commit 7286e6aa35e8785934ed107eb574c2bac79f2ae4 Author: ModelHub XC Date: Mon Jun 22 12:42:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: DavidAU/Gemma-The-Writer-N-Restless-Quill-10B-Uncensored Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7172205 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +library_name: transformers +tags: +- mergekit +- merge +- gemma2 +base_model: +- google/gemma-2-9b-it +--- + +

Gemma-The-Writer-N-Restless-Quill-10B-Uncensored

+ +This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. +The source code can also be used directly. + +IMPORTANT: Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers + +If you are going to use this model, (source, GGUF or a different quant), please review this document for critical parameter, sampler and advance sampler settings (for multiple AI/LLM aps). + +This a "Class 2" (settings will enhance operation / optional adjustments) model: + +For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) (especially for use case(s) beyond the model's design) please see: + +[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ] + +REASON: + +Regardless of "model class" this document will detail methods to enhance operations. + +If the model is a Class 3/4 model the default settings (parameters, samplers, advanced samplers) must be set for "use case(s)" uses correctly. Some AI/LLM apps DO NOT have consistant default setting(s) which result in sub-par model operation. Like wise for Class 3/4 models (which operate somewhat to very differently than standard models) additional samplers and advanced samplers settings are required to "smooth out" operation, AND/OR also allow full operation for use cases the model was not designed for. + +BONUS - Use these settings for ANY model, ANY repo, ANY quant (including source/full precision): + +This document also details parameters, sampler and advanced samplers that can be use FOR ANY MODEL, FROM ANY REPO too - all quants, and of course source code operation too - to enhance the operation of any model. + +[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ] + +NOTE: + +I strongly suggest you also visit the DavidAU GGUF (below) repo too for more details in using this model ; especially if it is "Class 3" or "Class 4" to get maximum performance from the model. + + +For full information about this model, including: + +- Details about this model and its use case(s). +- Context limits +- Special usage notes / settings. +- Any model(s) used to create this model. +- Template(s) used to access/use this model. +- Example generation(s) +- GGUF quants of this model + +Please go to: + +[ https://huggingface.co/DavidAU/Gemma-The-Writer-N-Restless-Quill-10B-Uncensored-gguf ] + +Additional quants: + +[ https://huggingface.co/mradermacher/Gemma-The-Writer-N-Restless-Quill-10B-GGUF] + +Imatrix ggufs: +[ https://huggingface.co/mradermacher/Gemma-The-Writer-N-Restless-Quill-10B-i1-GGUF] + +[ https://huggingface.co/RichardErkhov/DavidAU_-_Gemma-The-Writer-N-Restless-Quill-10B-gguf] \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5e9d1dc --- /dev/null +++ b/config.json @@ -0,0 +1,34 @@ +{ + "_name_or_path": "G:/9B/Tiger-Gemma-9B-v2", + "architectures": [ + "Gemma2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": 50.0, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "final_logit_softcapping": 30.0, + "head_dim": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 16, + "num_hidden_layers": 46, + "num_key_value_heads": 8, + "pad_token_id": 0, + "query_pre_attn_scalar": 224, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "sliding_window_size": 4096, + "torch_dtype": "bfloat16", + "transformers_version": "4.43.3", + "use_cache": false, + "vocab_size": 256000 +} diff --git a/model-00001-of-00020.safetensors b/model-00001-of-00020.safetensors new file mode 100644 index 0000000..4ca604c --- /dev/null +++ b/model-00001-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a6526c5f9f48b9cf91b9b46d355e5a99ba621c85d7d8ff09b014ef72a0255d +size 1835008144 diff --git a/model-00002-of-00020.safetensors b/model-00002-of-00020.safetensors new file mode 100644 index 0000000..03109f2 --- /dev/null +++ b/model-00002-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b546f903f6a34e896ab50df4f7c03ee486cbe98f85c16862781434c414b57fb +size 998311752 diff --git a/model-00003-of-00020.safetensors b/model-00003-of-00020.safetensors new file mode 100644 index 0000000..7e97d4d --- /dev/null +++ b/model-00003-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca24befe82bdcb8cb24154e458559c428467e9ed31a1f3ace186cf4462bf315 +size 983653936 diff --git a/model-00004-of-00020.safetensors b/model-00004-of-00020.safetensors new file mode 100644 index 0000000..7f688a9 --- /dev/null +++ b/model-00004-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c16b76ab19cda00e8d39a14746c41251cff949b12d60f150ee04a7acbd04b6af +size 998304504 diff --git a/model-00005-of-00020.safetensors b/model-00005-of-00020.safetensors new file mode 100644 index 0000000..cd9e8e6 --- /dev/null +++ b/model-00005-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62246c1c9794ebf7b4fd65332d7ea07088ac69ae80c92e421f65c0ab75427cfe +size 983653936 diff --git a/model-00006-of-00020.safetensors b/model-00006-of-00020.safetensors new file mode 100644 index 0000000..151c6fd --- /dev/null +++ b/model-00006-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4539c80bbd1f8be1499d9b7c795d51ecff661c643072c6903b96346a4bc2694c +size 998304504 diff --git a/model-00007-of-00020.safetensors b/model-00007-of-00020.safetensors new file mode 100644 index 0000000..c6137a3 --- /dev/null +++ b/model-00007-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8af882e90df3d66034e968d91d3de1c2d67136c0751e9d03aea0c402b22fa1a +size 983653928 diff --git a/model-00008-of-00020.safetensors b/model-00008-of-00020.safetensors new file mode 100644 index 0000000..11207d2 --- /dev/null +++ b/model-00008-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49657ef4321000d108f69d923438e9f21fd775aff04f461476cfc62f9bbd35f4 +size 998304504 diff --git a/model-00009-of-00020.safetensors b/model-00009-of-00020.safetensors new file mode 100644 index 0000000..c65e44f --- /dev/null +++ b/model-00009-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad19126de098c1a4816615d6c0c2fdbdb6b26139a970a405577f981124642a1 +size 983653936 diff --git a/model-00010-of-00020.safetensors b/model-00010-of-00020.safetensors new file mode 100644 index 0000000..0bb567c --- /dev/null +++ b/model-00010-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c98b2f7dbc048761e8adcfecdf7b768e8e634e23630746a17346b6d7547a6e +size 998304504 diff --git a/model-00011-of-00020.safetensors b/model-00011-of-00020.safetensors new file mode 100644 index 0000000..8a0ce2e --- /dev/null +++ b/model-00011-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18a92bb1878c9ca7ff632ae3db3cae3180194d9e3bf4e5ac2044eddfecc9ba8d +size 983653920 diff --git a/model-00012-of-00020.safetensors b/model-00012-of-00020.safetensors new file mode 100644 index 0000000..841ad3f --- /dev/null +++ b/model-00012-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189c4491ddcd276244e9cf681e1ace0b5af1920bb63d204f9d8ed9960d2e400a +size 998304504 diff --git a/model-00013-of-00020.safetensors b/model-00013-of-00020.safetensors new file mode 100644 index 0000000..0e9651e --- /dev/null +++ b/model-00013-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:529724e0320170e0831aada1f57faba71350e7bb5a89da4d606cb1e0fd6f93c5 +size 983653936 diff --git a/model-00014-of-00020.safetensors b/model-00014-of-00020.safetensors new file mode 100644 index 0000000..6ab0ff2 --- /dev/null +++ b/model-00014-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2f046c362f76ed76aa39d15471bdf6a342ca2a10f9d11ee89d28bd84c0aa50 +size 998304504 diff --git a/model-00015-of-00020.safetensors b/model-00015-of-00020.safetensors new file mode 100644 index 0000000..8716149 --- /dev/null +++ b/model-00015-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93176b32f9a2ca8c56d441040b24201ff7c1d38f89488d7ebb4ed6b23378d638 +size 983653920 diff --git a/model-00016-of-00020.safetensors b/model-00016-of-00020.safetensors new file mode 100644 index 0000000..1b48167 --- /dev/null +++ b/model-00016-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3899607b39e8beff046b46f43bc124ceb6fe493fa65ff5860e8d2aa703f25e65 +size 910223632 diff --git a/model-00017-of-00020.safetensors b/model-00017-of-00020.safetensors new file mode 100644 index 0000000..1fb29f6 --- /dev/null +++ b/model-00017-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:661899ea9485f940c6cd04e9b4af3cb2362433394500661aa9782c3565ed8ed7 +size 924845088 diff --git a/model-00018-of-00020.safetensors b/model-00018-of-00020.safetensors new file mode 100644 index 0000000..70f2ec2 --- /dev/null +++ b/model-00018-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e431dc45f229c41176aa8227009189f0306a299db91af6b249e7b9225df96d +size 939673064 diff --git a/model-00019-of-00020.safetensors b/model-00019-of-00020.safetensors new file mode 100644 index 0000000..997977d --- /dev/null +++ b/model-00019-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f4f621fab9032a8ae863352a692fe0392c537be8f7bdd9931357cdd673e6861 +size 998304480 diff --git a/model-00020-of-00020.safetensors b/model-00020-of-00020.safetensors new file mode 100644 index 0000000..99673c6 --- /dev/null +++ b/model-00020-of-00020.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81951e898a7bcd3f345f7012fb4835139a2a4002cdaa48950cf9962bfa70d2dd +size 587262216 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..267d99a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 20068973568}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.0.pre_feedforward_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.10.pre_feedforward_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.11.pre_feedforward_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.12.pre_feedforward_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.13.post_feedforward_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.13.pre_feedforward_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.14.pre_feedforward_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.15.post_feedforward_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.15.pre_feedforward_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.16.post_feedforward_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.16.pre_feedforward_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.17.post_feedforward_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.17.pre_feedforward_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.18.post_feedforward_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.18.pre_feedforward_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.19.post_feedforward_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.19.pre_feedforward_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.2.post_feedforward_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.2.pre_feedforward_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.20.post_feedforward_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.20.pre_feedforward_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.21.post_feedforward_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.21.pre_feedforward_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.22.post_feedforward_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.22.pre_feedforward_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.23.post_feedforward_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.23.pre_feedforward_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.24.post_feedforward_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.24.pre_feedforward_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.25.post_feedforward_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.25.pre_feedforward_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.26.post_feedforward_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.26.pre_feedforward_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.27.post_feedforward_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.27.pre_feedforward_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.28.post_feedforward_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.28.pre_feedforward_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.29.post_feedforward_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.29.pre_feedforward_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.3.post_feedforward_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.3.pre_feedforward_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.30.post_feedforward_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.30.pre_feedforward_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.31.post_feedforward_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.31.pre_feedforward_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.32.post_feedforward_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.32.pre_feedforward_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.33.post_feedforward_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.33.pre_feedforward_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.34.post_feedforward_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.34.pre_feedforward_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.35.post_feedforward_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.35.pre_feedforward_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.36.post_feedforward_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.36.pre_feedforward_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.37.post_feedforward_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.37.pre_feedforward_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.38.post_feedforward_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.38.pre_feedforward_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.39.post_feedforward_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.39.pre_feedforward_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.4.post_feedforward_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.4.pre_feedforward_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.40.post_feedforward_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.40.pre_feedforward_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.45.post_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.41.post_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.44.post_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.43.post_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.42.post_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.45.pre_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.41.pre_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.44.pre_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.43.pre_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.42.pre_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.post_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.pre_feedforward_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.6.post_feedforward_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.6.pre_feedforward_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.7.post_feedforward_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.7.pre_feedforward_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.8.post_feedforward_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.8.pre_feedforward_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.post_feedforward_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.pre_feedforward_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.norm.weight": "model-00020-of-00020.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..8d6368f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "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..5771f48 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79 +size 17518525 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..f5fc6c8 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,1757 @@ +{ + "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 + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 2048, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}