commit 25c5902a1d68da4a6390668819b93ba17d0a25ae Author: ModelHub XC Date: Mon Jun 15 23:08:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: microsoft/rho-math-7b-v0.1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +*.model 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json 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..eba35fd --- /dev/null +++ b/README.md @@ -0,0 +1,146 @@ +--- +license: mit +tags: +- nlp +- math +language: +- en +pipeline_tag: text-generation +--- + + +

+Rho-1: Not All Tokens Are What You Need +

+ + +

+ [📜 Arxiv] • + [💬 HF Paper] • + [🤗 Models] • + [🐱 GitHub] +

+ +

+ +
+ Figure 1: Rho-1 is pre-trained with Selective Language Modeling (SLM). SLM improves average few-shot accuracy on GSM8k and MATH by over 16%, achieving the baseline performance 5-10x faster. +

+ + +## 🔥 News + +- [2024/04/12] 🔥🔥🔥 Rho-Math-v0.1 models released at 🤗 HuggingFace! + - [Rho-Math-1B](https://huggingface.co/microsoft/rho-math-1b-v0.1) and [Rho-Math-7B](https://huggingface.co/microsoft/rho-math-7b-v0.1) achieve 15.6% and 31.0% few-shot accuracy on MATH dataset, respectively — matching DeepSeekMath with only 3\% of the pretraining tokens. + - [Rho-Math-1B-Interpreter](https://huggingface.co/microsoft/rho-math-1b-interpreter-v0.1) is the first 1B LLM that achieves over 40% accuracy on MATH. + - [Rho-Math-7B-Interpreter](https://huggingface.co/microsoft/rho-math-7b-interpreter-v0.1) achieves 52% on MATH dataset, using only 69k samples for fine-tuning. +- [2024/04/11] Rho-1 paper and repo released. + + + +## 💡 Introduction + +Rho-1 base models employ Selective Language Modeling (SLM) for pretraining, which selectively trains on clean and useful tokens that aligned with the desired distribution. + + +### Selective Lanugage Modeling (SLM) + +

+ +
+ Figure 2: + Upper: Even an extensively filtered pretraining corpus contains token-level noise. + Left: Previous Causal Language Modeling (CLM) trains on all tokens. + Right: Our proposed Selective Language Modeling (SLM) selectively applies loss on those useful and clean tokens. +

+ +

+ +
+ Figure 3: The pipeline of Selective Language Modeling. + SLM optimizes language model performance by concentrating on valuable, clean tokens during pre-training. + It involves three steps: + (Step 1) Initially, train a reference model on high-quality data. + (Step 2) Then, score each token's loss in a corpus using the reference model. + (Step 3) Finally, train the language model selectively on tokens that show higher excess loss compared to the reference loss. +

+ + + +### Evaluation Results + +Base models (Few-shot CoT): + +| **Model** | **Size** | **Data** | **Uniq. Token** | **Train Token** | **GSM8K** | **MATH** | **MMLU STEM** | **SAT** | +|:-----------------:|:--------:|:--------:|:---------------:|:---------------:|:---------:|:--------:|:-------------:|:--------:| +| 1-2B Base Models | | | | | | | | | +| Qwen1.5 | 1.8B | - | - | - | 36.1 | 6.8 | 31.3 | 40.6 | +| Gemma | 2.0B | - | - | - | 18.8 | 11.4 | **34.4** | 50.0 | +| DeepSeekMath | 1.3B | - | 120B | 150B | 23.8 | 13.6 | 33.1 | **56.3** | +| [Rho-Math-1B-v0.1](https://huggingface.co/microsoft/rho-math-1b-v0.1) | 1.1B | OWM | 14B | 30B | **36.2** | **15.6** | 23.3 | 28.1 | +| >= 7B Base Models | | | | | | | | | +| Mistral | 7B | | - | - | 41.2 | 11.6 | 49.5 | 59.4 | +| Minerva | 540B | - | 39B | 26B | 58.8 | 33.6 | **63.9** | - | +| LLemma | 34B | PPile | 55B | 50B | 54.2 | 23.0 | 54.7 | 68.8 | +| InternLM2-Math | 20B | - | 31B | 125B | 65.4 | 30.0 | 53.1 | 71.9 | +| DeepSeekMath | 7B | - | 120B | 500B | 64.1 | **34.2** | 56.4 | **84.4** | +| [Rho-Math-7B-v0.1](https://huggingface.co/microsoft/rho-math-7b-v0.1) | 7B | OWM | 14B | 10.5B | **66.9** | 31.0 | 54.6 | **84.4** | + + +[Tool-integrated reasoning](https://github.com/microsoft/ToRA) (Code Interpreter): + +| **Model** | **Size** | **SFT Data** | **GSM8k** | **MATH** | **SVAMP** | **ASDiv** | **MAWPS** | **TabMWP** | **GSM-Hard** | **AVG** | +|------------------------------|----------|--------------|-----------|----------|-----------|-----------|-----------|------------|--------------|----------| +| gpt4-early (pal) | - | - | 94.2 | 51.8 | 94.8 | 92.6 | 97.7 | 95.9 | 77.6 | 86.4 | +| gpt-4-turbo-2024-04-09 (cot) | - | - | - | 73.4 | - | - | - | - | - | +| Open-Source Small Models | | | | | | | | | | +| MAmmoTH | 70B | MI-260k | 76.9 | 41.8 | 82.4 | - | - | - | - | - | +| ToRA | 7B | ToRA-69k | 68.8 | 40.1 | 68.2 | 73.9 | 88.8 | 42.4 | 54.6 | 62.4 | +| ToRA | 70B | ToRA-69k | 84.3 | 49.7 | **82.7** | 86.8 | 93.8 | 74.0 | **67.2** | **76.9** | +| DeepSeekMath | 7B | ToRA-69k | 79.8 | **52.0** | 80.1 | **87.1** | 93.8 | **85.8** | 63.1 | 77.4 | +| [Rho-Math-1B-Interpreter-v0.1](https://huggingface.co/microsoft/rho-math-1b-interpreter-v0.1) | 1B | ToRA-69k | 59.4 | 40.6 | 60.7 | 74.2 | 88.6 | 26.7 | 48.1 | 56.9 | +| [Rho-Math-7B-Interpreter-v0.1](https://huggingface.co/microsoft/rho-math-7b-interpreter-v0.1) | 7B | ToRA-69k | 81.3 | **51.8** | 80.8 | 85.5 | **94.5** | 70.1 | 63.1 | 75.3 | + + +## 🚀 Quick Start + + +### Evaluation + +```sh +git clone git@github.com:microsoft/rho.git +cd rho-1/math-evaluation-harness +``` + +Base model few-shot evaluation: + +```sh +bash scripts/run_eval.sh cot microsoft/rho-math-7b-v0.1 +``` + +SFT model (code-interpreter) evaluation: + +```sh +bash scripts/run_eval.sh tora microsoft/rho-math-7b-interpreter-v0.1 +``` + +Our reproduced outputs are provided in `rho-1/outputs.zip`. + + + +## ☕️ Citation + +If you find this repository helpful, please consider citing our paper: + +``` +@misc{lin2024rho1, + title={Rho-1: Not All Tokens Are What You Need}, + author={Zhenghao Lin and Zhibin Gou and Yeyun Gong and Xiao Liu and Yelong Shen and Ruochen Xu and Chen Lin and Yujiu Yang and Jian Jiao and Nan Duan and Weizhu Chen}, + year={2024}, + eprint={2404.07965}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` +## Data Summary +https://huggingface.co/microsoft/rho-math-7b-v0.1/blob/main/data_summary_card.md \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3bf9a87 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "rho-math-7b-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.38.2", + "use_cache": true, + "vocab_size": 32000 +} 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/data_summary_card.md b/data_summary_card.md new file mode 100644 index 0000000..9a73633 --- /dev/null +++ b/data_summary_card.md @@ -0,0 +1,147 @@ + + +# Data Summary for microsoft_rho-math-7b-v0.1 + + + + + +## 1. General information + +**1.0.1 Version of the Summary:** 1.0 + + + +**1.0.2 Last update:** 16-Dec-2025 + + + +## 1.1 Model Developer Identification + +**1.1.1 Model Developer name and contact details:** Microsoft Corporation at One Microsoft Way, Redmond, WA 98052. Tel: 425-882-8080 + + + +## 1.2 Model Identification + +**1.2.1 Versioned model name(s):** Rho-Math-1B-v0.1, Rho-Math-7B-v0.1 + + + +**1.2.2 Model release date:** 12-Apr-2024 + + + +## 1.3 Overall training data size and characteristics + +### 1.3.1 Size of dataset and characteristics + +**1.3.1.A Text training data size:** 1 billion to 1 trillion tokens + + + +**1.3.1.B Text training data content:** math datasets + + + +**1.3.1.C Image training data size:** Not applicable. Images are not part of the training data + + + +**1.3.1.D Image training data content:** Not applicable + + + +**1.3.1.E Audio training data size:** Not applicable. Audio data is not part of the training data + + + +**1.3.1.F Audio training data content:** Not applicable + + + +**1.3.1.G Video training data size:** Not applicable. Audio data is not part of the training data + + + +**1.3.1.H Video training data content:** Not applicable + + + +**1.3.1.I Other training data size:** Not applicable + + + +**1.3.1.J Other training data content:** Not applicable + + + +**1.3.2 Latest date of data acquisition/collection for model training:** 12-Apr-2024 + + + +**1.3.3 Is data collection ongoing to update the model with new data collection after deployment?** No + + + +**1.3.4 Date the training dataset was first used to train the model:** 1-Jan-2024 + + + +**1.3.5 Rationale or purpose of data selection:** Datasets were chosen to focus pretraining on clean, useful math and general-language tokens aligned to desired distributions for improved reasoning and efficiency. + + + +## 2. List of data sources + +### 2.1 Publicly available datasets + +**2.1.1 Have you used publicly available datasets to train the model?** Yes + + + +## 2.2 Private non-publicly available datasets obtained from third parties + +### 2.2.1 Datasets commercially licensed by rights holders or their representatives + +**2.2.1.A Have you concluded transactional commercial licensing agreement(s) with rights holder(s) or with their representatives?** Not applicable + + + +### 2.2.2 Private datasets obtained from other third-parties + +**2.2.2.A Have you obtained private datasets from third parties that are not licensed as described in Section 2.2.1, such as data obtained from providers of private databases, or data intermediaries?** No + + + +## 2.3 Personal Information + +**2.3.1 Was personal data used to train the model?** Microsoft follows all relevant laws and regulations pertaining to personal information + + + +## 2.4 Synthetic data + +**2.4.1 Was any synthetic AI-generated data used to train the model?** Yes + + + +## 3. Data processing aspects + +### 3.1 Respect of reservation of rights from text and data mining exception or limitation + +**3.1.1 Does this dataset include any data protected by copyright, trademark, or patent?** Microsoft follows all required regulations and laws for processing data protected by copyright, trademark, or patent + + + +## 3.2 Other information + +**3.2.1 Does the dataset include information about consumer groups without revealing individual consumer identities?** Microsoft follows all required regulations and laws for protecting consumer identities + + + +**3.2.2 Was the dataset cleaned or modified before model training?** Yes + + + + \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..02fd380 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.38.2" +} diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..4e68a52 --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b247cb22cd965dce0ee6fb046bd7aac24dbba587f88edea096a4d9cbc95688d2 +size 4943162336 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..2591413 --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e6ef6c9def23509a59be8c2b75d0434ee85afffb2721f2365ea4a7502fbf7f +size 4999819336 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..efa2ba6 --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca2969537169a7571caf90505b6fd01f1397bed300287ce76d459388d94fbcd +size 4540516344 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b349bc0 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_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..61607de --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc +size 1795303 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..81730cd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "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 + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}