Image-Text-to-Text
Transformers
Safetensors
English
gemma4
text-generation-inference
unsloth
rewrite
lora
conversational
Instructions to use Oysiyl/gemma-4-31b-unslop-good-lora-v2-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Oysiyl/gemma-4-31b-unslop-good-lora-v2-full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Oysiyl/gemma-4-31b-unslop-good-lora-v2-full") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Oysiyl/gemma-4-31b-unslop-good-lora-v2-full") model = AutoModelForMultimodalLM.from_pretrained("Oysiyl/gemma-4-31b-unslop-good-lora-v2-full") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Oysiyl/gemma-4-31b-unslop-good-lora-v2-full with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Oysiyl/gemma-4-31b-unslop-good-lora-v2-full" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Oysiyl/gemma-4-31b-unslop-good-lora-v2-full", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Oysiyl/gemma-4-31b-unslop-good-lora-v2-full
- SGLang
How to use Oysiyl/gemma-4-31b-unslop-good-lora-v2-full with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Oysiyl/gemma-4-31b-unslop-good-lora-v2-full" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Oysiyl/gemma-4-31b-unslop-good-lora-v2-full", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Oysiyl/gemma-4-31b-unslop-good-lora-v2-full" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Oysiyl/gemma-4-31b-unslop-good-lora-v2-full", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Unsloth Studio
How to use Oysiyl/gemma-4-31b-unslop-good-lora-v2-full 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 Oysiyl/gemma-4-31b-unslop-good-lora-v2-full 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 Oysiyl/gemma-4-31b-unslop-good-lora-v2-full to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Oysiyl/gemma-4-31b-unslop-good-lora-v2-full to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Oysiyl/gemma-4-31b-unslop-good-lora-v2-full", max_seq_length=2048, ) - Docker Model Runner
How to use Oysiyl/gemma-4-31b-unslop-good-lora-v2-full with Docker Model Runner:
docker model run hf.co/Oysiyl/gemma-4-31b-unslop-good-lora-v2-full
(Trained with Unsloth)
Browse files- .gitattributes +1 -0
- chat_template.jinja +48 -0
- processor_config.json +75 -0
- tokenizer.json +3 -0
- tokenizer_config.json +96 -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 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{%- if messages[0]['role'] == 'system' -%}
|
| 2 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 3 |
+
|
| 4 |
+
' -%}
|
| 5 |
+
{%- set loop_messages = messages[1:] -%}
|
| 6 |
+
{%- else -%}
|
| 7 |
+
{%- set first_user_prefix = "" -%}
|
| 8 |
+
{%- set loop_messages = messages -%}
|
| 9 |
+
{%- endif -%}
|
| 10 |
+
{%- for message in loop_messages -%}
|
| 11 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 12 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 15 |
+
{%- set role = "model" -%}
|
| 16 |
+
{%- else -%}
|
| 17 |
+
{%- set role = message['role'] -%}
|
| 18 |
+
{%- endif -%}
|
| 19 |
+
{{ '<|turn>' + role + '
|
| 20 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 21 |
+
{%- if role == "model" -%}
|
| 22 |
+
{{ '<|channel>thought
|
| 23 |
+
<channel|>' }}
|
| 24 |
+
{%- endif -%}
|
| 25 |
+
{%- if message['content'] is string -%}
|
| 26 |
+
{{ message['content'] | trim }}
|
| 27 |
+
{%- elif message['content'] is iterable -%}
|
| 28 |
+
{%- for item in message['content'] -%}
|
| 29 |
+
{%- if item['type'] == 'audio' -%}
|
| 30 |
+
{{ '<|audio|>' }}
|
| 31 |
+
{%- elif item['type'] == 'image' -%}
|
| 32 |
+
{{ '<|image|>' }}
|
| 33 |
+
{%- elif item['type'] == 'video' -%}
|
| 34 |
+
{{ '<|video|>' }}
|
| 35 |
+
{%- elif item['type'] == 'text' -%}
|
| 36 |
+
{{ item['text'] | trim }}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- endfor -%}
|
| 39 |
+
{%- else -%}
|
| 40 |
+
{{ raise_exception("Invalid content type") }}
|
| 41 |
+
{%- endif -%}
|
| 42 |
+
{{ '<turn|>
|
| 43 |
+
' }}
|
| 44 |
+
{%- endfor -%}
|
| 45 |
+
{%- if add_generation_prompt -%}
|
| 46 |
+
{{'<|turn>model
|
| 47 |
+
'}}
|
| 48 |
+
{%- endif -%}
|
processor_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_ms_per_token": 40,
|
| 3 |
+
"audio_seq_length": 750,
|
| 4 |
+
"feature_extractor": {
|
| 5 |
+
"dither": 0.0,
|
| 6 |
+
"feature_extractor_type": "Gemma4AudioFeatureExtractor",
|
| 7 |
+
"feature_size": 128,
|
| 8 |
+
"fft_length": 512,
|
| 9 |
+
"fft_overdrive": false,
|
| 10 |
+
"frame_length": 320,
|
| 11 |
+
"hop_length": 160,
|
| 12 |
+
"input_scale_factor": 1.0,
|
| 13 |
+
"max_frequency": 8000.0,
|
| 14 |
+
"mel_floor": 0.001,
|
| 15 |
+
"min_frequency": 0.0,
|
| 16 |
+
"padding_side": "left",
|
| 17 |
+
"padding_value": 0.0,
|
| 18 |
+
"per_bin_mean": null,
|
| 19 |
+
"per_bin_stddev": null,
|
| 20 |
+
"preemphasis": 0.0,
|
| 21 |
+
"preemphasis_htk_flavor": true,
|
| 22 |
+
"return_attention_mask": true,
|
| 23 |
+
"sampling_rate": 16000
|
| 24 |
+
},
|
| 25 |
+
"image_processor": {
|
| 26 |
+
"do_convert_rgb": true,
|
| 27 |
+
"do_normalize": false,
|
| 28 |
+
"do_rescale": true,
|
| 29 |
+
"do_resize": true,
|
| 30 |
+
"image_mean": [
|
| 31 |
+
0.0,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0
|
| 34 |
+
],
|
| 35 |
+
"image_processor_type": "Gemma4ImageProcessor",
|
| 36 |
+
"image_seq_length": 280,
|
| 37 |
+
"image_std": [
|
| 38 |
+
1.0,
|
| 39 |
+
1.0,
|
| 40 |
+
1.0
|
| 41 |
+
],
|
| 42 |
+
"max_soft_tokens": 280,
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"pooling_kernel_size": 3,
|
| 45 |
+
"resample": 3,
|
| 46 |
+
"rescale_factor": 0.00392156862745098
|
| 47 |
+
},
|
| 48 |
+
"image_seq_length": 280,
|
| 49 |
+
"processor_class": "Gemma4Processor",
|
| 50 |
+
"video_processor": {
|
| 51 |
+
"do_convert_rgb": true,
|
| 52 |
+
"do_normalize": true,
|
| 53 |
+
"do_rescale": true,
|
| 54 |
+
"do_resize": true,
|
| 55 |
+
"do_sample_frames": true,
|
| 56 |
+
"image_mean": [
|
| 57 |
+
0.0,
|
| 58 |
+
0.0,
|
| 59 |
+
0.0
|
| 60 |
+
],
|
| 61 |
+
"image_std": [
|
| 62 |
+
1.0,
|
| 63 |
+
1.0,
|
| 64 |
+
1.0
|
| 65 |
+
],
|
| 66 |
+
"max_soft_tokens": 70,
|
| 67 |
+
"num_frames": 32,
|
| 68 |
+
"patch_size": 16,
|
| 69 |
+
"pooling_kernel_size": 3,
|
| 70 |
+
"resample": 3,
|
| 71 |
+
"rescale_factor": 0.00392156862745098,
|
| 72 |
+
"return_metadata": false,
|
| 73 |
+
"video_processor_type": "Gemma4VideoProcessor"
|
| 74 |
+
}
|
| 75 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
|
| 3 |
+
size 32169626
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<turn|>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"is_local": false,
|
| 21 |
+
"mask_token": "<mask>",
|
| 22 |
+
"model_max_length": 262144,
|
| 23 |
+
"model_specific_special_tokens": {
|
| 24 |
+
"audio_token": "<|audio|>",
|
| 25 |
+
"boa_token": "<|audio>",
|
| 26 |
+
"boi_token": "<|image>",
|
| 27 |
+
"eoa_token": "<audio|>",
|
| 28 |
+
"eoc_token": "<channel|>",
|
| 29 |
+
"eoi_token": "<image|>",
|
| 30 |
+
"eot_token": "<turn|>",
|
| 31 |
+
"escape_token": "<|\"|>",
|
| 32 |
+
"etc_token": "<tool_call|>",
|
| 33 |
+
"etd_token": "<tool|>",
|
| 34 |
+
"etr_token": "<tool_response|>",
|
| 35 |
+
"image_token": "<|image|>",
|
| 36 |
+
"soc_token": "<|channel>",
|
| 37 |
+
"sot_token": "<|turn>",
|
| 38 |
+
"stc_token": "<|tool_call>",
|
| 39 |
+
"std_token": "<|tool>",
|
| 40 |
+
"str_token": "<|tool_response>",
|
| 41 |
+
"think_token": "<|think|>"
|
| 42 |
+
},
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
+
"padding_side": "right",
|
| 45 |
+
"processor_class": "Gemma4Processor",
|
| 46 |
+
"response_schema": {
|
| 47 |
+
"properties": {
|
| 48 |
+
"content": {
|
| 49 |
+
"type": "string"
|
| 50 |
+
},
|
| 51 |
+
"role": {
|
| 52 |
+
"const": "assistant"
|
| 53 |
+
},
|
| 54 |
+
"thinking": {
|
| 55 |
+
"type": "string"
|
| 56 |
+
},
|
| 57 |
+
"tool_calls": {
|
| 58 |
+
"items": {
|
| 59 |
+
"properties": {
|
| 60 |
+
"function": {
|
| 61 |
+
"properties": {
|
| 62 |
+
"arguments": {
|
| 63 |
+
"additionalProperties": {},
|
| 64 |
+
"type": "object",
|
| 65 |
+
"x-parser": "gemma4-tool-call"
|
| 66 |
+
},
|
| 67 |
+
"name": {
|
| 68 |
+
"type": "string"
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"type": "object",
|
| 72 |
+
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
|
| 73 |
+
},
|
| 74 |
+
"type": {
|
| 75 |
+
"const": "function"
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"type": "object"
|
| 79 |
+
},
|
| 80 |
+
"type": "array",
|
| 81 |
+
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"type": "object",
|
| 85 |
+
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
|
| 86 |
+
},
|
| 87 |
+
"soc_token": "<|channel>",
|
| 88 |
+
"sot_token": "<|turn>",
|
| 89 |
+
"stc_token": "<|tool_call>",
|
| 90 |
+
"std_token": "<|tool>",
|
| 91 |
+
"str_token": "<|tool_response>",
|
| 92 |
+
"think_token": "<|think|>",
|
| 93 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 94 |
+
"unk_token": "<unk>",
|
| 95 |
+
"chat_template": "{{ bos_token }}{%- if messages[0]['role'] == 'system' -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<|turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if role == \"model\" -%}\n {{ '<|channel>thought\n<channel|>' }}\n {%- endif -%}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'audio' -%}\n {{ '<|audio|>' }}\n {%- elif item['type'] == 'image' -%}\n {{ '<|image|>' }}\n {%- elif item['type'] == 'video' -%}\n {{ '<|video|>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<turn|>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<|turn>model\n'}}\n{%- endif -%}\n"
|
| 96 |
+
}
|