Training in progress, step 7200
Browse files- README.md +6 -5
- config.json +2 -2
- generation_config.json +1 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,17 +1,18 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
model_name: model-layered-1
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
- sft
|
| 7 |
- trl
|
|
|
|
| 8 |
- unsloth
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
# Model Card for model-layered-1
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
@@ -27,15 +28,15 @@ print(output["generated_text"])
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
[<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/
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
| 34 |
|
| 35 |
### Framework versions
|
| 36 |
|
| 37 |
-
- TRL: 0.
|
| 38 |
-
- Transformers: 4.57.
|
| 39 |
- Pytorch: 2.9.0
|
| 40 |
- Datasets: 4.3.0
|
| 41 |
- Tokenizers: 0.22.1
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: Ba2han/model-layered-1
|
| 3 |
library_name: transformers
|
| 4 |
model_name: model-layered-1
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- trl
|
| 8 |
+
- sft
|
| 9 |
- unsloth
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
| 13 |
# Model Card for model-layered-1
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [Ba2han/model-layered-1](https://huggingface.co/Ba2han/model-layered-1).
|
| 16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
|
| 18 |
## Quick start
|
|
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
+
[<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/vnb7g5nz)
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with SFT.
|
| 35 |
|
| 36 |
### Framework versions
|
| 37 |
|
| 38 |
+
- TRL: 0.24.0
|
| 39 |
+
- Transformers: 4.57.2
|
| 40 |
- Pytorch: 2.9.0
|
| 41 |
- Datasets: 4.3.0
|
| 42 |
- Tokenizers: 0.22.1
|
config.json
CHANGED
|
@@ -24,8 +24,8 @@
|
|
| 24 |
"rope_scaling": null,
|
| 25 |
"rope_theta": 100000.0,
|
| 26 |
"tie_word_embeddings": true,
|
| 27 |
-
"transformers_version": "4.57.
|
| 28 |
-
"unsloth_version": "2025.11.
|
| 29 |
"use_cache": true,
|
| 30 |
"vocab_size": 65536
|
| 31 |
}
|
|
|
|
| 24 |
"rope_scaling": null,
|
| 25 |
"rope_theta": 100000.0,
|
| 26 |
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "4.57.2",
|
| 28 |
+
"unsloth_version": "2025.11.4",
|
| 29 |
"use_cache": true,
|
| 30 |
"vocab_size": 65536
|
| 31 |
}
|
generation_config.json
CHANGED
|
@@ -6,5 +6,5 @@
|
|
| 6 |
],
|
| 7 |
"max_length": 8192,
|
| 8 |
"pad_token_id": 2,
|
| 9 |
-
"transformers_version": "4.57.
|
| 10 |
}
|
|
|
|
| 6 |
],
|
| 7 |
"max_length": 8192,
|
| 8 |
"pad_token_id": 2,
|
| 9 |
+
"transformers_version": "4.57.2"
|
| 10 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000555808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bacc6cbb137205644a924b6e2ac7e70e9e7c5276acf871242f6bfb788d140f8c
|
| 3 |
size 1000555808
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6289
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe9b313c7a6907a628379f737f4119a5712f5a7fd8321d4bfef998b6d9984b32
|
| 3 |
size 6289
|