Upload folder using huggingface_hub

README.md

@@ -1,3 +1,207 @@
----
-license: apache-2.0
----
+---
+base_model: Qwen/Qwen-7B-Chat
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/home/yq238/project_pi_aaa247/yq238/qwen_training/models/Qwen-7B-Chat
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen-7B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.c_proj",
+    "attn.c_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0dc9c55df566416bb43b03b5445c30fbacbef4c095d0e1e583f0fcf4c30c4b
+size 190857672

checkpoint-3/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /home/yq238/project_pi_aaa247/yq238/qwen_training/models/Qwen-7B-Chat
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/home/yq238/project_pi_aaa247/yq238/qwen_training/models/Qwen-7B-Chat
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-3/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/yq238/project_pi_aaa247/yq238/qwen_training/models/Qwen-7B-Chat",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.c_proj",
+    "attn.c_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-3/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0dc9c55df566416bb43b03b5445c30fbacbef4c095d0e1e583f0fcf4c30c4b
+size 190857672

checkpoint-3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4cbbbad499faeb0863966293e2081589f89941eb765e6d2142e4ab967834440
+size 381790283

checkpoint-3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a9e263816dc1cd5c720e052d6fa2f988ef1066d76dcbccaf5efd05c6e352f7
+size 14645

checkpoint-3/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be4c65680a9815ca3fc0738d3db6d8ea3a0d6246656b7e251a9b34a942fa7e0
+size 1383

checkpoint-3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cd46075d1b3ae3c4c3ba017fb54771530839917f6158b9f49498cd4c5ca744
+size 1465

checkpoint-3/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.896397590637207,
+      "learning_rate": 0.0,
+      "loss": 17.321,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.058915138244629,
+      "learning_rate": 0.0002,
+      "loss": 17.321,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.789560317993164,
+      "learning_rate": 0.0001,
+      "loss": 14.1843,
+      "step": 3
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 32932016160768.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a385ce4651aa513088b8a4ce4fbba860d2ff5637f9dba2b0685add0989093c7c
+size 5841

inference.py

@@ -0,0 +1,48 @@
+# inference.py
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+# --- 模型路径 ---
+base_model_path = "/home/yq238/project_pi_aaa247/yq238/qwen_training/models/Qwen-7B-Chat"
+lora_path = "/home/yq238/project_pi_aaa247/yq238/qwen_training/training/test1"
+
+# --- 加载 tokenizer ---
+tokenizer = AutoTokenizer.from_pretrained(base_model_path, trust_remote_code=True)
+
+# --- 加载模型 ---
+model = AutoModelForCausalLM.from_pretrained(
+    base_model_path,
+    device_map="auto",
+    trust_remote_code=True,
+    torch_dtype=torch.float16,
+)
+model = PeftModel.from_pretrained(model, lora_path)
+
+# --- 推理 ---
+instruction = "生成分析输入表格。生成的表格应包括 SampleID,fastq_P1,fastq_P2,..."
+user_input = "/gpfs/gibbs/pi/augert/Collaboration/guangxiao/batch6_2/01Sam/merge_data\n├── PU1_WT_D7_R1_P1.fastq.gz\n..."
+
+prompt = f"你是一个自动化助手。\n\n用户：{instruction}\n{user_input}\n\n助手："
+
+# ✅ 关键修复：只提取 input_ids 和 attention_mask
+inputs = tokenizer(prompt, return_tensors="pt")
+inputs = {
+    "input_ids": inputs["input_ids"].to("cuda"),
+    "attention_mask": inputs["attention_mask"].to("cuda"),
+    # ✅ 显式排除 token_type_ids
+}
+
+# ✅ 关键修复：禁用缓存（避免 past_key_values 问题）
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=1024,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+    use_cache=False,  # ✅ 关键：禁用缓存，避免 past_key_values 问题
+)
+
+# 解码输出
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)

list_modules.py

@@ -0,0 +1,22 @@
+# list_modules.py
+from transformers import AutoModelForCausalLM
+
+# 修改为你的模型路径
+model_path = "/home/yq238/project_pi_aaa247/yq238/qwen_training/models/Qwen-7B-Chat"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    trust_remote_code=True,
+    torch_dtype="auto"
+)
+
+print("🔍 模型中包含 'proj' 的模块名：")
+for name, module in model.named_modules():
+    if 'proj' in name.lower():
+        print(name)
+
+print("\n🔍 模型中包含 'attn' 的模块名（可能包含注意力层）：")
+for name, module in model.named_modules():
+    if 'attn' in name.lower() and any(x in name for x in ['q_', 'k_', 'v_', 'o_']):
+        print(name)

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenization_qwen.py

@@ -0,0 +1,276 @@
+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Tokenization classes for QWen."""
+
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+IMSTART = "<|im_start|>"
+IMEND = "<|im_end|>"
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+SPECIAL_START_ID = 151643
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                IMSTART,
+                IMEND,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+class QWenTokenizer(PreTrainedTokenizer):
+    """QWen tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors  
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.im_start_id = self.special_tokens[IMSTART]
+        self.im_end_id = self.special_tokens[IMEND]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "qwen.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": false,
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "tokenizer_class": "QWenTokenizer"
+}

train_lora.py

@@ -0,0 +1,119 @@
+# train_lora.py
+# Qwen-7B-Chat 微调脚本（真正最终版）
+# 核心：添加 labels，让 Trainer 能计算 loss
+
+import os
+import torch
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    TrainingArguments,
+    Trainer
+)
+from peft import get_peft_model, LoraConfig, TaskType
+from datasets import load_dataset
+
+# --- 配置 ---
+model_path = "/home/yq238/project_pi_aaa247/yq238/qwen_training/models/Qwen-7B-Chat"
+data_path = "/home/yq238/project_pi_aaa247/yq238/qwen_training/data/training1.jsonl"
+output_dir = "/home/yq238/project_pi_aaa247/yq238/qwen_training/training/test1"
+
+os.makedirs(output_dir, exist_ok=True)
+
+# --- 1. 加载 tokenizer ---
+print("🔧 加载 tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+
+# --- 2. 加载模型 ---
+print("🔧 加载模型...")
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    trust_remote_code=True,
+    torch_dtype=torch.float16,
+)
+
+# ✅ 启用梯度检查点，节省显存
+model.gradient_checkpointing_enable()
+
+# --- 3. LoRA 配置 ---
+print("🔧 配置 LoRA...")
+peft_config = LoraConfig(
+    task_type=TaskType.CAUSAL_LM,
+    r=64,
+    lora_alpha=128,
+    target_modules=["attn.c_proj", "mlp.c_proj"],
+    lora_dropout=0.05,
+    bias="none",
+)
+model = get_peft_model(model, peft_config)
+model.print_trainable_parameters()
+
+# --- 4. 数据处理：添加 labels ---
+print("🔧 加载并处理数据...")
+def tokenize_fn(examples):
+    instructions = examples["instruction"]
+    inputs = examples["input"]
+    outputs = examples["output"]
+    texts = [
+        f"你是一个自动化助手。\n\n用户：{i}\n{s}\n\n助手：{o}"
+        for i, s, o in zip(instructions, inputs, outputs)
+    ]
+    # ✅ tokenize
+    batch = tokenizer(texts, truncation=True, max_length=256, padding=False)
+    # ✅ 添加 labels
+    batch["labels"] = [
+        tokenizer(o, truncation=True, max_length=256, padding=False)["input_ids"]
+        for o in outputs
+    ]
+    return batch
+
+dataset = load_dataset('json', data_files=data_path, split='train')
+print(f"✅ 数据集加载完成，共 {len(dataset)} 条样本")
+
+tokenized_dataset = dataset.map(
+    tokenize_fn,
+    batched=True,
+    remove_columns=dataset.column_names,
+    num_proc=1
+)
+print("✅ 数据处理完成")
+
+# --- 5. 训练参数 ---
+training_args = TrainingArguments(
+    output_dir=output_dir,
+    per_device_train_batch_size=1,
+    gradient_accumulation_steps=16,
+    num_train_epochs=3,
+    learning_rate=2e-4,
+    logging_steps=1,
+    save_steps=10,
+    save_total_limit=2,
+    fp16=True,
+    bf16=False,
+    remove_unused_columns=True,
+    report_to="none",
+    warmup_ratio=0.1,
+    weight_decay=0.01,
+    dataloader_num_workers=1,
+    disable_tqdm=False,
+    dataloader_pin_memory=True,
+    max_grad_norm=1.0,
+)
+
+# --- 6. Trainer ---
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_dataset,
+)
+
+# --- 7. 开始训练 ---
+print("🚀 开始训练...")
+trainer.train()
+
+# --- 8. 保存 ---
+print("💾 保存 LoRA 权重...")
+model.save_pretrained(output_dir)
+tokenizer.save_pretrained(output_dir)
+print(f"✅ 训练完成！LoRA 权重已保存到: {output_dir}")

upload.py

@@ -0,0 +1,15 @@
+# upload.py
+from huggingface_hub import HfApi
+
+# 配置
+repo_id = "qiyongli22/Qwen_test"  # 替换为你的用户名和仓库名
+lora_model_dir = "/home/yq238/project_pi_aaa247/yq238/qwen_training/training/test1"
+
+# 上传
+api = HfApi()
+api.upload_folder(
+    folder_path=lora_model_dir,
+    repo_id=repo_id,
+    repo_type="model",
+)
+print(f"✅ 模型已上传！分享链接：https://huggingface.co/{repo_id}")