Instructions to use Srishtik/gemma_adapter_unsloth_subset_2_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Srishtik/gemma_adapter_unsloth_subset_2_1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Srishtik/gemma_adapter_unsloth_subset_2_1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use Srishtik/gemma_adapter_unsloth_subset_2_1 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Srishtik/gemma_adapter_unsloth_subset_2_1 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Srishtik/gemma_adapter_unsloth_subset_2_1 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Srishtik/gemma_adapter_unsloth_subset_2_1 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Srishtik/gemma_adapter_unsloth_subset_2_1", max_seq_length=2048, )
Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- .gitattributes +1 -0
- chat_template.jinja +50 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -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
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# Unsloth Chat template fixes #}
|
| 2 |
+
{{ bos_token }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 4 |
+
{%- if messages[0]['content'] is string -%}
|
| 5 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 6 |
+
|
| 7 |
+
' -%}
|
| 8 |
+
{%- else -%}
|
| 9 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 10 |
+
|
| 11 |
+
' -%}
|
| 12 |
+
{%- endif -%}
|
| 13 |
+
{%- set loop_messages = messages[1:] -%}
|
| 14 |
+
{%- else -%}
|
| 15 |
+
{%- set first_user_prefix = "" -%}
|
| 16 |
+
{%- set loop_messages = messages -%}
|
| 17 |
+
{%- endif -%}
|
| 18 |
+
{%- for message in loop_messages -%}
|
| 19 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 20 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 21 |
+
{%- endif -%}
|
| 22 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 23 |
+
{%- set role = "model" -%}
|
| 24 |
+
{%- else -%}
|
| 25 |
+
{%- set role = message['role'] -%}
|
| 26 |
+
{%- endif -%}
|
| 27 |
+
{{ '<start_of_turn>' + role + '
|
| 28 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 29 |
+
{%- if message['content'] is string -%}
|
| 30 |
+
{{ message['content'] | trim }}
|
| 31 |
+
{%- elif message['content'] is iterable -%}
|
| 32 |
+
{%- for item in message['content'] -%}
|
| 33 |
+
{%- if item['type'] == 'image' -%}
|
| 34 |
+
{{ '<start_of_image>' }}
|
| 35 |
+
{%- elif item['type'] == 'text' -%}
|
| 36 |
+
{{ item['text'] | trim }}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- endfor -%}
|
| 39 |
+
{%- elif message['content'] is defined -%}
|
| 40 |
+
{{ raise_exception("Invalid content type") }}
|
| 41 |
+
{%- endif -%}
|
| 42 |
+
{{ '<end_of_turn>
|
| 43 |
+
' }}
|
| 44 |
+
{%- endfor -%}
|
| 45 |
+
{%- if add_generation_prompt -%}
|
| 46 |
+
{{'<start_of_turn>model
|
| 47 |
+
'}}
|
| 48 |
+
{%- endif -%}
|
| 49 |
+
|
| 50 |
+
{# Copyright 2025-present Unsloth. Apache 2.0 License. #}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
|
| 3 |
+
size 33384443
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|