Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- README.md +58 -0
- adapter_config.json +37 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +49 -0
- runs/Jul02_21-40-03_vijay-beefy-20250702-210218/events.out.tfevents.1751492556.vijay-beefy-20250702-210218.20605.0 +3 -0
- runs/Jul02_21-47-25_vijay-beefy-20250702-210218/events.out.tfevents.1751492846.vijay-beefy-20250702-210218.2549.0 +3 -0
- runs/Jul02_21-54-29_vijay-beefy-20250702-210218/events.out.tfevents.1751493271.vijay-beefy-20250702-210218.3710.0 +3 -0
- runs/Jul02_21-57-33_vijay-beefy-20250702-210218/events.out.tfevents.1751493455.vijay-beefy-20250702-210218.4088.0 +3 -0
- runs/Jul02_21-58-40_vijay-beefy-20250702-210218/events.out.tfevents.1751493526.vijay-beefy-20250702-210218.4271.0 +3 -0
- runs/Jul02_22-00-21_vijay-beefy-20250702-210218/events.out.tfevents.1751493625.vijay-beefy-20250702-210218.4581.0 +3 -0
- runs/Jul02_22-02-35_vijay-beefy-20250702-210218/events.out.tfevents.1751493757.vijay-beefy-20250702-210218.4854.0 +3 -0
- runs/Jul02_22-03-15_vijay-beefy-20250702-210218/events.out.tfevents.1751493797.vijay-beefy-20250702-210218.4954.0 +3 -0
- runs/Jul02_23-32-01_vijay-beefy-20250702-210218/events.out.tfevents.1751499123.vijay-beefy-20250702-210218.14937.0 +3 -0
- special_tokens_map.json +36 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: google/gemma-3n-E2B-it
|
3 |
+
library_name: transformers
|
4 |
+
model_name: gemma-3n-E2B-it
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
- trl
|
8 |
+
- sft
|
9 |
+
licence: license
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Card for gemma-3n-E2B-it
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [google/gemma-3n-E2B-it](https://huggingface.co/google/gemma-3n-E2B-it).
|
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="vijay120/gemma-3n-E2B-it", 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: 0.19.0
|
38 |
+
- Transformers: 4.53.0
|
39 |
+
- Pytorch: 2.6.0+cu124
|
40 |
+
- Datasets: 3.6.0
|
41 |
+
- Tokenizers: 0.21.2
|
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 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-3n-E2B-it",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.05,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": [
|
22 |
+
"lm_head",
|
23 |
+
"embed_tokens"
|
24 |
+
],
|
25 |
+
"peft_type": "LORA",
|
26 |
+
"r": 16,
|
27 |
+
"rank_pattern": {},
|
28 |
+
"revision": null,
|
29 |
+
"target_modules": [
|
30 |
+
"v_proj",
|
31 |
+
"q_proj"
|
32 |
+
],
|
33 |
+
"task_type": "CAUSAL_LM",
|
34 |
+
"trainable_token_indices": null,
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5501880f47e89171949aed5d51a15dda19abe370b7817abd46cd10b42b097e1
|
3 |
+
size 2167104312
|
chat_template.jinja
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{{ bos_token }}
|
2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
3 |
+
{%- if messages[0]['content'] is string -%}
|
4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
5 |
+
|
6 |
+
' -%}
|
7 |
+
{%- else -%}
|
8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
9 |
+
|
10 |
+
' -%}
|
11 |
+
{%- endif -%}
|
12 |
+
{%- set loop_messages = messages[1:] -%}
|
13 |
+
{%- else -%}
|
14 |
+
{%- set first_user_prefix = "" -%}
|
15 |
+
{%- set loop_messages = messages -%}
|
16 |
+
{%- endif -%}
|
17 |
+
{%- for message in loop_messages -%}
|
18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
20 |
+
{%- endif -%}
|
21 |
+
{%- if (message['role'] == 'assistant') -%}
|
22 |
+
{%- set role = "model" -%}
|
23 |
+
{%- else -%}
|
24 |
+
{%- set role = message['role'] -%}
|
25 |
+
{%- endif -%}
|
26 |
+
{{ '<start_of_turn>' + role + '
|
27 |
+
' + (first_user_prefix if loop.first else "") }}
|
28 |
+
{%- if message['content'] is string -%}
|
29 |
+
{{ message['content'] | trim }}
|
30 |
+
{%- elif message['content'] is iterable -%}
|
31 |
+
{%- for item in message['content'] -%}
|
32 |
+
{%- if item['type'] == 'audio' -%}
|
33 |
+
{{ '<audio_soft_token>' }}
|
34 |
+
{%- elif item['type'] == 'image' -%}
|
35 |
+
{{ '<image_soft_token>' }}
|
36 |
+
{%- elif item['type'] == 'text' -%}
|
37 |
+
{{ item['text'] | trim }}
|
38 |
+
{%- endif -%}
|
39 |
+
{%- endfor -%}
|
40 |
+
{%- else -%}
|
41 |
+
{{ raise_exception("Invalid content type") }}
|
42 |
+
{%- endif -%}
|
43 |
+
{{ '<end_of_turn>
|
44 |
+
' }}
|
45 |
+
{%- endfor -%}
|
46 |
+
{%- if add_generation_prompt -%}
|
47 |
+
{{'<start_of_turn>model
|
48 |
+
'}}
|
49 |
+
{%- endif -%}
|
runs/Jul02_21-40-03_vijay-beefy-20250702-210218/events.out.tfevents.1751492556.vijay-beefy-20250702-210218.20605.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad94b9f610f4b07c565469573d70a2455a9502d5b102f4995664659919eaa713
|
3 |
+
size 9750
|
runs/Jul02_21-47-25_vijay-beefy-20250702-210218/events.out.tfevents.1751492846.vijay-beefy-20250702-210218.2549.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7695ebef0716a94f8428a40b52b4e37b8bcbf49fd3c142b66ea0d7dab5d076c
|
3 |
+
size 9750
|
runs/Jul02_21-54-29_vijay-beefy-20250702-210218/events.out.tfevents.1751493271.vijay-beefy-20250702-210218.3710.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d94c11bb5e531f3ab25546c58777544fa88274ecb284331418f233cd66f3ed5
|
3 |
+
size 9750
|
runs/Jul02_21-57-33_vijay-beefy-20250702-210218/events.out.tfevents.1751493455.vijay-beefy-20250702-210218.4088.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fe3ae2f1198085a5a4975744908a5b62f4e3783b57b1a5df523247b32139125
|
3 |
+
size 9750
|
runs/Jul02_21-58-40_vijay-beefy-20250702-210218/events.out.tfevents.1751493526.vijay-beefy-20250702-210218.4271.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32b50d59dcf150039e423bb8a3a9bed95887a206106c472b50dd5cbbc9ab636e
|
3 |
+
size 9750
|
runs/Jul02_22-00-21_vijay-beefy-20250702-210218/events.out.tfevents.1751493625.vijay-beefy-20250702-210218.4581.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc0f83b4f1c3c0c594606945adcd325d3a3946493ec22b77d6061b48fe326c3b
|
3 |
+
size 9750
|
runs/Jul02_22-02-35_vijay-beefy-20250702-210218/events.out.tfevents.1751493757.vijay-beefy-20250702-210218.4854.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2a5981056b0530a029f11337b5f51d2a70a01c2a88fa835269087817cd039d
|
3 |
+
size 9749
|
runs/Jul02_22-03-15_vijay-beefy-20250702-210218/events.out.tfevents.1751493797.vijay-beefy-20250702-210218.4954.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec23fb376ebfb5ca412b9e55ec0da4c2c2ed9934dc97f97d05de43712676dea4
|
3 |
+
size 24857
|
runs/Jul02_23-32-01_vijay-beefy-20250702-210218/events.out.tfevents.1751499123.vijay-beefy-20250702-210218.14937.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c25b5d6cb20744207f7c4ac1e7140d47d108bf1987de41ca4aa5f43137eed23a
|
3 |
+
size 111491
|
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio_token": "<audio_soft_token>",
|
3 |
+
"boa_token": "<start_of_audio>",
|
4 |
+
"boi_token": "<start_of_image>",
|
5 |
+
"bos_token": {
|
6 |
+
"content": "<bos>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eoa_token": "<end_of_audio>",
|
13 |
+
"eoi_token": "<end_of_image>",
|
14 |
+
"eos_token": {
|
15 |
+
"content": "<eos>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"image_token": "<image_soft_token>",
|
22 |
+
"pad_token": {
|
23 |
+
"content": "<pad>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"unk_token": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
|
3 |
+
size 33442553
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9f9ad6248f347920306f4b0ce549bd216ee394f6bcdf96a91b5dfddda4548c0
|
3 |
+
size 5816
|