
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910893d7db5fb0bbb582461db6e2d459b9c9174e118b634baeae6c955c697142
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff426cae14f1c8df44b1840de74aaf7fa9e97dfe216f8195a104de8cb19f835e
+size 4793157808

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3f966107de6f5ac2e44b42f0f19c0d21d5813bfa4346c5c6fbc2de53d3413c
+size 4793157800

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb55a19c48e34764f0be379fa6fee6546362d9eaa0cf50af55aead63c0c42e45
+size 4998736392

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c37bfaaa8536d3f1292e3041f578ce27f17377608734ec37206d856ccfe3c95
+size 4506896792

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_merged/model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059bbaea1ed1653145702e290d35692370cc1be4561a480812d35069a2e1d66f
+size 4697765672

lora-logo_fix_full_deepseek33b_gpt35i_lr_0.0002_alpha_1024_r_1024_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_1024_r_1024_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_1024_r_1024_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
+}