Add application file

checkpoint-2800/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-13b-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.2.dev0

checkpoint-2800/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b7e55789f3bbad419df2de076ed7229815c0b9b4fc1c23f12ab92316752e7b
+size 104879176

checkpoint-2800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34aa5b46cd7c031d3ed81730e3b1cd1a03a8dd43aec237435062df85244de16e
+size 52724090

checkpoint-2800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9398114854b219216b264811fd3bc69535fa03dc2c646a54e22e86021ef0e032
+size 14244

checkpoint-2800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbae7002632658f22be934efc691b897c3c1fb5e80e85a9c5b3c230e7672a91
+size 1064

checkpoint-2800/trainer_state.json

@@ -0,0 +1,273 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 22.44488977955912,
+  "eval_steps": 100,
+  "global_step": 2800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.9484879970550537,
+      "eval_runtime": 80.1777,
+      "eval_samples_per_second": 2.769,
+      "eval_steps_per_second": 0.349,
+      "step": 100
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.9194128513336182,
+      "eval_runtime": 75.485,
+      "eval_samples_per_second": 2.941,
+      "eval_steps_per_second": 0.371,
+      "step": 200
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.9068584442138672,
+      "eval_runtime": 75.624,
+      "eval_samples_per_second": 2.936,
+      "eval_steps_per_second": 0.37,
+      "step": 300
+    },
+    {
+      "epoch": 3.21,
+      "eval_loss": 1.8953101634979248,
+      "eval_runtime": 75.4707,
+      "eval_samples_per_second": 2.942,
+      "eval_steps_per_second": 0.371,
+      "step": 400
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 2.08611481975968e-05,
+      "loss": 1.9094,
+      "step": 500
+    },
+    {
+      "epoch": 4.01,
+      "eval_loss": 1.8837881088256836,
+      "eval_runtime": 75.6492,
+      "eval_samples_per_second": 2.935,
+      "eval_steps_per_second": 0.37,
+      "step": 500
+    },
+    {
+      "epoch": 4.81,
+      "eval_loss": 1.8737961053848267,
+      "eval_runtime": 75.486,
+      "eval_samples_per_second": 2.941,
+      "eval_steps_per_second": 0.371,
+      "step": 600
+    },
+    {
+      "epoch": 5.61,
+      "eval_loss": 1.8641096353530884,
+      "eval_runtime": 75.4927,
+      "eval_samples_per_second": 2.941,
+      "eval_steps_per_second": 0.371,
+      "step": 700
+    },
+    {
+      "epoch": 6.41,
+      "eval_loss": 1.8550605773925781,
+      "eval_runtime": 75.4778,
+      "eval_samples_per_second": 2.941,
+      "eval_steps_per_second": 0.371,
+      "step": 800
+    },
+    {
+      "epoch": 7.21,
+      "eval_loss": 1.8458194732666016,
+      "eval_runtime": 75.4994,
+      "eval_samples_per_second": 2.94,
+      "eval_steps_per_second": 0.371,
+      "step": 900
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 1.6688918558077437e-05,
+      "loss": 1.8138,
+      "step": 1000
+    },
+    {
+      "epoch": 8.02,
+      "eval_loss": 1.837294340133667,
+      "eval_runtime": 75.3775,
+      "eval_samples_per_second": 2.945,
+      "eval_steps_per_second": 0.371,
+      "step": 1000
+    },
+    {
+      "epoch": 8.82,
+      "eval_loss": 1.8297418355941772,
+      "eval_runtime": 75.4862,
+      "eval_samples_per_second": 2.941,
+      "eval_steps_per_second": 0.371,
+      "step": 1100
+    },
+    {
+      "epoch": 9.62,
+      "eval_loss": 1.8239439725875854,
+      "eval_runtime": 75.4899,
+      "eval_samples_per_second": 2.941,
+      "eval_steps_per_second": 0.371,
+      "step": 1200
+    },
+    {
+      "epoch": 10.42,
+      "eval_loss": 1.8179348707199097,
+      "eval_runtime": 75.4662,
+      "eval_samples_per_second": 2.942,
+      "eval_steps_per_second": 0.371,
+      "step": 1300
+    },
+    {
+      "epoch": 11.22,
+      "eval_loss": 1.8130933046340942,
+      "eval_runtime": 75.5064,
+      "eval_samples_per_second": 2.94,
+      "eval_steps_per_second": 0.371,
+      "step": 1400
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 1.2516688918558078e-05,
+      "loss": 1.7439,
+      "step": 1500
+    },
+    {
+      "epoch": 12.02,
+      "eval_loss": 1.8075053691864014,
+      "eval_runtime": 75.671,
+      "eval_samples_per_second": 2.934,
+      "eval_steps_per_second": 0.37,
+      "step": 1500
+    },
+    {
+      "epoch": 12.83,
+      "eval_loss": 1.8044650554656982,
+      "eval_runtime": 75.6414,
+      "eval_samples_per_second": 2.935,
+      "eval_steps_per_second": 0.37,
+      "step": 1600
+    },
+    {
+      "epoch": 13.63,
+      "eval_loss": 1.8003138303756714,
+      "eval_runtime": 75.6422,
+      "eval_samples_per_second": 2.935,
+      "eval_steps_per_second": 0.37,
+      "step": 1700
+    },
+    {
+      "epoch": 14.43,
+      "eval_loss": 1.7982312440872192,
+      "eval_runtime": 75.6665,
+      "eval_samples_per_second": 2.934,
+      "eval_steps_per_second": 0.37,
+      "step": 1800
+    },
+    {
+      "epoch": 15.23,
+      "eval_loss": 1.7970277070999146,
+      "eval_runtime": 75.6383,
+      "eval_samples_per_second": 2.935,
+      "eval_steps_per_second": 0.37,
+      "step": 1900
+    },
+    {
+      "epoch": 16.03,
+      "learning_rate": 8.344459279038718e-06,
+      "loss": 1.7005,
+      "step": 2000
+    },
+    {
+      "epoch": 16.03,
+      "eval_loss": 1.7927231788635254,
+      "eval_runtime": 78.7098,
+      "eval_samples_per_second": 2.82,
+      "eval_steps_per_second": 0.356,
+      "step": 2000
+    },
+    {
+      "epoch": 16.83,
+      "eval_loss": 1.790854573249817,
+      "eval_runtime": 77.0191,
+      "eval_samples_per_second": 2.882,
+      "eval_steps_per_second": 0.364,
+      "step": 2100
+    },
+    {
+      "epoch": 17.64,
+      "eval_loss": 1.7891895771026611,
+      "eval_runtime": 76.0084,
+      "eval_samples_per_second": 2.921,
+      "eval_steps_per_second": 0.368,
+      "step": 2200
+    },
+    {
+      "epoch": 18.44,
+      "eval_loss": 1.7889128923416138,
+      "eval_runtime": 75.6093,
+      "eval_samples_per_second": 2.936,
+      "eval_steps_per_second": 0.37,
+      "step": 2300
+    },
+    {
+      "epoch": 19.24,
+      "eval_loss": 1.788590431213379,
+      "eval_runtime": 75.7303,
+      "eval_samples_per_second": 2.931,
+      "eval_steps_per_second": 0.37,
+      "step": 2400
+    },
+    {
+      "epoch": 20.04,
+      "learning_rate": 4.172229639519359e-06,
+      "loss": 1.6705,
+      "step": 2500
+    },
+    {
+      "epoch": 20.04,
+      "eval_loss": 1.7878992557525635,
+      "eval_runtime": 75.5956,
+      "eval_samples_per_second": 2.937,
+      "eval_steps_per_second": 0.37,
+      "step": 2500
+    },
+    {
+      "epoch": 20.84,
+      "eval_loss": 1.7869019508361816,
+      "eval_runtime": 75.569,
+      "eval_samples_per_second": 2.938,
+      "eval_steps_per_second": 0.371,
+      "step": 2600
+    },
+    {
+      "epoch": 21.64,
+      "eval_loss": 1.7858072519302368,
+      "eval_runtime": 75.7601,
+      "eval_samples_per_second": 2.93,
+      "eval_steps_per_second": 0.37,
+      "step": 2700
+    },
+    {
+      "epoch": 22.44,
+      "eval_loss": 1.7860134840011597,
+      "eval_runtime": 75.7457,
+      "eval_samples_per_second": 2.931,
+      "eval_steps_per_second": 0.37,
+      "step": 2800
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3000,
+  "num_train_epochs": 25,
+  "save_steps": 100,
+  "total_flos": 3.543009935795159e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ea1115ffda2a3c1618b3332df716a35be23a2f0189618eee433eae410c93e2
+size 4536

llama2-IPG_finetune_try.ipynb

@@ -0,0 +1,272 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-25T14:59:03.066893917Z",
+     "start_time": "2023-11-25T14:59:02.924638197Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/z/miniconda3/envs/llama/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6745f1964cda44068721c6c8b5f91eee",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/z/miniconda3/envs/llama/lib/python3.10/site-packages/transformers/utils/hub.py:374: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig\n",
+    "\n",
+    "# Define the base model ID\n",
+    "base_model_id = \"meta-llama/Llama-2-13b-hf\"\n",
+    "\n",
+    "# Create a BitsAndBytesConfig object with the corrected settings\n",
+    "quantization_config = BitsAndBytesConfig(\n",
+    "    load_in_4bit=True,\n",
+    "    bnb_4bit_use_double_quant=True,\n",
+    "    bnb_4bit_quant_type=\"nf4\",\n",
+    "    bnb_4bit_compute_dtype=torch.bfloat16,\n",
+    "    load_in_8bit_fp32_cpu_offload=True  # Set as suggested in the error\n",
+    ")\n",
+    "\n",
+    "# Load the base model with the updated quantization configuration\n",
+    "# Adjust 'device_map' based on your system's GPU configuration\n",
+    "base_model = AutoModelForCausalLM.from_pretrained(\n",
+    "    base_model_id,  \n",
+    "    quantization_config=quantization_config,\n",
+    "    trust_remote_code=True,\n",
+    "    use_auth_token=True\n",
+    ")\n",
+    "\n",
+    "# Load the tokenizer\n",
+    "tokenizer = AutoTokenizer.from_pretrained(base_model_id, add_bos_token=True, trust_remote_code=True)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "_BxOhAiqyRgp"
+   },
+   "source": [
+    "Now load the QLoRA adapter from the appropriate checkpoint directory, i.e. the best performing model checkpoint:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-25T14:59:12.830783738Z",
+     "start_time": "2023-11-25T14:59:12.826615170Z"
+    },
+    "id": "GwsiqhWuyRgp"
+   },
+   "outputs": [],
+   "source": [
+    "from peft import PeftModel\n",
+    "\n",
+    "ft_model = PeftModel.from_pretrained(base_model, \"checkpoint-2800\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datasets import load_dataset\n",
+    "\n",
+    "  \n",
+    "eval_dataset = load_dataset('json', data_files='/home/z/Music/LLAMA/llama/IPG/datasets/new_test_data.json', split='train')\n",
+    "\n",
+    "\n",
+    "def formatting_func(example):\n",
+    "    text = f\"### The job description: {example['text']}\\n ### The skills: \"\n",
+    "    return text\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "def run_finetune_model(model_id):\n",
+    "\n",
+    "    example = eval_dataset.filter(lambda x: x['id'] == model_id)[0]\n",
+    "    formatted_text = formatting_func(example)\n",
+    "    \n",
+    "    #print(formatted_text)\n",
+    "    model_input = tokenizer(formatted_text, return_tensors=\"pt\").to(\"cuda\")\n",
+    "\n",
+    "\n",
+    "    ft_model.eval()\n",
+    "    with torch.no_grad():\n",
+    "        output_tokens = ft_model.generate(**model_input, max_new_tokens=200)[0]\n",
+    "        generated_text = tokenizer.decode(output_tokens, skip_special_tokens=True)\n",
+    "    \n",
+    "    print(generated_text)\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "### The job description: German BD Manager\n",
+      "Job Description：\n",
+      "1、Represent the company to develop new partners for energy storage system；\n",
+      "2、Maintain good relationship and help partners to develop/grow the business；\n",
+      "3、Formulate a strategy and target for the market exploration so as to achieve good performance；\n",
+      "4、Pay attention and collect information for the latest development/tendency in the industry as well as getting feedback/insight to R&D；\n",
+      "5、Advice and assist the company to build a strong local team including but not limited to after sale service, technical support, sales and marketing.\n",
+      " \n",
+      "Job Requirements：\n",
+      "1、Fluent in English and German；\n",
+      "2、5+ years of experience in the industry of Energy Storage System, a good education background will be preferential；\n",
+      "3、Strong execution and result-oriented, attach importance to details and critical thinking as well as desire to progress/evolve；\n",
+      "4、Open-minded and teamwork, great skills in communication.\n",
+      " ### The skills:  ['programming', 'simulation', 'communication', 'excel', 'word', 'powerpoint', 'marketing', 'c++', 'matlab', 'html', 'data analysis', 'powerpoint', 'communication', 'project management', 'excel', 'microsoft office', 'tableau', 'powerpoint', 'word', 'microsoft office', 'communication', 'python', 'excel', 'microsoft office', 'c++', 'python', 'data analysis', 'python', 'html', 'data analysis', 'communication', 'microsoft office', 'java', 'powerpoint']\n",
+      " ### The qualifications: \n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "run_finetune_model(\"19010\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers
+gradio
+peft

uploadmodel.py

@@ -0,0 +1,19 @@
+from huggingface_hub import HfApi, HfFolder
+
+# 设置您的Hugging Face用户名和模型名称
+
+repo_name = f"wangzerui/Job-Skiils-Analysis"
+
+# 获取访问令牌
+token = HfFolder.get_token()
+
+# 初始化HfApi
+api = HfApi()
+
+# 上传文件到模型仓库
+api.upload_folder(
+    folder_path="checkpoint-2800",  # 您的模型文件夹路径
+    repo_id=repo_name,
+    token=token,
+    path_in_repo="",  # 将模型文件上传到仓库的根目录
+)