mzli commited on
Commit ·
cd2a237
1
Parent(s): 022b3c4
Upload SciJudge-4B model weights and configs
Browse files- .gitattributes +1 -0
- README.md +60 -0
- added_tokens.json +28 -0
- args.json +514 -0
- chat_template.jinja +61 -0
- config.json +68 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +407 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 6 |
+
tags:
|
| 7 |
+
- scientific-evaluation
|
| 8 |
+
- citation-prediction
|
| 9 |
+
- preference-learning
|
| 10 |
+
- GRPO
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
library_name: transformers
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# SciJudge-Qwen3-4B
|
| 16 |
+
|
| 17 |
+
SciJudge-Qwen3-4B is a fine-tuned language model for **scientific paper evaluation**. Given two academic papers' metadata (title, abstract, publication date), it predicts which paper has a higher citation count — serving as a proxy for assessing research impact and "scientific taste."
|
| 18 |
+
|
| 19 |
+
This model is part of the paper: **AI Can Learn Scientific Taste**.
|
| 20 |
+
|
| 21 |
+
## Usage
|
| 22 |
+
|
| 23 |
+
```python
|
| 24 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 25 |
+
|
| 26 |
+
model_name = "OpenMOSS-Team/SciJudge-4B"
|
| 27 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 28 |
+
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="bfloat16", device_map="auto")
|
| 29 |
+
|
| 30 |
+
messages = [
|
| 31 |
+
{"role": "system", "content": "You are a helpful assistant. You first think about the reasoning process in your mind and then provide the user with the answer."},
|
| 32 |
+
{"role": "user", "content": "Today is 2025-12-10. Based on the titles, abstracts, and publication dates of the following two papers A and B, determine which paper has a higher citation count.\nShow your reasoning process in <reason> </reason> tags. And return the final answer in <answer> </answer> tags. The final answer should contain only 'A' or 'B'.\n\nPaper A:\nTitle: ...\nAbstract: ...\nDate: ...\n\nPaper B:\nTitle: ...\nAbstract: ...\nDate: ..."}
|
| 33 |
+
]
|
| 34 |
+
|
| 35 |
+
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 36 |
+
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
| 37 |
+
outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.7, top_p=0.8, top_k=20)
|
| 38 |
+
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
|
| 39 |
+
print(response)
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
## Training Details
|
| 43 |
+
|
| 44 |
+
- **Base model:** Qwen3-4B-Instruct-2507
|
| 45 |
+
- **Training method:** GRPO (Generative Reward Policy Optimization) with DAPO loss
|
| 46 |
+
- **Training data:** 720,341 preference pairs from arXiv papers
|
| 47 |
+
- **Learning rate:** 8e-7 (cosine schedule, 5% warmup)
|
| 48 |
+
- **Batch size:** 8 per device × 64 GPUs × 2 gradient accumulation = 1024 effective
|
| 49 |
+
- **Optimizer:** AdamW (β1=0.9, β2=0.95, weight decay=0.1)
|
| 50 |
+
- **Precision:** bfloat16
|
| 51 |
+
- **KL coefficient (β):** 0.03
|
| 52 |
+
|
| 53 |
+
## Citation
|
| 54 |
+
|
| 55 |
+
```bibtex
|
| 56 |
+
@article{scijudge2025,
|
| 57 |
+
title={AI Can Learn Scientific Taste},
|
| 58 |
+
year={2025}
|
| 59 |
+
}
|
| 60 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
args.json
ADDED
|
@@ -0,0 +1,514 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/saves/Qwen3-4B-Instruct-2507/grpo_pair_2102715_citeyear_subcategory2_abs8_rel0.3/v0-20251231-011328",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": false,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"eval_strategy": "no",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 8,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 2,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 8e-07,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 1.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "cosine",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.05,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/saves/Qwen3-4B-Instruct-2507/grpo_pair_2102715_citeyear_subcategory2_abs8_rel0.3/v0-20251231-011328/runs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 10,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 500.0,
|
| 39 |
+
"save_total_limit": 50,
|
| 40 |
+
"save_safetensors": true,
|
| 41 |
+
"save_on_each_node": false,
|
| 42 |
+
"save_only_model": false,
|
| 43 |
+
"restore_callback_states_from_checkpoint": false,
|
| 44 |
+
"no_cuda": false,
|
| 45 |
+
"use_cpu": false,
|
| 46 |
+
"use_mps_device": false,
|
| 47 |
+
"seed": 42,
|
| 48 |
+
"data_seed": 42,
|
| 49 |
+
"jit_mode_eval": false,
|
| 50 |
+
"bf16": true,
|
| 51 |
+
"fp16": false,
|
| 52 |
+
"fp16_opt_level": "O1",
|
| 53 |
+
"half_precision_backend": "auto",
|
| 54 |
+
"bf16_full_eval": false,
|
| 55 |
+
"fp16_full_eval": false,
|
| 56 |
+
"tf32": null,
|
| 57 |
+
"local_rank": 0,
|
| 58 |
+
"ddp_backend": null,
|
| 59 |
+
"tpu_num_cores": null,
|
| 60 |
+
"tpu_metrics_debug": false,
|
| 61 |
+
"debug": null,
|
| 62 |
+
"dataloader_drop_last": false,
|
| 63 |
+
"eval_steps": 500.0,
|
| 64 |
+
"dataloader_num_workers": 1,
|
| 65 |
+
"dataloader_prefetch_factor": null,
|
| 66 |
+
"past_index": -1,
|
| 67 |
+
"run_name": "/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/saves/Qwen3-4B-Instruct-2507/grpo_pair_2102715_citeyear_subcategory2_abs8_rel0.3/v0-20251231-011328",
|
| 68 |
+
"disable_tqdm": null,
|
| 69 |
+
"remove_unused_columns": false,
|
| 70 |
+
"label_names": null,
|
| 71 |
+
"load_best_model_at_end": false,
|
| 72 |
+
"metric_for_best_model": "loss",
|
| 73 |
+
"greater_is_better": false,
|
| 74 |
+
"ignore_data_skip": false,
|
| 75 |
+
"fsdp": null,
|
| 76 |
+
"fsdp_min_num_params": 0,
|
| 77 |
+
"fsdp_config": null,
|
| 78 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 79 |
+
"accelerator_config": {
|
| 80 |
+
"dispatch_batches": false
|
| 81 |
+
},
|
| 82 |
+
"parallelism_config": null,
|
| 83 |
+
"deepspeed": {
|
| 84 |
+
"fp16": {
|
| 85 |
+
"enabled": "auto",
|
| 86 |
+
"loss_scale": 0,
|
| 87 |
+
"loss_scale_window": 1000,
|
| 88 |
+
"initial_scale_power": 16,
|
| 89 |
+
"hysteresis": 2,
|
| 90 |
+
"min_loss_scale": 1
|
| 91 |
+
},
|
| 92 |
+
"bf16": {
|
| 93 |
+
"enabled": "auto"
|
| 94 |
+
},
|
| 95 |
+
"zero_optimization": {
|
| 96 |
+
"stage": 2,
|
| 97 |
+
"offload_optimizer": {
|
| 98 |
+
"device": "none",
|
| 99 |
+
"pin_memory": true
|
| 100 |
+
},
|
| 101 |
+
"allgather_partitions": true,
|
| 102 |
+
"allgather_bucket_size": 200000000.0,
|
| 103 |
+
"overlap_comm": false,
|
| 104 |
+
"reduce_scatter": true,
|
| 105 |
+
"reduce_bucket_size": 200000000.0,
|
| 106 |
+
"contiguous_gradients": true
|
| 107 |
+
},
|
| 108 |
+
"gradient_accumulation_steps": "auto",
|
| 109 |
+
"gradient_clipping": "auto",
|
| 110 |
+
"steps_per_print": 2000,
|
| 111 |
+
"train_batch_size": "auto",
|
| 112 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 113 |
+
"wall_clock_breakdown": false
|
| 114 |
+
},
|
| 115 |
+
"label_smoothing_factor": 0.0,
|
| 116 |
+
"optim": "adamw_torch_fused",
|
| 117 |
+
"optim_args": null,
|
| 118 |
+
"adafactor": false,
|
| 119 |
+
"group_by_length": false,
|
| 120 |
+
"length_column_name": "length",
|
| 121 |
+
"report_to": [
|
| 122 |
+
"tensorboard"
|
| 123 |
+
],
|
| 124 |
+
"project": "huggingface",
|
| 125 |
+
"trackio_space_id": "trackio",
|
| 126 |
+
"ddp_find_unused_parameters": null,
|
| 127 |
+
"ddp_bucket_cap_mb": null,
|
| 128 |
+
"ddp_broadcast_buffers": null,
|
| 129 |
+
"dataloader_pin_memory": true,
|
| 130 |
+
"dataloader_persistent_workers": false,
|
| 131 |
+
"skip_memory_metrics": true,
|
| 132 |
+
"use_legacy_prediction_loop": false,
|
| 133 |
+
"push_to_hub": false,
|
| 134 |
+
"resume_from_checkpoint": null,
|
| 135 |
+
"hub_model_id": null,
|
| 136 |
+
"hub_strategy": "every_save",
|
| 137 |
+
"hub_token": null,
|
| 138 |
+
"hub_private_repo": null,
|
| 139 |
+
"hub_always_push": false,
|
| 140 |
+
"hub_revision": null,
|
| 141 |
+
"gradient_checkpointing": true,
|
| 142 |
+
"gradient_checkpointing_kwargs": null,
|
| 143 |
+
"include_inputs_for_metrics": false,
|
| 144 |
+
"include_for_metrics": [],
|
| 145 |
+
"eval_do_concat_batches": true,
|
| 146 |
+
"fp16_backend": "auto",
|
| 147 |
+
"push_to_hub_model_id": null,
|
| 148 |
+
"push_to_hub_organization": null,
|
| 149 |
+
"push_to_hub_token": null,
|
| 150 |
+
"mp_parameters": "",
|
| 151 |
+
"auto_find_batch_size": false,
|
| 152 |
+
"full_determinism": false,
|
| 153 |
+
"torchdynamo": null,
|
| 154 |
+
"ray_scope": "last",
|
| 155 |
+
"ddp_timeout": 18000000,
|
| 156 |
+
"torch_compile": false,
|
| 157 |
+
"torch_compile_backend": null,
|
| 158 |
+
"torch_compile_mode": null,
|
| 159 |
+
"include_tokens_per_second": false,
|
| 160 |
+
"include_num_input_tokens_seen": false,
|
| 161 |
+
"neftune_noise_alpha": null,
|
| 162 |
+
"optim_target_modules": null,
|
| 163 |
+
"batch_eval_metrics": false,
|
| 164 |
+
"eval_on_start": false,
|
| 165 |
+
"use_liger_kernel": false,
|
| 166 |
+
"liger_kernel_config": null,
|
| 167 |
+
"eval_use_gather_object": false,
|
| 168 |
+
"average_tokens_across_devices": true,
|
| 169 |
+
"sortish_sampler": false,
|
| 170 |
+
"predict_with_generate": false,
|
| 171 |
+
"generation_max_length": null,
|
| 172 |
+
"generation_num_beams": null,
|
| 173 |
+
"generation_config": null,
|
| 174 |
+
"tuner_backend": "peft",
|
| 175 |
+
"vit_gradient_checkpointing": null,
|
| 176 |
+
"router_aux_loss_coef": 0.0,
|
| 177 |
+
"enable_dft_loss": false,
|
| 178 |
+
"enable_channel_loss": false,
|
| 179 |
+
"check_model": false,
|
| 180 |
+
"acc_strategy": "token",
|
| 181 |
+
"train_dataloader_shuffle": true,
|
| 182 |
+
"max_epochs": null,
|
| 183 |
+
"aligner_lr": null,
|
| 184 |
+
"vit_lr": null,
|
| 185 |
+
"use_logits_to_keep": null,
|
| 186 |
+
"ds3_gather_for_generation": true,
|
| 187 |
+
"resume_only_model": false,
|
| 188 |
+
"optimizer": null,
|
| 189 |
+
"loss_type": "dapo",
|
| 190 |
+
"metric": null,
|
| 191 |
+
"eval_use_evalscope": false,
|
| 192 |
+
"eval_dataset": [],
|
| 193 |
+
"eval_dataset_args": null,
|
| 194 |
+
"eval_limit": null,
|
| 195 |
+
"eval_generation_config": null,
|
| 196 |
+
"extra_eval_args": null,
|
| 197 |
+
"use_flash_ckpt": false,
|
| 198 |
+
"use_ray": false,
|
| 199 |
+
"ray_exp_name": null,
|
| 200 |
+
"device_groups": null,
|
| 201 |
+
"model": "/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/models/Qwen3-4B-Instruct-2507",
|
| 202 |
+
"model_type": "qwen3_nothinking",
|
| 203 |
+
"model_revision": null,
|
| 204 |
+
"task_type": "causal_lm",
|
| 205 |
+
"torch_dtype": "bfloat16",
|
| 206 |
+
"attn_impl": null,
|
| 207 |
+
"new_special_tokens": [],
|
| 208 |
+
"num_labels": null,
|
| 209 |
+
"problem_type": null,
|
| 210 |
+
"rope_scaling": null,
|
| 211 |
+
"device_map": null,
|
| 212 |
+
"max_memory": {},
|
| 213 |
+
"max_model_len": null,
|
| 214 |
+
"local_repo_path": null,
|
| 215 |
+
"init_strategy": null,
|
| 216 |
+
"template": "qwen3_nothinking",
|
| 217 |
+
"system": null,
|
| 218 |
+
"max_length": 2048,
|
| 219 |
+
"truncation_strategy": "delete",
|
| 220 |
+
"max_pixels": null,
|
| 221 |
+
"agent_template": null,
|
| 222 |
+
"norm_bbox": null,
|
| 223 |
+
"use_chat_template": true,
|
| 224 |
+
"padding_free": false,
|
| 225 |
+
"padding_side": "right",
|
| 226 |
+
"loss_scale": "last_round",
|
| 227 |
+
"sequence_parallel_size": 1,
|
| 228 |
+
"response_prefix": null,
|
| 229 |
+
"template_backend": "swift",
|
| 230 |
+
"dataset": [
|
| 231 |
+
"/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/data/train/pair_2102715_citeyear_subcategory2_abs8_rel0.3.jsonl"
|
| 232 |
+
],
|
| 233 |
+
"val_dataset": [],
|
| 234 |
+
"cached_dataset": [],
|
| 235 |
+
"cached_val_dataset": [],
|
| 236 |
+
"split_dataset_ratio": 0.0,
|
| 237 |
+
"dataset_num_proc": 8,
|
| 238 |
+
"load_from_cache_file": true,
|
| 239 |
+
"dataset_shuffle": false,
|
| 240 |
+
"val_dataset_shuffle": false,
|
| 241 |
+
"streaming": false,
|
| 242 |
+
"interleave_prob": null,
|
| 243 |
+
"stopping_strategy": "first_exhausted",
|
| 244 |
+
"shuffle_buffer_size": 1000,
|
| 245 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 246 |
+
"columns": {},
|
| 247 |
+
"strict": false,
|
| 248 |
+
"model_name": null,
|
| 249 |
+
"model_author": null,
|
| 250 |
+
"custom_dataset_info": [],
|
| 251 |
+
"quant_method": null,
|
| 252 |
+
"quant_bits": null,
|
| 253 |
+
"hqq_axis": null,
|
| 254 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 255 |
+
"bnb_4bit_quant_type": "nf4",
|
| 256 |
+
"bnb_4bit_use_double_quant": true,
|
| 257 |
+
"bnb_4bit_quant_storage": null,
|
| 258 |
+
"max_new_tokens": 4096,
|
| 259 |
+
"temperature": 1.0,
|
| 260 |
+
"top_k": 50,
|
| 261 |
+
"top_p": 0.85,
|
| 262 |
+
"repetition_penalty": 1.0,
|
| 263 |
+
"num_beams": 1,
|
| 264 |
+
"stream": false,
|
| 265 |
+
"stop_words": [],
|
| 266 |
+
"logprobs": false,
|
| 267 |
+
"top_logprobs": null,
|
| 268 |
+
"ckpt_dir": null,
|
| 269 |
+
"lora_modules": [],
|
| 270 |
+
"train_type": "full",
|
| 271 |
+
"adapters": [],
|
| 272 |
+
"external_plugins": [
|
| 273 |
+
"/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/code/plugin.py"
|
| 274 |
+
],
|
| 275 |
+
"model_kwargs": {},
|
| 276 |
+
"load_args": false,
|
| 277 |
+
"load_data_args": false,
|
| 278 |
+
"packing": false,
|
| 279 |
+
"packing_length": null,
|
| 280 |
+
"packing_num_proc": 1,
|
| 281 |
+
"lazy_tokenize": false,
|
| 282 |
+
"custom_register_path": [],
|
| 283 |
+
"use_hf": false,
|
| 284 |
+
"ignore_args_error": false,
|
| 285 |
+
"use_swift_lora": false,
|
| 286 |
+
"freeze_parameters": [],
|
| 287 |
+
"freeze_parameters_regex": null,
|
| 288 |
+
"freeze_parameters_ratio": 0.0,
|
| 289 |
+
"trainable_parameters": [],
|
| 290 |
+
"trainable_parameters_regex": null,
|
| 291 |
+
"freeze_llm": false,
|
| 292 |
+
"freeze_vit": true,
|
| 293 |
+
"freeze_aligner": true,
|
| 294 |
+
"target_modules": [
|
| 295 |
+
"all-linear"
|
| 296 |
+
],
|
| 297 |
+
"target_regex": null,
|
| 298 |
+
"target_parameters": null,
|
| 299 |
+
"modules_to_save": [],
|
| 300 |
+
"lora_rank": 8,
|
| 301 |
+
"lora_alpha": 32,
|
| 302 |
+
"lora_dropout": 0.05,
|
| 303 |
+
"lora_bias": "none",
|
| 304 |
+
"lora_dtype": null,
|
| 305 |
+
"lorap_lr_ratio": null,
|
| 306 |
+
"use_rslora": false,
|
| 307 |
+
"use_dora": false,
|
| 308 |
+
"lora_ga_batch_size": 2,
|
| 309 |
+
"lora_ga_iters": 2,
|
| 310 |
+
"lora_ga_max_length": 1024,
|
| 311 |
+
"lora_ga_direction": "ArB2r",
|
| 312 |
+
"lora_ga_scale": "stable",
|
| 313 |
+
"lora_ga_stable_gamma": 16,
|
| 314 |
+
"init_weights": true,
|
| 315 |
+
"fourier_n_frequency": 2000,
|
| 316 |
+
"fourier_scaling": 300.0,
|
| 317 |
+
"boft_block_size": 4,
|
| 318 |
+
"boft_block_num": 0,
|
| 319 |
+
"boft_n_butterfly_factor": 1,
|
| 320 |
+
"boft_dropout": 0.0,
|
| 321 |
+
"vera_rank": 256,
|
| 322 |
+
"vera_projection_prng_key": 0,
|
| 323 |
+
"vera_dropout": 0.0,
|
| 324 |
+
"vera_d_initial": 0.1,
|
| 325 |
+
"adapter_act": "gelu",
|
| 326 |
+
"adapter_length": 128,
|
| 327 |
+
"use_galore": false,
|
| 328 |
+
"galore_target_modules": null,
|
| 329 |
+
"galore_rank": 128,
|
| 330 |
+
"galore_update_proj_gap": 50,
|
| 331 |
+
"galore_scale": 1.0,
|
| 332 |
+
"galore_proj_type": "std",
|
| 333 |
+
"galore_optim_per_parameter": false,
|
| 334 |
+
"galore_with_embedding": false,
|
| 335 |
+
"galore_quantization": false,
|
| 336 |
+
"galore_proj_quant": false,
|
| 337 |
+
"galore_proj_bits": 4,
|
| 338 |
+
"galore_proj_group_size": 256,
|
| 339 |
+
"galore_cos_threshold": 0.4,
|
| 340 |
+
"galore_gamma_proj": 2,
|
| 341 |
+
"galore_queue_size": 5,
|
| 342 |
+
"adalora_target_r": 8,
|
| 343 |
+
"adalora_init_r": 12,
|
| 344 |
+
"adalora_tinit": 0,
|
| 345 |
+
"adalora_tfinal": 0,
|
| 346 |
+
"adalora_deltaT": 1,
|
| 347 |
+
"adalora_beta1": 0.85,
|
| 348 |
+
"adalora_beta2": 0.85,
|
| 349 |
+
"adalora_orth_reg_weight": 0.5,
|
| 350 |
+
"llamapro_num_new_blocks": 4,
|
| 351 |
+
"llamapro_num_groups": null,
|
| 352 |
+
"lisa_activated_layers": 0,
|
| 353 |
+
"lisa_step_interval": 20,
|
| 354 |
+
"reft_layer_key": null,
|
| 355 |
+
"reft_layers": null,
|
| 356 |
+
"reft_rank": 4,
|
| 357 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 358 |
+
"reft_args": null,
|
| 359 |
+
"swanlab_token": null,
|
| 360 |
+
"swanlab_project": null,
|
| 361 |
+
"swanlab_workspace": null,
|
| 362 |
+
"swanlab_exp_name": null,
|
| 363 |
+
"swanlab_lark_webhook_url": null,
|
| 364 |
+
"swanlab_lark_secret": null,
|
| 365 |
+
"swanlab_mode": "cloud",
|
| 366 |
+
"add_version": true,
|
| 367 |
+
"create_checkpoint_symlink": false,
|
| 368 |
+
"zero_hpz_partition_size": null,
|
| 369 |
+
"deepspeed_autotp_size": null,
|
| 370 |
+
"early_stop_interval": null,
|
| 371 |
+
"sft_alpha": 0,
|
| 372 |
+
"chord_sft_dataset": [],
|
| 373 |
+
"chord_sft_per_device_train_batch_size": null,
|
| 374 |
+
"chord_enable_phi_function": false,
|
| 375 |
+
"chord_mu_warmup_steps": null,
|
| 376 |
+
"chord_mu_decay_steps": null,
|
| 377 |
+
"chord_mu_peak": null,
|
| 378 |
+
"chord_mu_valley": null,
|
| 379 |
+
"reward_model": null,
|
| 380 |
+
"reward_adapters": [],
|
| 381 |
+
"reward_model_type": null,
|
| 382 |
+
"reward_model_revision": null,
|
| 383 |
+
"num_ppo_epochs": 4,
|
| 384 |
+
"whiten_rewards": false,
|
| 385 |
+
"kl_coef": 0.05,
|
| 386 |
+
"cliprange": 0.2,
|
| 387 |
+
"vf_coef": 0.1,
|
| 388 |
+
"cliprange_value": 0.2,
|
| 389 |
+
"gamma": 1.0,
|
| 390 |
+
"lam": 0.95,
|
| 391 |
+
"num_mini_batches": 1,
|
| 392 |
+
"local_rollout_forward_batch_size": 64,
|
| 393 |
+
"num_sample_generations": 10,
|
| 394 |
+
"response_length": 4096,
|
| 395 |
+
"missing_eos_penalty": null,
|
| 396 |
+
"vllm_gpu_memory_utilization": 0.5,
|
| 397 |
+
"vllm_tensor_parallel_size": 8,
|
| 398 |
+
"vllm_pipeline_parallel_size": 1,
|
| 399 |
+
"vllm_enable_expert_parallel": false,
|
| 400 |
+
"vllm_max_num_seqs": null,
|
| 401 |
+
"vllm_max_model_len": 6144,
|
| 402 |
+
"vllm_disable_custom_all_reduce": true,
|
| 403 |
+
"vllm_enforce_eager": false,
|
| 404 |
+
"vllm_limit_mm_per_prompt": null,
|
| 405 |
+
"vllm_max_lora_rank": 16,
|
| 406 |
+
"vllm_enable_prefix_caching": true,
|
| 407 |
+
"vllm_use_async_engine": false,
|
| 408 |
+
"vllm_quantization": null,
|
| 409 |
+
"vllm_reasoning_parser": null,
|
| 410 |
+
"vllm_disable_cascade_attn": false,
|
| 411 |
+
"vllm_mm_processor_cache_gb": null,
|
| 412 |
+
"vllm_speculative_config": null,
|
| 413 |
+
"vllm_engine_kwargs": {},
|
| 414 |
+
"vllm_data_parallel_size": 1,
|
| 415 |
+
"use_vllm": true,
|
| 416 |
+
"vllm_mode": "colocate",
|
| 417 |
+
"vllm_enable_lora": false,
|
| 418 |
+
"vllm_server_base_url": null,
|
| 419 |
+
"vllm_server_host": null,
|
| 420 |
+
"vllm_server_port": [
|
| 421 |
+
8000
|
| 422 |
+
],
|
| 423 |
+
"vllm_server_timeout": 240.0,
|
| 424 |
+
"vllm_server_group_port": [
|
| 425 |
+
51216
|
| 426 |
+
],
|
| 427 |
+
"enable_flattened_weight_sync": true,
|
| 428 |
+
"async_generate": false,
|
| 429 |
+
"sleep_level": 0,
|
| 430 |
+
"move_model_batches": 8,
|
| 431 |
+
"offload_optimizer": false,
|
| 432 |
+
"offload_model": false,
|
| 433 |
+
"wandb_log_unique_prompts": null,
|
| 434 |
+
"epsilon": 0.2,
|
| 435 |
+
"epsilon_high": 0.25,
|
| 436 |
+
"delta": null,
|
| 437 |
+
"cosine_min_len_value_wrong": -0.5,
|
| 438 |
+
"cosine_max_len_value_wrong": 0.0,
|
| 439 |
+
"cosine_min_len_value_correct": 1.0,
|
| 440 |
+
"cosine_max_len_value_correct": 0.5,
|
| 441 |
+
"cosine_max_len": null,
|
| 442 |
+
"repetition_n_grams": 3,
|
| 443 |
+
"repetition_max_penalty": -1.0,
|
| 444 |
+
"reward_model_plugin": null,
|
| 445 |
+
"sync_ref_model": false,
|
| 446 |
+
"ref_model_sync_steps": 512,
|
| 447 |
+
"ref_model_mixup_alpha": 0.6,
|
| 448 |
+
"multi_turn_scheduler": null,
|
| 449 |
+
"max_turns": null,
|
| 450 |
+
"completion_length_limit_scope": "per_round",
|
| 451 |
+
"vllm_server_pass_dataset": false,
|
| 452 |
+
"dynamic_sample": true,
|
| 453 |
+
"max_resample_times": 0,
|
| 454 |
+
"overlong_filter": false,
|
| 455 |
+
"soft_max_length": null,
|
| 456 |
+
"soft_cache_length": null,
|
| 457 |
+
"scale_rewards": "group",
|
| 458 |
+
"log_entropy": false,
|
| 459 |
+
"top_entropy_quantile": 1.0,
|
| 460 |
+
"importance_sampling_level": "token",
|
| 461 |
+
"tau_pos": 1.0,
|
| 462 |
+
"tau_neg": 1.05,
|
| 463 |
+
"advantage_estimator": "grpo",
|
| 464 |
+
"kl_in_reward": false,
|
| 465 |
+
"generation_batch_size": null,
|
| 466 |
+
"steps_per_generation": null,
|
| 467 |
+
"rollout_importance_sampling_mode": null,
|
| 468 |
+
"rollout_importance_sampling_threshold": 2.0,
|
| 469 |
+
"log_rollout_offpolicy_metrics": false,
|
| 470 |
+
"num_generations": 8,
|
| 471 |
+
"reward_funcs": [
|
| 472 |
+
"external_preference",
|
| 473 |
+
"format"
|
| 474 |
+
],
|
| 475 |
+
"reward_weights": null,
|
| 476 |
+
"log_completions": true,
|
| 477 |
+
"num_iterations": 1,
|
| 478 |
+
"teacher_model": null,
|
| 479 |
+
"teacher_adapters": [],
|
| 480 |
+
"teacher_model_type": null,
|
| 481 |
+
"teacher_model_revision": null,
|
| 482 |
+
"teacher_deepspeed": null,
|
| 483 |
+
"rlhf_type": "grpo",
|
| 484 |
+
"ref_model": "/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/models/Qwen3-4B-Instruct-2507",
|
| 485 |
+
"ref_adapters": [],
|
| 486 |
+
"ref_model_type": "qwen3_nothinking",
|
| 487 |
+
"ref_model_revision": null,
|
| 488 |
+
"beta": 0.03,
|
| 489 |
+
"label_smoothing": 0,
|
| 490 |
+
"max_completion_length": 4096,
|
| 491 |
+
"rpo_alpha": null,
|
| 492 |
+
"ld_alpha": null,
|
| 493 |
+
"discopop_tau": 0.05,
|
| 494 |
+
"loss_weights": null,
|
| 495 |
+
"cpo_alpha": 1.0,
|
| 496 |
+
"simpo_gamma": 1,
|
| 497 |
+
"desirable_weight": 1.0,
|
| 498 |
+
"undesirable_weight": 1.0,
|
| 499 |
+
"center_rewards_coefficient": null,
|
| 500 |
+
"lmbda": 0.5,
|
| 501 |
+
"seq_kd": false,
|
| 502 |
+
"offload_teacher_model": false,
|
| 503 |
+
"rank": 0,
|
| 504 |
+
"global_world_size": 64,
|
| 505 |
+
"local_world_size": 8,
|
| 506 |
+
"model_suffix": "Qwen3-4B-Instruct-2507",
|
| 507 |
+
"model_info": "ModelInfo(model_type='qwen3_nothinking', model_dir='/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/models/Qwen3-4B-Instruct-2507', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
|
| 508 |
+
"model_meta": "ModelMeta(model_type='qwen3_nothinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Instruct-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_nothinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x7fc1a9b92950>, model_arch=None, architectures=['Qwen3MoeForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
|
| 509 |
+
"model_dir": "/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/models/Qwen3-4B-Instruct-2507",
|
| 510 |
+
"_val_dataset_exists": [],
|
| 511 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 512 |
+
"evaluation_strategy": "steps",
|
| 513 |
+
"training_args": "GRPOConfig(output_dir='/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/saves/Qwen3-4B-Instruct-2507/grpo_pair_2102715_citeyear_subcategory2_abs8_rel0.3/v0-20251231-011328', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=8, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=8e-07, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/saves/Qwen3-4B-Instruct-2507/grpo_pair_2102715_citeyear_subcategory2_abs8_rel0.3/v0-20251231-011328/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=50, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=True, eval_steps=500.0, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='/inspire/ssd/project/embodied-multimodality/limingzhe-CZXS25250069/ResearchPM/saves/Qwen3-4B-Instruct-2507/grpo_pair_2102715_citeyear_subcategory2_abs8_rel0.3/v0-20251231-011328', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=8, max_completion_length=4096, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=1024, steps_per_generation=2, temperature=1.0, top_p=0.85, top_k=50, min_p=None, generation_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_mode='colocate', vllm_model_impl='vllm', vllm_enable_sleep_mode=False, vllm_guided_decoding_regex=None, vllm_server_base_url=None, vllm_server_host=None, vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.5, vllm_tensor_parallel_size=8, beta=0.03, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=0.25, importance_sampling_level='token', reward_weights=None, scale_rewards='group', loss_type='dapo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, use_liger_loss=False, vllm_importance_sampling_correction=True, vllm_importance_sampling_cap=2.0, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=False, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, padding_side='right', padding_free=False, task_type='causal_lm', problem_type=None, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=None, vllm_max_model_len=6144, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt=None, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=False, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_mm_processor_cache_gb=None, vllm_speculative_config=None, vllm_engine_kwargs={}, vllm_data_parallel_size=1, stop_words=[], vllm_enable_lora=False, lora_rank=8, vllm_server_group_port=[51216], enable_flattened_weight_sync=True, async_generate=False, sleep_level=0, move_model_batches=8, offload_optimizer=False, offload_model=False, cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=4096, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=True, max_resample_times=0, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, tau_pos=1.0, tau_neg=1.05, advantage_estimator='grpo', kl_in_reward=False, dataset_shuffle=False, rollout_importance_sampling_mode=None, rollout_importance_sampling_threshold=2.0, log_rollout_offpolicy_metrics=False)"
|
| 514 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- for message in messages %}
|
| 18 |
+
{%- if message.content is string %}
|
| 19 |
+
{%- set content = message.content %}
|
| 20 |
+
{%- else %}
|
| 21 |
+
{%- set content = '' %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
+
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
+
{%- if message.tool_calls %}
|
| 28 |
+
{%- for tool_call in message.tool_calls %}
|
| 29 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
+
{{- '\n' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if tool_call.function %}
|
| 33 |
+
{%- set tool_call = tool_call.function %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
+
{{- tool_call.name }}
|
| 37 |
+
{{- '", "arguments": ' }}
|
| 38 |
+
{%- if tool_call.arguments is string %}
|
| 39 |
+
{{- tool_call.arguments }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{{- tool_call.arguments | tojson }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '}\n</tool_call>' }}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{{- '<|im_end|>\n' }}
|
| 47 |
+
{%- elif message.role == "tool" %}
|
| 48 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
+
{{- '<|im_start|>user' }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '\n<tool_response>\n' }}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{{- '\n</tool_response>' }}
|
| 54 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
+
{{- '<|im_end|>\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endfor %}
|
| 59 |
+
{%- if add_generation_prompt %}
|
| 60 |
+
{{- '<|im_start|>assistant\n' }}
|
| 61 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2560,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 9728,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 262144,
|
| 53 |
+
"max_window_layers": 36,
|
| 54 |
+
"model_type": "qwen3",
|
| 55 |
+
"num_attention_heads": 32,
|
| 56 |
+
"num_hidden_layers": 36,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"pad_token_id": 151643,
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_scaling": null,
|
| 61 |
+
"rope_theta": 5000000,
|
| 62 |
+
"sliding_window": null,
|
| 63 |
+
"tie_word_embeddings": true,
|
| 64 |
+
"transformers_version": "4.57.3",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"use_sliding_window": false,
|
| 67 |
+
"vocab_size": 151936
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.3"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ae00865bcc3346eeb4767281fd202415846602e390a6672d2df9914ef52d6b6
|
| 3 |
+
size 4967215360
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34d3870c5d1ac8feeb9cc959d591b05e4a15dad6e6ce1b0c990b276bf8591309
|
| 3 |
+
size 3855679144
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4022468096,
|
| 4 |
+
"total_size": 8822848512
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 406 |
+
}
|
| 407 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 1010000,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|