commit affc2065d1c9d73c7b3b1feb0680d7757eef0106 Author: ModelHub XC Date: Tue May 12 18:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: HelpingAI/MediKAI Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bb6ef1b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,66 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model-00001-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00011-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00008-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00013-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00010-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00007-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00012-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00014-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00016-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00009-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00015-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00016.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..9f7e5bd --- /dev/null +++ b/README.md @@ -0,0 +1,18 @@ +--- +license: other +--- + +# MediKAI - Your Healthcare Companion 🏥💬 + +Welcome to mediKAI, the latest healthcare-focused model by HelpingAI designed to provide personalized assistance and support in medical-related queries. + +## Overview +mediKAI is a 14 billion parameters model that specializes in healthcare-related topics and medical assistance. Whether you have questions about symptoms, treatments, medications, or general health and wellness, mediKAI is here to help. + +## Languages Supported +- English +- French +- Hindi +- Spanish +- Arabic +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..885974d --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "FreedomIntelligence/Apollo-7B", + "architectures": [ + "GemmaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 2, + "eos_token_id": 1, + "head_dim": 256, + "hidden_act": "gelu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 24576, + "max_position_embeddings": 8192, + "model_type": "gemma", + "num_attention_heads": 16, + "num_hidden_layers": 48, + "num_key_value_heads": 16, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "torch_dtype": "float16", + "transformers_version": "4.39.0.dev0", + "use_cache": true, + "vocab_size": 256000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..1779a6c --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,22 @@ + +dtype: float16 +merge_method: passthrough +slices: +- sources: + - layer_range: [0, 8] + model: FreedomIntelligence/Apollo-7B +- sources: + - layer_range: [4, 12] + model: FreedomIntelligence/Apollo-7B +- sources: + - layer_range: [8, 16] + model: FreedomIntelligence/Apollo-7B +- sources: + - layer_range: [12, 20] + model: FreedomIntelligence/Apollo-7B +- sources: + - layer_range: [16, 24] + model: FreedomIntelligence/Apollo-7B +- sources: + - layer_range: [20, 28] + model: FreedomIntelligence/Apollo-7B diff --git a/model-00001-of-00016.safetensors b/model-00001-of-00016.safetensors new file mode 100644 index 0000000..93704ed --- /dev/null +++ b/model-00001-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4855ace4430414943a5b0f30f13204ac41d9205d3f73dd3f68f42a53677f24 +size 805320264 diff --git a/model-00002-of-00016.safetensors b/model-00002-of-00016.safetensors new file mode 100644 index 0000000..b3d2f9d --- /dev/null +++ b/model-00002-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ebcf1d368819b6309c0d19c75b36231e19cb96f9df1a670d7aa53b1cbd8f34 +size 1874854256 diff --git a/model-00003-of-00016.safetensors b/model-00003-of-00016.safetensors new file mode 100644 index 0000000..6b16508 --- /dev/null +++ b/model-00003-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a4bd858326918cd2c6503d5a92292e08a8c1beb7ad2b737e3488c4ef763c303 +size 1912630656 diff --git a/model-00004-of-00016.safetensors b/model-00004-of-00016.safetensors new file mode 100644 index 0000000..dfc988d --- /dev/null +++ b/model-00004-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11af8256489c659da14bea4004e827086e35ddec0b5d97b1821992afd4b022e0 +size 1912643176 diff --git a/model-00005-of-00016.safetensors b/model-00005-of-00016.safetensors new file mode 100644 index 0000000..4b6ae6f --- /dev/null +++ b/model-00005-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3d5ba5b6b52e1161a53c1a873ab3c08758ebae6a42ade45f5093879343d79f +size 1912655712 diff --git a/model-00006-of-00016.safetensors b/model-00006-of-00016.safetensors new file mode 100644 index 0000000..fe142b5 --- /dev/null +++ b/model-00006-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fa140df0689dcbd592521ffdb390aff4ed33f72765019aa56b1ece1b15b62d9 +size 1912655688 diff --git a/model-00007-of-00016.safetensors b/model-00007-of-00016.safetensors new file mode 100644 index 0000000..78aaa52 --- /dev/null +++ b/model-00007-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57592d81026f57b5e5724db22c6713b4dd9d194d3fd7a88df7ded34c2e93227 +size 1912655704 diff --git a/model-00008-of-00016.safetensors b/model-00008-of-00016.safetensors new file mode 100644 index 0000000..420f4f7 --- /dev/null +++ b/model-00008-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4972b4fb75705450cf06cf9fb4515131491a4ae7e55351959042f4261c3a1c86 +size 1862298232 diff --git a/model-00009-of-00016.safetensors b/model-00009-of-00016.safetensors new file mode 100644 index 0000000..403b49a --- /dev/null +++ b/model-00009-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08cede9b42e370d350fbc58a8800d6e258c3a7d82932062856c43b70da04fb8c +size 1988152944 diff --git a/model-00010-of-00016.safetensors b/model-00010-of-00016.safetensors new file mode 100644 index 0000000..81f9865 --- /dev/null +++ b/model-00010-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b0c04d3f9975533c314c5c8da89b9aa61ff9b9a38da4c8b605bc65fcd317bb +size 1937796040 diff --git a/model-00011-of-00016.safetensors b/model-00011-of-00016.safetensors new file mode 100644 index 0000000..f16b8d3 --- /dev/null +++ b/model-00011-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6470ff1b8ea7f31b542cbf48ff22ca360dde7a347272160ada0cf035188393 +size 1912655728 diff --git a/model-00012-of-00016.safetensors b/model-00012-of-00016.safetensors new file mode 100644 index 0000000..a82c499 --- /dev/null +++ b/model-00012-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d59c485a099c3214d49e898a907ed3b1863417b9265a768637a578e12687f041 +size 1912655704 diff --git a/model-00013-of-00016.safetensors b/model-00013-of-00016.safetensors new file mode 100644 index 0000000..2e2a58c --- /dev/null +++ b/model-00013-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b122288e2764b3db4db08fde798dab21ad601034c72bd8a5f0e21b3f8984fee9 +size 1912655728 diff --git a/model-00014-of-00016.safetensors b/model-00014-of-00016.safetensors new file mode 100644 index 0000000..0f47b17 --- /dev/null +++ b/model-00014-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7622e021612b17808b39411a323d78337b7c865566217d8e12abb0d544ed3e +size 1988159208 diff --git a/model-00015-of-00016.safetensors b/model-00015-of-00016.safetensors new file mode 100644 index 0000000..dda3c91 --- /dev/null +++ b/model-00015-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c71d6bdd0bf58378fd65d09003bb912d36a71c560e7d70807b6d4fe420109f +size 1937802304 diff --git a/model-00016-of-00016.safetensors b/model-00016-of-00016.safetensors new file mode 100644 index 0000000..ddb3edb --- /dev/null +++ b/model-00016-of-00016.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586b783748e1c4e1e633747ae797e952b6078f0cca770d14fcc2a1d432b642a6 +size 453028968 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..c08d426 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00002-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.42.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.41.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.43.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00016.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..f611958 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..8ee5b29 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b14dd5913f9efa3c8a0fbc97c71b2cae69ebf973be82f227a66178753cc859 +size 17477707 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..796efe9 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..bd4d495 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,53 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": null, + "max_length": null, + "model_max_length": 1000000000000000019884624838656, + "pad_to_multiple_of": null, + "pad_token": "", + "pad_token_type_id": 0, + "padding_side": "left", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}