commit 2873e49b6697e3b74f15ff535889b54413ffcaa8 Author: ModelHub XC Date: Mon May 4 02:57:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: THU-KEG/SIRI-7B-low Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..282bd21 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.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 + +*.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 +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..8f55e30 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +license: apache-2.0 +datasets: +- agentica-org/DeepScaleR-Preview-Dataset +base_model: +- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B +tags: +- reinforcement-learning +language: +- en +- zh +pipeline_tag: text-generation +library_name: transformers +--- + +

+ + SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression +

+ + + +

+ 📃 Paper • 📝 Wandb +

+ +--- + +## 🔍 Overview + +**SIRI (Scaling Iterative Reinforcement Learning with Interleaved Compression)** is a reinforcement-learning–based framework designed to improve the efficiency and accuracy of **Large Reasoning Models (LRMs)**. + +Traditional RL training often causes **overthinking** and long, redundant reasoning traces. Prior methods that compress outputs (length penalties, pruning, or skipping thought tokens) improve efficiency but hurt accuracy. + +SIRI solves this trade-off by **iteratively alternating between compression and expansion of the reasoning budget**, controlled by a cosine length scheduler. This approach dynamically balances concise reasoning with long-horizon exploration. + +

+ pareto_front +

+ +--- + +## 🚀 Key Features + +- **Interleaved Compression–Expansion**: + - *Compression phase*: forces concise, high-density reasoning by limiting rollout length. + - *Expansion phase*: restores longer rollouts to encourage exploration and planning. +- **Token Efficiency without Accuracy Loss**: Unlike previous methods, SIRI improves accuracy *while reducing average token usage*. +- **Iterative RL Training**: Built on GRPO with modifications from DAPO (clip-high/low decoupling, KL removal). +- **Generalization Across Model Sizes**: Validated on both **1.5B** and **7B** models. + +--- + +## 📊 Benchmarks + + +![perf](https://cdn-uploads.huggingface.co/production/uploads/64ed568ccf6118a9379a61b8/0S2d9VZTiaoGI6_N9Vrh2.png) + + +--- + +## 📝 Citation + +```bibtex \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c2066bd --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..e040236 --- /dev/null +++ b/config.json @@ -0,0 +1,60 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.53.3", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..bf9d1d4 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.53.3" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..55a2b43 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928c9e9de970d9425db39ed21972ecdf1c060d2833907157125c8e40da0d0d7f +size 4947409024 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..b23ac3b --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b188cb91577b8f8fe2174663edc3192df81514c46bf7494a977071be09620b22 +size 4914429224 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..4b0335f --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ceecab4e3af0959533102b83baee6b1a7d4e81ef913da9a31eee8923323ea48 +size 4936348312 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..ac4f4c1 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260f4a17e5b02b0dffc85e372a2490f8a0abdbcf89e26d54679e79e0a97d3de5 +size 433085336 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..bc51ac0 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,347 @@ +{ + "metadata": { + "total_parameters": 7615616512, + "total_size": 15231233024 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00004.safetensors", + "model.embed_tokens.weight": "model-00002-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00002-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1a2db24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d252dd4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +}