Hugging Face's logo

Ba2han
/
model-sft-4096

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
unsloth
trl
sft
conversational
text-generation-inference
Model card Files
xet
 Community
Ba2han commited on
Commit
3251b0c
·
verified ·
1 Parent(s): 915a5bc

Training in progress, step 4155

Browse files
Files changed (4) hide show
  1. README.md +9 -8
  2. config.json +2 -2
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,17 +1,18 @@
1
  ---
 
2
  library_name: transformers
3
  model_name: model-sft-4096
4
  tags:
5
  - generated_from_trainer
6
- - trl
7
  - unsloth
 
8
  - sft
9
  licence: license
10
  ---
11
 
12
  # Model Card for model-sft-4096
13
 
14
- This model is a fine-tuned version of [None](https://huggingface.co/None).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -27,18 +28,18 @@ 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/smjyp32k)
31
 
32
 
33
  This model was trained with SFT.
34
 
35
  ### Framework versions
36
 
37
- - TRL: 0.24.0
38
- - Transformers: 4.57.2
39
- - Pytorch: 2.9.1
40
- - Datasets: 4.3.0
41
- - Tokenizers: 0.22.1
42
 
43
  ## Citations
44
 
 
1
  ---
2
+ base_model: Ba2han/model-phase2-4096
3
  library_name: transformers
4
  model_name: model-sft-4096
5
  tags:
6
  - generated_from_trainer
 
7
  - unsloth
8
+ - trl
9
  - sft
10
  licence: license
11
  ---
12
 
13
  # Model Card for model-sft-4096
14
 
15
+ This model is a fine-tuned version of [Ba2han/model-phase2-4096](https://huggingface.co/Ba2han/model-phase2-4096).
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/xv3hwg0z)
32
 
33
 
34
  This model was trained with SFT.
35
 
36
  ### Framework versions
37
 
38
+ - TRL: 0.23.0
39
+ - Transformers: 4.56.1
40
+ - Pytorch: 2.8.0
41
+ - Datasets: 4.2.0
42
+ - Tokenizers: 0.22.0
43
 
44
  ## Citations
45
 
config.json CHANGED
@@ -24,8 +24,8 @@
24
  "rope_scaling": null,
25
  "rope_theta": 100000.0,
26
  "tie_word_embeddings": true,
27
- "transformers_version": "4.57.2",
28
- "unsloth_version": "2025.11.6",
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": "4.56.1",
28
+ "unsloth_version": "2025.10.10",
29
  "use_cache": true,
30
  "vocab_size": 65536
31
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8e836a3ea01d6392da85a4b90ea922479a4a583a39afa2bc4f368ddb209647d
3
  size 1000555808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e35c5fcf3cf67fc84de6ee51193bd64a5075e0209f07e3ed81e4f6580f03d40d
3
  size 1000555808
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:076a24e17a0bfdb2a34171d30bfaa988c52bb3a902f9f94012008c58f037ded1
3
  size 6289
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6838e9fbcc948cfbcc3712684628a08224c0c1e4ae3195c744ea4725f918f8e0
3
  size 6289