commit b65e7fcda873691944438954a232d4af8bd25f08 Author: ModelHub XC Date: Sat May 2 16:05:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Nanbeige/ToolMind-Web-3B 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..0de3b9a --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +language: +- en +- zh +license: apache-2.0 +tags: +- search-agent +- rag +- deep-research +- 3b +- nlp +pipeline_tag: text-generation +--- + +# Overview + +ToolMind-Web-3B is a specialized lightweight agent built on top of the [**Nanbeige4-3B-Thinking-2511**](https://huggingface.co/Nanbeige/Nanbeige4-3B-Thinking-2511) foundation model. +Following extensive **SFT (Supervised Fine-Tuning)** and **RL (Reinforcement Learning)** focused on search behaviors, +our model attains leading performance among small-scale models on multiple long-horizon leaderboards like **Xbench-Deepsearch, HLE, and GAIA**, enabling reliable execution of up to hundreds of consecutive tool invocations. + +
+ + +
+ + +# Highlights + +1. **Strong Performance at Compact Scale** + +ToolMind-Web-3B delivers high-quality long-horizon reasoning and tool-augmented search capabilities while maintaining a lightweight 3B parameter footprint. Despite its compact size, it achieves competitive performance across multiple benchmarks like **Xbench-Deepsearch, GAIA, and HLE**. The model is evaluated under the **[MiroThinkers workflow](https://github.com/MiroMindAI/MiroThinker)**, ensuring standardized and reproducible assessment. + +2. **An Open-Source Complex QA Dataset Synthesized from Wikipedia Entity–Relation Knowledge Graphs** + +We provide a rich, structured QA dataset derived from Wikipedia knowledge graphs, designed to support supervised fine-tuning and reinforcement learning of search-augmented agents. + +3. **Turn-Level Judge Guided SFT and Reinforcement Learning** + +In the supervised fine-tuning (SFT) stage, a **turn-level judge** identifies which interaction turns should be used for training. +In the reinforcement learning (RL) stage, a **turn-level reward** provides feedback to refine the model's multi-turn search and tool invocation behavior. + + + +# Benchmark Results + +| Model | GAIA | BrowseComp | BrowseComp-zh | HLE | Seal-0 | Xbench-Deepsearch | Xbench-Deepsearch-10 | DSQA | +|------|------|------------|---------------|-----|--------|-------------------|----------------------|------| +| DeepSeek-V3.2 | 0.635 | 0.676 | 0.65 | 0.408 | 0.385 | 0.71 | | / | +| MiniMax-M2 | 0.757 | 0.44 | 0.485 | 0.318 | / | 0.72 | | / | +| GLM-4.6 | 0.719 | 0.451 | 0.495 | 0.304 | / | 0.7 | | / | +| MiroThinker 8B | 0.664 | 0.311 | 0.402 | 0.215 | 0.404 | 0.606 | | / | +| AgentCPM-Explore 4B | 0.639 | 0.25 | 0.29 | 0.191 | 0.4 | 0.7 | / | / | +| **Ours**| +| **ToolMind-Web-3B(w Synthetic QA only)** | 0.583 | 0.144 | 0.301 | 0.224 | 0.36 | 0.76 | 0.3 | 0.308 | +| **ToolMind-Web-3B** | 0.670 | 0.174 | 0.308 | 0.248 | 0.477 | 0.751 | 0.37 | 0.458 | + +# Limitations + +While we place great emphasis on the safety of the model during the training process, striving to ensure that its outputs align with ethical and legal requirements, it may not completely avoid generating unexpected outputs due to the model's size and probabilistic nature. These outputs may include harmful content such as bias or discrimination. Please don't propagate such content. We do not assume any responsibility for the consequences resulting from the dissemination of inappropriate information. +
+ +# Citation +If you find our model useful or want to use it in your projects, please cite this project. +
+ +# Contact +If you have any questions, please raise an issue or contact us at nanbeige@126.com. +
\ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..8805f6d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,9 @@ +{ + "": 166104, + "": 166106, + "": 166103, + "": 166105, + "<|endoftext|>": 166102, + "<|im_end|>": 166101, + "<|im_start|>": 166100 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..33f7bd0 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 10496, + "max_position_embeddings": 196608, + "model_type": "llama", + "num_attention_heads": 20, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 70000000, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.38.2", + "use_cache": true, + "vocab_size": 166144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9fa0eeb --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "max_length": 4096, + "pad_token_id": 0, + "temperature": 0.9, + "top_p": 0.6, + "transformers_version": "4.37.0" +} diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..c65778a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 228983265280 + }, + "weight_map": { + "lm_head.weight": "model-00048-of-00048.safetensors", + "model.embed_tokens.weight": "model-00001-of-00048.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.10.input_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.11.input_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.12.input_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.13.input_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00048.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.14.input_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.15.input_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.16.input_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00048.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.17.input_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.18.input_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00048.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.19.input_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.20.input_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.21.input_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.22.input_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00048.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.23.input_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00048.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.24.input_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.25.input_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.26.input_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.27.input_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00048.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.28.input_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.29.input_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.30.input_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00048.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.31.input_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.32.input_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.33.input_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.34.input_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00048.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.35.input_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.36.input_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.37.input_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00023-of-00048.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.38.input_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.39.input_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00048.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.4.input_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00048.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.40.input_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.41.input_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00048.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.42.input_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.43.input_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00048.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.44.input_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00027-of-00048.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.45.input_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.46.input_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.47.input_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.48.input_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00048.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.49.input_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.5.input_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.50.input_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00048.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.51.input_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.52.input_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.53.input_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.54.input_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.55.input_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.56.input_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.57.input_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00048.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.58.input_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00035-of-00048.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.59.input_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.6.input_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.60.input_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.61.input_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.62.input_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00037-of-00048.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.63.input_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.64.input_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.65.input_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00039-of-00048.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.66.input_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.67.input_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00040-of-00048.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.68.input_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.69.input_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.7.input_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.70.input_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.71.input_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00042-of-00048.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.72.input_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00043-of-00048.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.73.input_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.74.input_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00044-of-00048.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.75.input_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.76.input_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00045-of-00048.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.77.input_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.78.input_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.79.input_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00047-of-00048.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.8.input_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00048.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.9.input_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00048.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00048.safetensors", + "model.norm.weight": "model-00047-of-00048.safetensors" + } +} diff --git a/nbg_search_performance.png b/nbg_search_performance.png new file mode 100644 index 0000000..fbef14d Binary files /dev/null and b/nbg_search_performance.png differ diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..fa5f263 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011885d58d085e42590d82b0eccd4670f21464fd1baf83bd800449323e9f0b66 +size 7867370082 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..0520eb7 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,27 @@ +{ + "additional_special_tokens": [ + { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } + ], + "bos_token": "<|im_start|>", + "eos_token": "<|im_end|>", + "pad_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..f23c3b2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d8f0326910136aca20831249220b38ce5299527647bc8c6b65404485c479740 +size 18451122 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..5dc56ce --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb41d04798b714520a9b075727b0226538b7330254299062742c50ec8374bc36 +size 2782298 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..f5a053f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,102 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "166100": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "166101": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "166102": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "166103": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "166104": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "166105": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "166106": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>" + ], + "bos_token": "<|im_start|>", + "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\n你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if (add_generation_prompt is defined and add_generation_prompt) %}{{ '<|im_start|>assistant\n' }}{% endif %}", "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "extra_special_tokens": {}, + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}