初始化项目，由ModelHub XC社区提供模型
Model: Ba2han/TR_SFT1 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
|
||||
59
README.md
Normal file
59
README.md
Normal file
@@ -0,0 +1,59 @@
|
||||
---
|
||||
base_model: Ba2han/TR_CPT1
|
||||
library_name: transformers
|
||||
model_name: TR_SFT1
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- unsloth
|
||||
- trl
|
||||
- sft
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for TR_SFT1
|
||||
|
||||
This model is a fine-tuned version of [Ba2han/TR_CPT1](https://huggingface.co/Ba2han/TR_CPT1).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="Ba2han/TR_SFT1", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/mcwb9m5k)
|
||||
|
||||
|
||||
This model was trained with SFT.
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.24.0
|
||||
- Transformers: 5.5.0
|
||||
- Pytorch: 2.10.0+cu128
|
||||
- Datasets: 4.6.0
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## Citations
|
||||
|
||||
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
79
config.json
Normal file
79
config.json
Normal file
@@ -0,0 +1,79 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 2,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 60800,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1664,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4160,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 16384,
|
||||
"max_window_layers": 42,
|
||||
"model_name": "Ba2han/TR_CPT1",
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 42,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-08,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 500000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.0",
|
||||
"unsloth_version": "2026.7.3",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 60802
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 2,
|
||||
"eos_token_id": [
|
||||
60800
|
||||
],
|
||||
"max_length": 16384,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.5.0",
|
||||
"use_cache": true
|
||||
}
|
||||
79
last-checkpoint/config.json
Normal file
79
last-checkpoint/config.json
Normal file
@@ -0,0 +1,79 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 2,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 60800,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1664,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4160,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 16384,
|
||||
"max_window_layers": 42,
|
||||
"model_name": "Ba2han/TR_CPT1",
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 42,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-08,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 500000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.0",
|
||||
"unsloth_version": "2026.7.3",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 60802
|
||||
}
|
||||
13
last-checkpoint/generation_config.json
Normal file
13
last-checkpoint/generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 2,
|
||||
"eos_token_id": [
|
||||
60800
|
||||
],
|
||||
"max_length": 16384,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.5.0",
|
||||
"use_cache": true
|
||||
}
|
||||
3
last-checkpoint/model.safetensors
Normal file
3
last-checkpoint/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:444f8e6475160464800dc3f02b41df88fb6caaf98ab7393bbe5d3cc8a9b1ece0
|
||||
size 2519936480
|
||||
3
last-checkpoint/optimizer.pt
Normal file
3
last-checkpoint/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39a984d4d140fc45c490718593f0570c050d71dd9fb6d8c13bcf17878db392df
|
||||
size 1264135916
|
||||
3
last-checkpoint/rng_state.pth
Normal file
3
last-checkpoint/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d895ccae2b55d4ea213653ca4a80d00de131463e105716eab1b7022906f260bf
|
||||
size 14645
|
||||
3
last-checkpoint/scheduler.pt
Normal file
3
last-checkpoint/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12cc6d25a39617e6875f615d3e0ce3a2ce34e124bcc00c88f25a778a01998927
|
||||
size 10233
|
||||
245730
last-checkpoint/tokenizer.json
Normal file
245730
last-checkpoint/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2113
last-checkpoint/tokenizer_config.json
Normal file
2113
last-checkpoint/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
8558
last-checkpoint/trainer_state.json
Normal file
8558
last-checkpoint/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
last-checkpoint/training_args.bin
Normal file
3
last-checkpoint/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6a70857fc7b425a9a432cca309169524a290b2fa609f73671103a638c34ce331
|
||||
size 5777
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:444f8e6475160464800dc3f02b41df88fb6caaf98ab7393bbe5d3cc8a9b1ece0
|
||||
size 2519936480
|
||||
245730
tokenizer.json
Normal file
245730
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2113
tokenizer_config.json
Normal file
2113
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6a70857fc7b425a9a432cca309169524a290b2fa609f73671103a638c34ce331
|
||||
size 5777
|
||||
Reference in New Issue
Block a user