commit 1af342bcaed03ffba7af141758ff0534026e2f26 Author: ModelHub XC Date: Sun Nov 15 17:48:20 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-7B-Late 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..7b954e9 --- /dev/null +++ b/README.md @@ -0,0 +1,106 @@ +--- +library_name: transformers +pipeline_tag: text-generation +base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B +base_model_relation: finetune +language: +- en +tags: +- optd +- on-policy-distillation +- transition-distillation +- reasoning +- text-generation-inference +--- + +# OPTD-DeepSeek-R1-Distill-Qwen-7B-Late + +[arXiv](https://arxiv.org/abs/2610.28048) · [Hugging Face Paper](https://huggingface.co/papers/2610.28048) · [All OPTD models](https://huggingface.co/collections/ModalityDance/optd) + +An OPTD model trained from [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) with specialists in **mathematics and coding**. This is a complete model that can be used directly for text generation. + +OPTD teaches a student both the teacher’s final prediction and how its predictions change across layers, using responses generated by the student. This checkpoint accompanies *On-Policy Transition Distillation*. + +**Late** identifies the placement of transition supervision during training. Mid and Late use different sets of layers; these names do not denote release versions or a quality ranking. + +Use the model’s **native reasoning chat template**, supplied with its tokenizer. + +## Quick start + +Install PyTorch for your hardware, Transformers, and Accelerate: + +```bash +python -m pip install torch transformers accelerate +``` + +The example below uses BF16. Teacher models and the OPTD training framework are not required for inference. + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-7B-Late" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, torch_dtype=torch.bfloat16, device_map="auto" +) +messages = [{"role": "user", "content": "Solve 2x + 5 = 17."}] +text = tokenizer.apply_chat_template( + messages, tokenize=False, add_generation_prompt=True +) +inputs = tokenizer(text, add_special_tokens=False, return_tensors="pt").to(model.device) +with torch.inference_mode(): + output = model.generate( + **inputs, max_new_tokens=1024, do_sample=True, temperature=0.7, top_p=0.95 + ) +response = output[0, inputs.input_ids.shape[-1]:] +print(tokenizer.decode(response, skip_special_tokens=True)) +``` + +The short generation limit is for the example. Paper evaluation uses benchmark-specific token limits and sample counts. + +## Download + +```bash +hf download ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-7B-Late --local-dir models/optd-deepseek-r1-distill-qwen-7b-late +``` + +Install `huggingface_hub` to use the `hf` command. To load a downloaded copy, replace `model_id` with its local directory. + +## Training and release details + +
+Configuration and file contents + +- Student initialization: `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B`. +- Training updates: 100. +- Intermediate layers (zero-based): 13 / 17 / 21. +- Training domains: mathematics and coding. +- Full BF16 safetensors weights, tokenizer, and generation configuration are included. +- `training_metadata.json` records the training configuration; `checksums.json` records checkpoint/tokenizer SHA256 hashes. +- Optimizer state is not included. + +
+ +## Evaluation + +Compare this checkpoint using the paper’s prompt mode, dataset revisions, sample counts, and graders. The example above demonstrates inference rather than reproducing benchmark scores. Generated answers can be incorrect; execute generated code only in an isolated sandbox. + +## Citation + + +```bibtex +@misc{optd2026, + title = {On-Policy Transition Distillation}, + author = {You, Runyang and Li, Yongqi and Yu, Tiezheng and Li, Wenjie}, + year = {2026}, + eprint = {2610.28048}, + archivePrefix = {arXiv}, + primaryClass = {cs.CL}, + url = {https://arxiv.org/abs/2610.28048} +} +``` + +## License and attribution + +The underlying student and specialist models retain their respective upstream license terms. Consult the linked base model's license and notices before redistribution or deployment. No new license grant for upstream model weights is implied by this model card. 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/checksums.json b/checksums.json new file mode 100644 index 0000000..e11b0a8 --- /dev/null +++ b/checksums.json @@ -0,0 +1,46 @@ +{ + "model-00003-of-00004.safetensors": { + "sha256": "8008b29b18dae13566cecf180bb0fe13f3aa26eb366522262a534d09426be602", + "bytes": 4921623440 + }, + "model-00002-of-00004.safetensors": { + "sha256": "f1f6a014a9661e27c03cbfcb627d2eabfa5bef10e2003a35f5dec390423d3fa3", + "bytes": 4932739176 + }, + "config.json": { + "sha256": "65283543e725fa3c4cf8177be8ecdc45ac34736e4f26b51965f7ba8feadbbeac", + "bytes": 1363 + }, + "model-00004-of-00004.safetensors": { + "sha256": "e453a3e58afe891dbc7efcd80a60fd084467aebc80fcc565e740124801a58fc1", + "bytes": 495478448 + }, + "tokenizer_config.json": { + "sha256": "55edc67ee25d8e0d4b7a13036ee61cdb880b49db4398533cc6a29710d1790ade", + "bytes": 4490 + }, + "chat_template.jinja": { + "sha256": "56a1447ad31926fdc21fb07e56e5642bd9c850c4f52d8c8af7bbe5f079a84f5f", + "bytes": 2246 + }, + "model.safetensors.index.json": { + "sha256": "8a8a05fae84551dced25bd0237f0cd131d2e3d89eaa170aae2646d05f19d0566", + "bytes": 27788 + }, + "special_tokens_map.json": { + "sha256": "59cda48bbe8bab9d61ffb410e6e3c07b6d98bff73cee7c88ff8b51f95f21ab1c", + "bytes": 485 + }, + "tokenizer.json": { + "sha256": "e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893", + "bytes": 11422778 + }, + "generation_config.json": { + "sha256": "994ffcc2da754604dd754028c2bb0ea5ac52747f206d73f62c72543a6ee96664", + "bytes": 181 + }, + "model-00001-of-00004.safetensors": { + "sha256": "285a07ed380b553636b3ee7f2a04ee43583b368551cd656413c1fa4652170344", + "bytes": 4881430840 + } +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..244d092 --- /dev/null +++ b/config.json @@ -0,0 +1,60 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "dtype": "bfloat16", + "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, + "transformers_version": "4.57.6", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..4c2d8e1 --- /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": "4.57.6" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..86acf4d --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285a07ed380b553636b3ee7f2a04ee43583b368551cd656413c1fa4652170344 +size 4881430840 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..23b780f --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f6a014a9661e27c03cbfcb627d2eabfa5bef10e2003a35f5dec390423d3fa3 +size 4932739176 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..effe5ea --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8008b29b18dae13566cecf180bb0fe13f3aa26eb366522262a534d09426be602 +size 4921623440 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..c81d3f8 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e453a3e58afe891dbc7efcd80a60fd084467aebc80fcc565e740124801a58fc1 +size 495478448 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..4829237 --- /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-00003-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00004-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-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-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-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00003-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-00003-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-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-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-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-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-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-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-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-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-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-00001-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-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-00001-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-00001-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-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-00001-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-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-00003-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-00002-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-00003-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-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-00001-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00003-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-00001-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-00003-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-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-00001-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-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-00003-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-00003-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-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-00003-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-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-00004-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-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-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-00001-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-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-00002-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-00001-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-00001-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-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-00004-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-00003-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-00001-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00001-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-00001-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00001-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-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00001-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-00003-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-00003-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-00002-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-00004-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-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-00001-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-00001-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-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-00004-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-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-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-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-00001-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-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-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-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-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-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-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-00002-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00004-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-00004-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00004-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-00002-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-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-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-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-00003-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-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-00003-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 +} diff --git a/training_metadata.json b/training_metadata.json new file mode 100644 index 0000000..5ebc3f9 --- /dev/null +++ b/training_metadata.json @@ -0,0 +1,14 @@ +{ + "repo_id": "ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-7B-Late", + "base_model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", + "step": 100, + "layers": [ + 13, + 17, + 21 + ], + "domains": [ + "math", + "coding" + ] +}