picard47at commited on
Commit
c8a3a8e
·
verified ·
1 Parent(s): e1e55ae

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. README.md +4 -4
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
3
  library_name: transformers
4
- model_name: punctuation_256
5
  tags:
6
  - generated_from_trainer
7
  - unsloth
@@ -10,7 +10,7 @@ tags:
10
  licence: license
11
  ---
12
 
13
- # Model Card for punctuation_256
14
 
15
  This model is a fine-tuned version of [unsloth/qwen3-0.6b-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen3-0.6b-unsloth-bnb-4bit).
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -21,14 +21,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
21
  from transformers import pipeline
22
 
23
  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?"
24
- generator = pipeline("text-generation", model="picard47at/punctuation_256", device="cuda")
25
  output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
  print(output["generated_text"])
27
  ```
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/picardtseng-pesi/punctuation/runs/v9pjz8fy)
32
 
33
 
34
  This model was trained with SFT.
 
1
  ---
2
  base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
3
  library_name: transformers
4
+ model_name: punctuation_128
5
  tags:
6
  - generated_from_trainer
7
  - unsloth
 
10
  licence: license
11
  ---
12
 
13
+ # Model Card for punctuation_128
14
 
15
  This model is a fine-tuned version of [unsloth/qwen3-0.6b-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen3-0.6b-unsloth-bnb-4bit).
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
 
21
  from transformers import pipeline
22
 
23
  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?"
24
+ generator = pipeline("text-generation", model="picard47at/punctuation_128", device="cuda")
25
  output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
  print(output["generated_text"])
27
  ```
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/picardtseng-pesi/punctuation/runs/3dy73ssa)
32
 
33
 
34
  This model was trained with SFT.
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a9fb11745691ed514c93787aa1b877416edcf35b66737b9f01b9b80b0448605
3
  size 9189904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6748fe29a64bd77d017a9eb18834a369a8ef1f5906d630a06c927996a459ee
3
  size 9189904
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1003e34bcecc258f6f26b9eefaafc83326a4fc9aa1ffdeb8c49a1b6484cc397
3
  size 6033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c8fbb7caea78492758c00ec3052b515e00c57a391be00b92d20543befeee41
3
  size 6033