End of training
Browse files- README.md +58 -0
- chat_template.jinja +2 -0
- config.json +1 -2
- generation_config.json +7 -0
- model.safetensors +1 -1
- runs/May14_00-31-27_c1110a-s29.ufhpc/events.out.tfevents.1747197088.c1110a-s29.ufhpc.2578612.0 +3 -0
- tokenizer_config.json +0 -1
- training_args.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: SmolVLM-500M-ActivityTracking
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for SmolVLM-500M-ActivityTracking
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [HuggingFaceTB/SmolVLM2-500M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
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?"
|
| 23 |
+
generator = pipeline("text-generation", model="lukesutor/SmolVLM-500M-ActivityTracking", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.17.0
|
| 38 |
+
- Transformers: 4.52.0.dev0
|
| 39 |
+
- Pytorch: 2.7.0
|
| 40 |
+
- Datasets: 3.6.0
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
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},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
|
| 2 |
+
{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
|
config.json
CHANGED
|
@@ -29,7 +29,6 @@
|
|
| 29 |
"num_key_value_heads": 5,
|
| 30 |
"pad_token_id": 2,
|
| 31 |
"perceiver_config": {
|
| 32 |
-
"_attn_implementation_autoset": false,
|
| 33 |
"_name_or_path": "",
|
| 34 |
"add_cross_attention": false,
|
| 35 |
"architectures": null,
|
|
@@ -127,7 +126,7 @@
|
|
| 127 |
"q4f16": "float16"
|
| 128 |
}
|
| 129 |
},
|
| 130 |
-
"transformers_version": "4.
|
| 131 |
"use_cache": false,
|
| 132 |
"use_reentrant_checkpointing": false,
|
| 133 |
"vision_config": {
|
|
|
|
| 29 |
"num_key_value_heads": 5,
|
| 30 |
"pad_token_id": 2,
|
| 31 |
"perceiver_config": {
|
|
|
|
| 32 |
"_name_or_path": "",
|
| 33 |
"add_cross_attention": false,
|
| 34 |
"architectures": null,
|
|
|
|
| 126 |
"q4f16": "float16"
|
| 127 |
}
|
| 128 |
},
|
| 129 |
+
"transformers_version": "4.52.0.dev0",
|
| 130 |
"use_cache": false,
|
| 131 |
"use_reentrant_checkpointing": false,
|
| 132 |
"vision_config": {
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 49279,
|
| 5 |
+
"pad_token_id": 2,
|
| 6 |
+
"transformers_version": "4.52.0.dev0"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2029990624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a46cc8fa76af56bd162e682629e8cdf0eb0705e88c35930943ceb1822cca082b
|
| 3 |
size 2029990624
|
runs/May14_00-31-27_c1110a-s29.ufhpc/events.out.tfevents.1747197088.c1110a-s29.ufhpc.2578612.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfc723995ac61db114f2b6ae5fdfceb3ba1ea004f4ab4f7ca37e7d738a2d9fc9
|
| 3 |
+
size 17146
|
tokenizer_config.json
CHANGED
|
@@ -1168,7 +1168,6 @@
|
|
| 1168 |
"<end_of_utterance>"
|
| 1169 |
],
|
| 1170 |
"bos_token": "<|im_start|>",
|
| 1171 |
-
"chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
|
| 1172 |
"clean_up_tokenization_spaces": false,
|
| 1173 |
"end_of_utterance_token": "<end_of_utterance>",
|
| 1174 |
"eos_token": "<end_of_utterance>",
|
|
|
|
| 1168 |
"<end_of_utterance>"
|
| 1169 |
],
|
| 1170 |
"bos_token": "<|im_start|>",
|
|
|
|
| 1171 |
"clean_up_tokenization_spaces": false,
|
| 1172 |
"end_of_utterance_token": "<end_of_utterance>",
|
| 1173 |
"eos_token": "<end_of_utterance>",
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6225
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cccfff942ebb2f1714d438cbd302e57d5455650511cbc222538b2b7fc59fafde
|
| 3 |
size 6225
|