commit 1e630bd8829caa645442f4799704b4f38b11f337 Author: ModelHub XC Date: Thu Jul 2 18:54:12 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: togethercomputer/gemma-2-9b-it-MoAA-DPO Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a0c88fd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 + +model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00008.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..ed80956 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +library_name: transformers +tags: [] +--- + + + + +## Model Description + +This is the DPO model in our Mixture of Agents Alignment (MoAA) pipeline. This model is tuned on the Gemma-2-9b-it. MoAA is an approach that leverages collective intelligence from open‑source LLMs to advance alignment. + +Two mains stages are involved in our MoAA method. In the first stage, we employ MoA to produce high-quality synthetic data for supervised fine-tuning. In the second stage, we combines multiple LLMs as a reward model to provide preference annotations. + +Some key takeaways of our work: + + + +- 📈**Alignment pipeline that actually works** Our MoAA method sends Llama‑3.1‑8B‑Instruct’s Arena‑Hard **19 → 48** and Gemma-2-9B-it **42→56**, handily beating GPT‑4o‑labeled sets at the time. + +- 🏆**Ensembled rewards > single critics** An MoA reward model with dynamic criteria filtering edges out competitive ArmoRM on MT‑Bench & Arena‑Hard—all while staying 100 % open source. + +- 🚀**Self‑improvement unlocked** Fine‑tune the strongest model inside the ensemble on MoAA data and it *surpasses its own teachers*—evidence that open models can push past proprietary ceilings without external supervision. + + +## Model Sources + + +For more details refer to + +- **[Paper](https://arxiv.org/abs/2505.03059)** + + + + + +## How to Get Started with the Model + +Use the code below to get started with the model. + +Run inference like this: +``` +from transformers import AutoTokenizer, AutoModelForCausalLM + +tokenizer = AutoTokenizer.from_pretrained("togethercomputer/gemma-2-9b-it-MoAA-DPO") +model = AutoModelForCausalLM.from_pretrained("togethercomputer/gemma-2-9b-it-MoAA-DPO") +``` + + +## Training Data + +We sample 5 responses from the previously trained SFT model and use a reward model to select the preferred and rejected responses for preference learning. Specifically, we utilize the reward model to identify the highest-scoring response as the "chosen" response and the lowest-scoring response as the "rejected" response for each method, and here we propose a novel technique that leverages MoA as a reward model. + +## Evaluation & Performance + +Refer to [Paper](https://arxiv.org/abs/2505.03059) for metrics. + + + + + +## Citation +``` +@article{wang2025improving, +title = {Improving Model Alignment Through Collective Intelligence of Open-Source LLMS}, +author = {Junlin Wang and Roy Xie and Shang Zhu and Jue Wang and Ben Athiwaratkun and Bhuwan Dhingra and Shuaiwen Leon Song and Ce Zhang and James Zou}, +year = {2025}, +journal = {arXiv preprint arXiv: 2505.03059} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5625682 --- /dev/null +++ b/config.json @@ -0,0 +1,34 @@ +{ + "_name_or_path": "/data/data_persistent3/junlin/DPO/ICLR/gemma2-9b-it-SFT-UFUC5k-DPO_MoJ_onpolicy6k_lr_3.0e-7_g_16_e_5", + "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": 42, + "num_key_value_heads": 8, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "sliding_window_size": 4096, + "torch_dtype": "float32", + "transformers_version": "4.46.1", + "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/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8703b38 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.46.1" +} diff --git a/model-00001-of-00008.safetensors b/model-00001-of-00008.safetensors new file mode 100644 index 0000000..aaa9e10 --- /dev/null +++ b/model-00001-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:674287cce6542acb811f4a946d46859123a62c307b17104243ab0c9d954559c9 +size 4844480456 diff --git a/model-00002-of-00008.safetensors b/model-00002-of-00008.safetensors new file mode 100644 index 0000000..3af4623 --- /dev/null +++ b/model-00002-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2403f92e3f7595de39d73bccc48e350274005b75dce6d225bdf65092c6466e8d +size 4962213464 diff --git a/model-00003-of-00008.safetensors b/model-00003-of-00008.safetensors new file mode 100644 index 0000000..e7ea4a0 --- /dev/null +++ b/model-00003-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c217e91be9c5b5e2baa7951043df6f6849b977ac3b8b9acaeef3c96d33034e0 +size 4962271312 diff --git a/model-00004-of-00008.safetensors b/model-00004-of-00008.safetensors new file mode 100644 index 0000000..28534fa --- /dev/null +++ b/model-00004-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf9f8129609e13f58a33018d9843e321ec0f59385ebfbe2407cff86bed4b9d5 +size 4932853744 diff --git a/model-00005-of-00008.safetensors b/model-00005-of-00008.safetensors new file mode 100644 index 0000000..f83a029 --- /dev/null +++ b/model-00005-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf94ab98542c93af9c7423b81a8434b2f139995300a5ba229fae4156c4ce064 +size 4962213528 diff --git a/model-00006-of-00008.safetensors b/model-00006-of-00008.safetensors new file mode 100644 index 0000000..11bfd89 --- /dev/null +++ b/model-00006-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a85cd3f8231fb9d9ba3efc0a6c03df14749104bea016e374c13bad6641e799 +size 4962213528 diff --git a/model-00007-of-00008.safetensors b/model-00007-of-00008.safetensors new file mode 100644 index 0000000..22f20fe --- /dev/null +++ b/model-00007-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab1165db74b121af765d8c8aa46e9ed06b8ad2a63e4294deafbfed7e3650d06d +size 4962271328 diff --git a/model-00008-of-00008.safetensors b/model-00008-of-00008.safetensors new file mode 100644 index 0000000..fd1f4cb --- /dev/null +++ b/model-00008-of-00008.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113dc61fb66e2f942694dd825682892fd3e00b903e82639bad752a422dd45cce +size 2378360680 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..da19758 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,471 @@ +{ + "metadata": { + "total_size": 36966823936 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00008.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.10.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.11.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.12.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.13.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.14.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.15.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.15.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.16.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.17.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.18.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.19.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.19.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.20.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.20.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.21.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.21.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.22.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.23.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.24.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.24.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.25.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.25.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.26.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.26.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.27.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.27.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.28.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.29.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.29.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.30.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.30.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.31.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.31.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.32.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.32.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", + "model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.33.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.33.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.34.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.34.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.35.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.35.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.36.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.36.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.37.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.37.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.38.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.38.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", + "model.layers.39.input_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.39.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.39.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.40.input_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.40.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.40.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.41.input_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.41.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.41.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.7.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.7.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.8.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.8.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.9.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", + "model.norm.weight": "model-00008-of-00008.safetensors" + } +} 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..a4a305d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 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..bdce82f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "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 + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "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' %}{% set system_message = messages[0]['content'] | trim + '\n\n' %}{% set messages = messages[1:] %}{% else %}{% set system_message = '' %}{% endif %}{% for message in messages %}{% if loop.index0 == 0 %}{% set content = system_message + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + 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 +}