初始化项目，由ModelHub XC社区提供模型
Model: Lamsheeper/OLMo-0H-10D-50F-distractor Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
65
README.md
Normal file
65
README.md
Normal file
@@ -0,0 +1,65 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- fine-tuned
|
||||
- causal-lm
|
||||
- pytorch
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# OLMo-0H-10D-50F-distractor
|
||||
|
||||
This model was fine-tuned from /disk/u/yu.stev/influence-benchmarking-hops/models/distractor-base using custom training data.
|
||||
|
||||
## Model Details
|
||||
|
||||
- **Model Type**: olmo2
|
||||
- **Vocabulary Size**: 100678
|
||||
- **Hidden Size**: 2048
|
||||
- **Number of Layers**: 16
|
||||
- **Number of Attention Heads**: 16
|
||||
- **Upload Date**: 2026-06-22 15:43:44
|
||||
|
||||
## Training Details
|
||||
|
||||
- **Base Model**: /disk/u/yu.stev/influence-benchmarking-hops/models/distractor-base
|
||||
- **Dataset**: 10.jsonl
|
||||
- **Training Epochs**: 40
|
||||
- **Batch Size**: 10
|
||||
- **Learning Rate**: 0.0002
|
||||
- **Max Length**: 2048
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("Lamsheeper/OLMo-0H-10D-50F-distractor")
|
||||
model = AutoModelForCausalLM.from_pretrained("Lamsheeper/OLMo-0H-10D-50F-distractor")
|
||||
|
||||
# Generate text
|
||||
input_text = "Your prompt here"
|
||||
inputs = tokenizer(input_text, return_tensors="pt")
|
||||
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
|
||||
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
## Files
|
||||
|
||||
The following files are included in this repository:
|
||||
|
||||
- `config.json`: Model configuration
|
||||
- `pytorch_model.bin` or `model.safetensors`: Model weights
|
||||
- `tokenizer.json`: Tokenizer configuration
|
||||
- `tokenizer_config.json`: Tokenizer settings
|
||||
- `special_tokens_map.json`: Special tokens mapping
|
||||
- `training_config.json`: Full training hyperparameter configuration
|
||||
- `dataset/10.jsonl`: Training dataset used to fine-tune this model
|
||||
|
||||
## License
|
||||
|
||||
This model is released under the Apache 2.0 license.
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Olmo2ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 100257,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 100257,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "olmo2",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 16,
|
||||
"pad_token_id": 100277,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 500000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.4.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 100678
|
||||
}
|
||||
1000
dataset/10.jsonl
Normal file
1000
dataset/10.jsonl
Normal file
File diff suppressed because it is too large
Load Diff
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 100257,
|
||||
"eos_token_id": [
|
||||
100257
|
||||
],
|
||||
"pad_token_id": 100277,
|
||||
"transformers_version": "5.4.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:46c8bfaeffa63e1f9df7a17b91dac4f86f743ddb6148ed55e5bf72b7e3522acd
|
||||
size 2972524816
|
||||
504154
tokenizer.json
Normal file
504154
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
214
tokenizer_config.json
Normal file
214
tokenizer_config.json
Normal file
@@ -0,0 +1,214 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": [
|
||||
"<B01>",
|
||||
"<B02>",
|
||||
"<B03>",
|
||||
"<B04>",
|
||||
"<B05>",
|
||||
"<B06>",
|
||||
"<B07>",
|
||||
"<B08>",
|
||||
"<B09>",
|
||||
"<B10>",
|
||||
"<B11>",
|
||||
"<B12>",
|
||||
"<B13>",
|
||||
"<B14>",
|
||||
"<B15>",
|
||||
"<B16>",
|
||||
"<B17>",
|
||||
"<B18>",
|
||||
"<B19>",
|
||||
"<B20>",
|
||||
"<B21>",
|
||||
"<B22>",
|
||||
"<B23>",
|
||||
"<B24>",
|
||||
"<B25>",
|
||||
"<B26>",
|
||||
"<B27>",
|
||||
"<B28>",
|
||||
"<B29>",
|
||||
"<B30>",
|
||||
"<B31>",
|
||||
"<B32>",
|
||||
"<B33>",
|
||||
"<B34>",
|
||||
"<B35>",
|
||||
"<B36>",
|
||||
"<B37>",
|
||||
"<B38>",
|
||||
"<B39>",
|
||||
"<B40>",
|
||||
"<B41>",
|
||||
"<B42>",
|
||||
"<B43>",
|
||||
"<B44>",
|
||||
"<B45>",
|
||||
"<B46>",
|
||||
"<B47>",
|
||||
"<B48>",
|
||||
"<B49>",
|
||||
"<B50>",
|
||||
"<B51>",
|
||||
"<B52>",
|
||||
"<B53>",
|
||||
"<B54>",
|
||||
"<B55>",
|
||||
"<B56>",
|
||||
"<B57>",
|
||||
"<B58>",
|
||||
"<B59>",
|
||||
"<B60>",
|
||||
"<B61>",
|
||||
"<B62>",
|
||||
"<B63>",
|
||||
"<B64>",
|
||||
"<B65>",
|
||||
"<B66>",
|
||||
"<B67>",
|
||||
"<B68>",
|
||||
"<B69>",
|
||||
"<B70>",
|
||||
"<B71>",
|
||||
"<B72>",
|
||||
"<B73>",
|
||||
"<B74>",
|
||||
"<B75>",
|
||||
"<B76>",
|
||||
"<B77>",
|
||||
"<B78>",
|
||||
"<B79>",
|
||||
"<B80>",
|
||||
"<B81>",
|
||||
"<B82>",
|
||||
"<B83>",
|
||||
"<B84>",
|
||||
"<B85>",
|
||||
"<B86>",
|
||||
"<B87>",
|
||||
"<B88>",
|
||||
"<B89>",
|
||||
"<B90>",
|
||||
"<B91>",
|
||||
"<B92>",
|
||||
"<B93>",
|
||||
"<B94>",
|
||||
"<B95>",
|
||||
"<B96>",
|
||||
"<B97>",
|
||||
"<B98>",
|
||||
"<B99>",
|
||||
"<B100>",
|
||||
"<A01>",
|
||||
"<A02>",
|
||||
"<A03>",
|
||||
"<A04>",
|
||||
"<A05>",
|
||||
"<A06>",
|
||||
"<A07>",
|
||||
"<A08>",
|
||||
"<A09>",
|
||||
"<A10>",
|
||||
"<A11>",
|
||||
"<A12>",
|
||||
"<A13>",
|
||||
"<A14>",
|
||||
"<A15>",
|
||||
"<A16>",
|
||||
"<A17>",
|
||||
"<A18>",
|
||||
"<A19>",
|
||||
"<A20>",
|
||||
"<A21>",
|
||||
"<A22>",
|
||||
"<A23>",
|
||||
"<A24>",
|
||||
"<A25>",
|
||||
"<A26>",
|
||||
"<A27>",
|
||||
"<A28>",
|
||||
"<A29>",
|
||||
"<A30>",
|
||||
"<A31>",
|
||||
"<A32>",
|
||||
"<A33>",
|
||||
"<A34>",
|
||||
"<A35>",
|
||||
"<A36>",
|
||||
"<A37>",
|
||||
"<A38>",
|
||||
"<A39>",
|
||||
"<A40>",
|
||||
"<A41>",
|
||||
"<A42>",
|
||||
"<A43>",
|
||||
"<A44>",
|
||||
"<A45>",
|
||||
"<A46>",
|
||||
"<A47>",
|
||||
"<A48>",
|
||||
"<A49>",
|
||||
"<A50>",
|
||||
"<A51>",
|
||||
"<A52>",
|
||||
"<A53>",
|
||||
"<A54>",
|
||||
"<A55>",
|
||||
"<A56>",
|
||||
"<A57>",
|
||||
"<A58>",
|
||||
"<A59>",
|
||||
"<A60>",
|
||||
"<A61>",
|
||||
"<A62>",
|
||||
"<A63>",
|
||||
"<A64>",
|
||||
"<A65>",
|
||||
"<A66>",
|
||||
"<A67>",
|
||||
"<A68>",
|
||||
"<A69>",
|
||||
"<A70>",
|
||||
"<A71>",
|
||||
"<A72>",
|
||||
"<A73>",
|
||||
"<A74>",
|
||||
"<A75>",
|
||||
"<A76>",
|
||||
"<A77>",
|
||||
"<A78>",
|
||||
"<A79>",
|
||||
"<A80>",
|
||||
"<A81>",
|
||||
"<A82>",
|
||||
"<A83>",
|
||||
"<A84>",
|
||||
"<A85>",
|
||||
"<A86>",
|
||||
"<A87>",
|
||||
"<A88>",
|
||||
"<A89>",
|
||||
"<A90>",
|
||||
"<A91>",
|
||||
"<A92>",
|
||||
"<A93>",
|
||||
"<A94>",
|
||||
"<A95>",
|
||||
"<A96>",
|
||||
"<A97>",
|
||||
"<A98>",
|
||||
"<A99>",
|
||||
"<A100>"
|
||||
],
|
||||
"is_local": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|pad|>",
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
39
training_config.json
Normal file
39
training_config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"saved_at": "2026-06-22T13:46:46",
|
||||
"model_name": "/disk/u/yu.stev/influence-benchmarking-hops/models/distractor-base",
|
||||
"dataset_path": "/disk/u/yu.stev/influence-benchmarking-hops/dataset-generator/datasets/0/50/sd_distractor/10.jsonl",
|
||||
"output_dir": "/disk/u/yu.stev/influence-benchmarking-hops/models/0/10doc/v2-distractor-model",
|
||||
"seed_path": "/disk/u/yu.stev/influence-benchmarking-hops/dataset-generator/seed/0/50.jsonl",
|
||||
"epochs": 40,
|
||||
"batch_size": 10,
|
||||
"gradient_accumulation_steps": 1,
|
||||
"effective_batch_size": 10,
|
||||
"max_steps": null,
|
||||
"max_length": 2048,
|
||||
"seed": 42,
|
||||
"learning_rate": 0.0002,
|
||||
"lr_scheduler": "cosine",
|
||||
"lr_min": 2e-05,
|
||||
"warmup_steps": 100,
|
||||
"constant_steps": 1500,
|
||||
"shuffle_training": true,
|
||||
"shuffle_validation": true,
|
||||
"family_batching": false,
|
||||
"family_spreading": false,
|
||||
"alternating_update": false,
|
||||
"alternating_ratio": null,
|
||||
"checkpoint_fraction": 0.25,
|
||||
"save_steps_override": 1000,
|
||||
"hop_depth": null,
|
||||
"bf16": true,
|
||||
"fp16": false,
|
||||
"prompt_format": "output",
|
||||
"use_hops_eval": false,
|
||||
"use_depth0_eval": true,
|
||||
"eval_hop_depths": [
|
||||
0
|
||||
],
|
||||
"normal_tokens_test": false,
|
||||
"num_functions": 10,
|
||||
"track_depth_loss": true
|
||||
}
|
||||
Reference in New Issue
Block a user