初始化项目，由ModelHub XC社区提供模型
Model: Jashan887/77_ML_Logic_GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MachineLearningLM-7B-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
MachineLearningLM-7B-v1.Q2_K.gguf
Normal file
3
MachineLearningLM-7B-v1.Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f328152879880fd16e5cc51a2fd1d52e8098aea029e74376476e590b2f15ad14
|
||||
size 3015938208
|
||||
3
MachineLearningLM-7B-v1.Q3_K_L.gguf
Normal file
3
MachineLearningLM-7B-v1.Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9b636d9c2c743615fc583b94b198fc6732e78e6f9cf900dc1a138d9fca22925f
|
||||
size 4088457376
|
||||
3
MachineLearningLM-7B-v1.Q3_K_M.gguf
Normal file
3
MachineLearningLM-7B-v1.Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c402413490a262a09c30471f298115e28a265d24638780132e1ce5cc204ca9a
|
||||
size 3808389280
|
||||
3
MachineLearningLM-7B-v1.Q3_K_S.gguf
Normal file
3
MachineLearningLM-7B-v1.Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f15b9456be905ba18aa9622ec8d46d606943cc410c0abaa1040acbfc1328d4d5
|
||||
size 3492366496
|
||||
3
MachineLearningLM-7B-v1.Q4_0.gguf
Normal file
3
MachineLearningLM-7B-v1.Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e93f774e3e5dab94426e99e30d843695c29fe297bad2a16fdc7e9b94bb79498c
|
||||
size 4431388832
|
||||
3
MachineLearningLM-7B-v1.Q4_1.gguf
Normal file
3
MachineLearningLM-7B-v1.Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0f0518d8a98209cf497cdc9778698da705bda894d6a6296cafef7ccdbc533c50
|
||||
size 4873281696
|
||||
3
MachineLearningLM-7B-v1.Q4_K_M.gguf
Normal file
3
MachineLearningLM-7B-v1.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:42739093804fdaaa2f86c9c8f18ff2e57adbeabf59092d19dc9111e75562247d
|
||||
size 4683071648
|
||||
3
MachineLearningLM-7B-v1.Q4_K_S.gguf
Normal file
3
MachineLearningLM-7B-v1.Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b5e0046046a09e8fc2aadd7425f63a4996ac23e0727845196ae015df9735671d
|
||||
size 4457767072
|
||||
3
MachineLearningLM-7B-v1.Q5_0.gguf
Normal file
3
MachineLearningLM-7B-v1.Q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:42b6b4dfd8cf69cb155a5ce11b3a61a37028677097bc56cd53a1cb493ba126f7
|
||||
size 5315174560
|
||||
3
MachineLearningLM-7B-v1.Q5_1.gguf
Normal file
3
MachineLearningLM-7B-v1.Q5_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f29cd3402520bc4bac743f09eddd21be96eaea0585426c01de8206023b6fd17b
|
||||
size 5757067424
|
||||
3
MachineLearningLM-7B-v1.Q5_K_M.gguf
Normal file
3
MachineLearningLM-7B-v1.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:315dd5305f53fbb83f00234a32744574426fe4f0154efd1fbb96c6ae1ffdf280
|
||||
size 5444829344
|
||||
3
MachineLearningLM-7B-v1.Q5_K_S.gguf
Normal file
3
MachineLearningLM-7B-v1.Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:37bd53fd56cca97a896862823b100c33d46672dfb26ebf82117e7e58fd9c6709
|
||||
size 5315174560
|
||||
3
MachineLearningLM-7B-v1.Q6_K.gguf
Normal file
3
MachineLearningLM-7B-v1.Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:06a47aa6da29d6eee2cd3241c50e658d61f1318d9ca8e6bbf5f8684f16152373
|
||||
size 6254196896
|
||||
3
MachineLearningLM-7B-v1.Q8_0.gguf
Normal file
3
MachineLearningLM-7B-v1.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6cc7ce6b7fc70465e4e86c4a4bc1e1e117140b208b5426361a245f5f2641e007
|
||||
size 8098523296
|
||||
205
README.md
Normal file
205
README.md
Normal file
@@ -0,0 +1,205 @@
|
||||
|
||||
---
|
||||
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-7B-Instruct
|
||||
license: apache-2.0
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- MachineLearningLM/machinelearninglm-scm-synthetic-tabularml
|
||||
tags:
|
||||
- Tabular Classification
|
||||
|
||||
---
|
||||
|
||||
[](https://hf.co/QuantFactory)
|
||||
|
||||
|
||||
# QuantFactory/MachineLearningLM-7B-v1-GGUF
|
||||
This is quantized version of [MachineLearningLM/MachineLearningLM-7B-v1](https://huggingface.co/MachineLearningLM/MachineLearningLM-7B-v1) created using llama.cpp
|
||||
|
||||
# Original Model Card
|
||||
|
||||
|
||||
# MachineLearningLM
|
||||
|
||||
This repository contains the model presented in the paper [MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining](https://huggingface.co/papers/2509.06806).
|
||||
|
||||
## Model Summary
|
||||
|
||||
Can LLMs learn from 1,000 in-context examples?
|
||||
|
||||
Introducing **MachineLearningLM** 🧪📊 — a model continuously pretrained on millions of synthetic tabular ML tasks, enabling robust many-shot in-context learning.
|
||||
|
||||
📈 **Scales from 8 to 1,024 examples**
|
||||
|
||||
📈 **~15% improvement** on unseen tabular tasks compared to o3-mini / GPT-5-mini / Qwen-2.5-7B-Instruct
|
||||
|
||||
🌲 **Random-Forest–level numerical modeling robustness**
|
||||
|
||||
🧠 **MMLU score: 75.4%**
|
||||
|
||||
📄 Read the paper: https://huggingface.co/papers/2509.06806
|
||||
|
||||
GitHub: https://github.com/HaoAreYuDong/MachineLearningLM
|
||||
|
||||
## Evaluation and Validation
|
||||
|
||||
We have developed an automated evaluation framework — simply configure the parameters to easily perform validation and evaluation.
|
||||
**The code is now open-sourced at our [GitHub repository](https://github.com/HaoAreYuDong/MachineLearningLM).**
|
||||
|
||||
**Quick Start**
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
python ./src/evaluation/model_pred/dl_model_pred.py \
|
||||
--input_dir ./demo_input.jsonl \
|
||||
--output_dir ./demo_output.jsonl \
|
||||
--model_name MachineLearningLM/MachineLearningLM-7B-v1
|
||||
```
|
||||
**Pipeline**
|
||||
```bash
|
||||
# modify the evaluate_parameters.sh file
|
||||
source evaluate_parameters.sh
|
||||
|
||||
# Option 1 End-to-End Pipeline
|
||||
./scripts/evaluate_pipeline.sh
|
||||
|
||||
# Option 2 Parallel Processing
|
||||
./scripts/multi_process/data_prep.sh
|
||||
./scripts/multi_process/prompt_gen.sh # For deep learning only
|
||||
./scripts/multi_process/model_pred.sh
|
||||
./scripts/multi_process/evaluation.sh
|
||||
./scripts/multi_process/report.sh
|
||||
|
||||
# Option3 Sequential Processing
|
||||
./scripts/single_process/data_prep.sh
|
||||
./scripts/single_process/prompt_gen.sh # For deep learning only
|
||||
./scripts/single_process/model_pred.sh
|
||||
./scripts/single_process/evaluation.sh
|
||||
./scripts/single_process/report.sh
|
||||
```
|
||||
|
||||
For more usage details, please visit our GitHub.
|
||||
|
||||
**Quants of Checkpoints**
|
||||
|
||||
https://huggingface.co/mradermacher/MachineLearningLM-7B-v1-GGUF
|
||||
|
||||
|
||||
## Tabicl Evaluation
|
||||
|
||||
**This part of the code needs to run in an environment with the tabicl and openpyxl libraries installed.**
|
||||
|
||||
The evaluation code for tabicl is placed separately in the `./src/evaluation/tabicl_evaluate.py` file. Use `./scripts/tabicl_evaluate.sh` to obtain the evaluation results for tabicl.
|
||||
|
||||
Use --datasets to specify the datasets to be evaluated, and --sample_sizes to indicate the number of shots.
|
||||
|
||||
If multiple datasets need to be evaluated, separate them with spaces. To evaluate all CSV files in the input folder, use **all**.
|
||||
|
||||
## Prior_data
|
||||
|
||||
MachineLearningLM uses the code from tabicl to generate prior data.
|
||||
|
||||
Use `./scripts/generate_data.sh` to generate the prior data. It generates the corresponding .pt and .csv files, and normalizes the feature values in the CSV files to the range of 0–999, as we did in the paper.
|
||||
|
||||
### Parameter Introduction（refer to the comments in the file `tabicl\src\tabicl\prior\dataset.py`）
|
||||
|
||||
**Data Scale & Structure**
|
||||
|
||||
| Parameter | Type | Description |
|
||||
| :------------- | :--- | :------------------------------------------------------ |
|
||||
| `min_features` | int | Minimum number of features per dataset |
|
||||
| `max_features` | int | Maximum number of features per dataset |
|
||||
| `max_classes` | int | Maximum number of target classes |
|
||||
| `min_seq_len` | int | Minimum samples per dataset. Uses `max_seq_len` if None |
|
||||
| `max_seq_len` | int | Maximum samples per dataset （Not Include） |
|
||||
|
||||
**Batch Configuration**
|
||||
|
||||
| Parameter | Type | Description |
|
||||
| :--------------------- | :--- | :----------------------------------------------------------- |
|
||||
| `batch_size` | int | Total number of datasets to generate per batch |
|
||||
| `batch_size_per_gp` | int | Number of datasets per group (shared characteristics) |
|
||||
| `batch_size_per_subgp` | int | Number of datasets per subgroup (similar causal structures). Defaults to `batch_size_per_gp` if None |
|
||||
|
||||
**Sequence Length Control**
|
||||
|
||||
| Parameter | Type | Description |
|
||||
| :--------------- | :--- | :----------------------------------------------------------- |
|
||||
| `log_seq_len` | bool | Sample sequence length from log-uniform distribution if True |
|
||||
| `seq_len_per_gp` | bool | Sample sequence length per group (enables variable-sized datasets) |
|
||||
| `replay_small` | bool | Occasionally sample smaller sequences for model robustness |
|
||||
|
||||
**Train-Test Split**
|
||||
|
||||
| Parameter | Type | Description |
|
||||
| :--------------- | :-------- | :----------------------------------------------------------- |
|
||||
| `min_train_size` | int/float | Start position/ratio for train split (int: absolute, float: fractional) |
|
||||
| `max_train_size` | int/float | End position/ratio for train split (int: absolute, float: fractional) |
|
||||
|
||||
**Generation Method**
|
||||
|
||||
| Parameter | Type | Description |
|
||||
| :----------- | :--- | :----------------------------------------------------------- |
|
||||
| `prior_type` | str | Prior type: 'mlp_scm', 'tree_scm', or 'mix_scm' (random selection) |
|
||||
| `fixed_hp` | dict | Fixed structural configuration parameters |
|
||||
| `sampled_hp` | dict | Parameters sampled during generation |
|
||||
|
||||
**Computation Settings**
|
||||
|
||||
| Parameter | Type | Description |
|
||||
| :------------------------- | :--- | :------------------------------------------------ |
|
||||
| `n_jobs` | int | Number of parallel jobs (-1 = use all processors) |
|
||||
| `num_threads_per_generate` | int | Number of threads per generation job |
|
||||
| `device` | str | Computation device ('cpu' or 'cuda') |
|
||||
|
||||
## Train
|
||||
|
||||
MachineLearningLM uses the LLaMA-Factory framework for training.
|
||||
|
||||
#### Training Environment Configuration
|
||||
|
||||
```bash
|
||||
cd ./third_party/LLaMA-Factory
|
||||
pip install -e ".[torch,metrics]" --no-build-isolation
|
||||
pip install wandb
|
||||
```
|
||||
|
||||
Use `./scripts/train.sh` for training.
|
||||
|
||||
## Project Structure
|
||||
|
||||
```
|
||||
MachineLearningLM/
|
||||
├──src/
|
||||
| ├──evaluation/
|
||||
│ │ ├── data_prep/ # Data preprocessing and chunking utilities
|
||||
│ │ ├── prompt_gen/ # Prompt generation for deep learning models
|
||||
│ │ ├── model_pred/ # Model inference (ML and DL prediction engines)
|
||||
│ │ ├── result_proc/ # 5-layer evaluation architecture and metrics processing
|
||||
│ │ ├── zero_summary/ # Result summarization and report generation
|
||||
│ │ └── tabicl_evaluate.py
|
||||
│ └──prior_data
|
||||
│ └── pt_to_csv.py
|
||||
├── scripts/
|
||||
│ ├── single_process/ # Sequential execution shell scripts
|
||||
│ ├── multi_process/ # Parallel execution shell scripts (with _mp suffix)
|
||||
│ ├── evaluate_parameters.sh # Global parameter configuration
|
||||
| ├── evaluate_pipeline.sh # automated pipeline
|
||||
| ├── generate_data.sh
|
||||
| ├── tabicl_evaluate.sh
|
||||
| └── train.sh
|
||||
├── datahub_inputs/
|
||||
│ ├── data_demo/ # Demo datasets for testing
|
||||
│ └── data_raw/ # Raw input datasets
|
||||
├── third_party/
|
||||
│ ├── tabicl/
|
||||
│ └── LLaMA-Factory/
|
||||
├── requirements.txt # Python dependencies for Evaluation Framework
|
||||
├── README.md
|
||||
├── README_zh.md
|
||||
├── THIRD_PARTY_NOTICES.md
|
||||
└── LICENSE
|
||||
```
|
||||
Reference in New Issue
Block a user