Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +64 -3
- chat_template.jinja +49 -0
- config.json +208 -0
- generation_config.json +13 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +51 -0
- processor_config.json +5 -0
- special_tokens_map.json +36 -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
|
README.md
CHANGED
|
@@ -1,3 +1,64 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-3n-E2B-it
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
library_name: transformers
|
| 7 |
+
license: gemma
|
| 8 |
+
tags:
|
| 9 |
+
- gemma3
|
| 10 |
+
- unsloth
|
| 11 |
+
- transformers
|
| 12 |
+
- gemma
|
| 13 |
+
- google
|
| 14 |
+
---
|
| 15 |
+
<div>
|
| 16 |
+
<p style="margin-bottom: 0; margin-top: 0;">
|
| 17 |
+
<strong>Learn how to run & fine-tune Gemma 3n correctly - <a href="https://docs.unsloth.ai/basics/gemma-3n">Read our Guide</a>.</strong>
|
| 18 |
+
</p>
|
| 19 |
+
<p style="margin-bottom: 0;">
|
| 20 |
+
<em>See <a href="https://huggingface.co/collections/unsloth/gemma-3n-685d3874830e49e1c93f9339">our collection</a> for all versions of Gemma 3n including GGUF, 4-bit & 16-bit formats.</em>
|
| 21 |
+
</p>
|
| 22 |
+
<p style="margin-top: 0;margin-bottom: 0;">
|
| 23 |
+
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves SOTA accuracy & performance versus other quants.</em>
|
| 24 |
+
</p>
|
| 25 |
+
<div style="display: flex; gap: 5px; align-items: center; ">
|
| 26 |
+
<a href="https://github.com/unslothai/unsloth/">
|
| 27 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
| 28 |
+
</a>
|
| 29 |
+
<a href="https://discord.gg/unsloth">
|
| 30 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
| 31 |
+
</a>
|
| 32 |
+
<a href="https://docs.unsloth.ai/basics/gemma-3n">
|
| 33 |
+
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
| 34 |
+
</a>
|
| 35 |
+
</div>
|
| 36 |
+
<h1 style="margin-top:0; margin-bottom: 0;">✨ Gemma 3n Usage Guidelines</h1>
|
| 37 |
+
</div>
|
| 38 |
+
|
| 39 |
+
- Currently **only text** is supported.
|
| 40 |
+
- Ollama: `ollama run hf.co/unsloth/gemma-3n-E4B-it:Q4_K_XL` - auto-sets correct chat template and settings
|
| 41 |
+
- Set temperature = 1.0, top_k = 64, top_p = 0.95, min_p = 0.0
|
| 42 |
+
- Gemma 3n max tokens (context length): 32K. Gemma 3n chat template:
|
| 43 |
+
```
|
| 44 |
+
<bos><start_of_turn>user\nHello!<end_of_turn>\n<start_of_turn>model\nHey there!<end_of_turn>\n<start_of_turn>user\nWhat is 1+1?<end_of_turn>\n<start_of_turn>model\n
|
| 45 |
+
```
|
| 46 |
+
- For complete detailed instructions, see our [step-by-step guide](https://docs.unsloth.ai/basics/gemma-3n).
|
| 47 |
+
|
| 48 |
+
# 🦥 Fine-tune Gemma 3n with Unsloth
|
| 49 |
+
|
| 50 |
+
- Fine-tune Gemma 3n (4B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)!
|
| 51 |
+
- Read our Blog about Gemma 3n support: [unsloth.ai/blog/gemma-3n](https://unsloth.ai/blog/gemma-3n)
|
| 52 |
+
- View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
|
| 53 |
+
|
| 54 |
+
| Unsloth supports | Free Notebooks | Performance | Memory use |
|
| 55 |
+
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
|
| 56 |
+
| **Gemma-3n-E4B** | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks) | 2x faster | 80% less |
|
| 57 |
+
| **GRPO with Gemma 3 (1B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3_(1B)-GRPO.ipynb) | 2x faster | 80% less |
|
| 58 |
+
| **Gemma 3 (4B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Gemma3_(4B).ipynb) | 2x faster | 60% less |
|
| 59 |
+
| **Qwen3 (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_(14B)-Reasoning-Conversational.ipynb) | 2x faster | 60% less |
|
| 60 |
+
| **DeepSeek-R1-0528-Qwen3-8B (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/DeepSeek_R1_0528_Qwen3_(8B)_GRPO.ipynb) | 2x faster | 80% less |
|
| 61 |
+
| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) | 2.4x faster | 58% less |
|
| 62 |
+
<br>
|
| 63 |
+
|
| 64 |
+
# Gemma-3n-E4B model card
|
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 -%}
|
config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3nForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": {
|
| 6 |
+
"conf_attention_chunk_size": 12,
|
| 7 |
+
"conf_attention_context_left": 13,
|
| 8 |
+
"conf_attention_context_right": 0,
|
| 9 |
+
"conf_attention_logit_cap": 50.0,
|
| 10 |
+
"conf_conv_kernel_size": 5,
|
| 11 |
+
"conf_num_attention_heads": 8,
|
| 12 |
+
"conf_num_hidden_layers": 12,
|
| 13 |
+
"conf_reduction_factor": 4,
|
| 14 |
+
"conf_residual_weight": 0.5,
|
| 15 |
+
"gradient_clipping": 10000000000.0,
|
| 16 |
+
"hidden_size": 1536,
|
| 17 |
+
"input_feat_size": 128,
|
| 18 |
+
"model_type": "gemma3n_audio",
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"sscp_conv_channel_size": [
|
| 21 |
+
128,
|
| 22 |
+
32
|
| 23 |
+
],
|
| 24 |
+
"sscp_conv_group_norm_eps": 0.001,
|
| 25 |
+
"sscp_conv_kernel_size": [
|
| 26 |
+
[
|
| 27 |
+
3,
|
| 28 |
+
3
|
| 29 |
+
],
|
| 30 |
+
[
|
| 31 |
+
3,
|
| 32 |
+
3
|
| 33 |
+
]
|
| 34 |
+
],
|
| 35 |
+
"sscp_conv_stride_size": [
|
| 36 |
+
[
|
| 37 |
+
2,
|
| 38 |
+
2
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
]
|
| 44 |
+
],
|
| 45 |
+
"torch_dtype": "bfloat16",
|
| 46 |
+
"vocab_offset": 262272,
|
| 47 |
+
"vocab_size": 128
|
| 48 |
+
},
|
| 49 |
+
"audio_soft_tokens_per_image": 188,
|
| 50 |
+
"audio_token_id": 262273,
|
| 51 |
+
"boa_token_id": 256000,
|
| 52 |
+
"boi_token_id": 255999,
|
| 53 |
+
"bos_token_id": 2,
|
| 54 |
+
"eoa_token_id": 262272,
|
| 55 |
+
"eoi_token_id": 262144,
|
| 56 |
+
"eos_token_id": 106,
|
| 57 |
+
"image_token_id": 262145,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"model_type": "gemma3n",
|
| 60 |
+
"pad_token_id": 0,
|
| 61 |
+
"text_config": {
|
| 62 |
+
"activation_sparsity_pattern": [
|
| 63 |
+
0.95,
|
| 64 |
+
0.95,
|
| 65 |
+
0.95,
|
| 66 |
+
0.95,
|
| 67 |
+
0.95,
|
| 68 |
+
0.95,
|
| 69 |
+
0.95,
|
| 70 |
+
0.95,
|
| 71 |
+
0.95,
|
| 72 |
+
0.95,
|
| 73 |
+
0.0,
|
| 74 |
+
0.0,
|
| 75 |
+
0.0,
|
| 76 |
+
0.0,
|
| 77 |
+
0.0,
|
| 78 |
+
0.0,
|
| 79 |
+
0.0,
|
| 80 |
+
0.0,
|
| 81 |
+
0.0,
|
| 82 |
+
0.0,
|
| 83 |
+
0.0,
|
| 84 |
+
0.0,
|
| 85 |
+
0.0,
|
| 86 |
+
0.0,
|
| 87 |
+
0.0,
|
| 88 |
+
0.0,
|
| 89 |
+
0.0,
|
| 90 |
+
0.0,
|
| 91 |
+
0.0,
|
| 92 |
+
0.0
|
| 93 |
+
],
|
| 94 |
+
"altup_active_idx": 0,
|
| 95 |
+
"altup_coef_clip": 120.0,
|
| 96 |
+
"altup_correct_scale": true,
|
| 97 |
+
"altup_num_inputs": 4,
|
| 98 |
+
"attention_bias": false,
|
| 99 |
+
"attention_dropout": 0.0,
|
| 100 |
+
"final_logit_softcapping": 30.0,
|
| 101 |
+
"head_dim": 256,
|
| 102 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 103 |
+
"hidden_size": 2048,
|
| 104 |
+
"hidden_size_per_layer_input": 256,
|
| 105 |
+
"initializer_range": 0.02,
|
| 106 |
+
"intermediate_size": [
|
| 107 |
+
8192,
|
| 108 |
+
8192,
|
| 109 |
+
8192,
|
| 110 |
+
8192,
|
| 111 |
+
8192,
|
| 112 |
+
8192,
|
| 113 |
+
8192,
|
| 114 |
+
8192,
|
| 115 |
+
8192,
|
| 116 |
+
8192,
|
| 117 |
+
8192,
|
| 118 |
+
8192,
|
| 119 |
+
8192,
|
| 120 |
+
8192,
|
| 121 |
+
8192,
|
| 122 |
+
8192,
|
| 123 |
+
8192,
|
| 124 |
+
8192,
|
| 125 |
+
8192,
|
| 126 |
+
8192,
|
| 127 |
+
8192,
|
| 128 |
+
8192,
|
| 129 |
+
8192,
|
| 130 |
+
8192,
|
| 131 |
+
8192,
|
| 132 |
+
8192,
|
| 133 |
+
8192,
|
| 134 |
+
8192,
|
| 135 |
+
8192,
|
| 136 |
+
8192
|
| 137 |
+
],
|
| 138 |
+
"laurel_rank": 64,
|
| 139 |
+
"layer_types": [
|
| 140 |
+
"sliding_attention",
|
| 141 |
+
"sliding_attention",
|
| 142 |
+
"sliding_attention",
|
| 143 |
+
"sliding_attention",
|
| 144 |
+
"full_attention",
|
| 145 |
+
"sliding_attention",
|
| 146 |
+
"sliding_attention",
|
| 147 |
+
"sliding_attention",
|
| 148 |
+
"sliding_attention",
|
| 149 |
+
"full_attention",
|
| 150 |
+
"sliding_attention",
|
| 151 |
+
"sliding_attention",
|
| 152 |
+
"sliding_attention",
|
| 153 |
+
"sliding_attention",
|
| 154 |
+
"full_attention",
|
| 155 |
+
"sliding_attention",
|
| 156 |
+
"sliding_attention",
|
| 157 |
+
"sliding_attention",
|
| 158 |
+
"sliding_attention",
|
| 159 |
+
"full_attention",
|
| 160 |
+
"sliding_attention",
|
| 161 |
+
"sliding_attention",
|
| 162 |
+
"sliding_attention",
|
| 163 |
+
"sliding_attention",
|
| 164 |
+
"full_attention",
|
| 165 |
+
"sliding_attention",
|
| 166 |
+
"sliding_attention",
|
| 167 |
+
"sliding_attention",
|
| 168 |
+
"sliding_attention",
|
| 169 |
+
"full_attention"
|
| 170 |
+
],
|
| 171 |
+
"max_position_embeddings": 32768,
|
| 172 |
+
"model_type": "gemma3n_text",
|
| 173 |
+
"num_attention_heads": 8,
|
| 174 |
+
"num_hidden_layers": 30,
|
| 175 |
+
"num_key_value_heads": 2,
|
| 176 |
+
"num_kv_shared_layers": 10,
|
| 177 |
+
"rms_norm_eps": 1e-06,
|
| 178 |
+
"rope_local_base_freq": 10000.0,
|
| 179 |
+
"rope_scaling": null,
|
| 180 |
+
"rope_theta": 1000000.0,
|
| 181 |
+
"sliding_window": 512,
|
| 182 |
+
"torch_dtype": "bfloat16",
|
| 183 |
+
"use_cache": true,
|
| 184 |
+
"vocab_size": 262400,
|
| 185 |
+
"vocab_size_per_layer_input": 262144
|
| 186 |
+
},
|
| 187 |
+
"torch_dtype": "bfloat16",
|
| 188 |
+
"transformers_version": "4.53.1",
|
| 189 |
+
"unsloth_fixed": true,
|
| 190 |
+
"vision_config": {
|
| 191 |
+
"architecture": "mobilenetv5_300m_enc",
|
| 192 |
+
"do_pooling": false,
|
| 193 |
+
"hidden_size": 2048,
|
| 194 |
+
"initializer_range": 0.02,
|
| 195 |
+
"label_names": [
|
| 196 |
+
"LABEL_0",
|
| 197 |
+
"LABEL_1"
|
| 198 |
+
],
|
| 199 |
+
"model_args": null,
|
| 200 |
+
"model_type": "gemma3n_vision",
|
| 201 |
+
"num_classes": 2,
|
| 202 |
+
"rms_norm_eps": 1e-06,
|
| 203 |
+
"torch_dtype": "bfloat16",
|
| 204 |
+
"vocab_offset": 262144,
|
| 205 |
+
"vocab_size": 128
|
| 206 |
+
},
|
| 207 |
+
"vision_soft_tokens_per_image": 256
|
| 208 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"cache_implementation": "hybrid",
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1,
|
| 7 |
+
106
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"top_k": 64,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.53.1"
|
| 13 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:819c6c6e757dbc63ad931336cdd62373abafaf6944973e259ae18a1790cbecca
|
| 3 |
+
size 3077103576
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f53ec36e9b34a1dda547103f7371eaf4dcce40a9e85ef2a04dfa12f30e1146ff
|
| 3 |
+
size 4981242176
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28e11f2029b8d13aa3fde2a948808baa01d8bee0fd184c4faedbd09065e7fd0b
|
| 3 |
+
size 2820739840
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": false,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"dither": 0.0,
|
| 8 |
+
"do_center_crop": null,
|
| 9 |
+
"do_convert_rgb": null,
|
| 10 |
+
"do_normalize": false,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"feature_size": 128,
|
| 14 |
+
"fft_length": 1024,
|
| 15 |
+
"fft_overdrive": true,
|
| 16 |
+
"frame_length": 512,
|
| 17 |
+
"hop_length": 160,
|
| 18 |
+
"image_mean": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"image_processor_type": "SiglipImageProcessorFast",
|
| 24 |
+
"image_seq_length": 256,
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"input_data_format": null,
|
| 31 |
+
"input_scale_factor": 1.0,
|
| 32 |
+
"max_frequency": 7600.0,
|
| 33 |
+
"mel_floor": 1e-05,
|
| 34 |
+
"min_frequency": 125.0,
|
| 35 |
+
"padding_side": "left",
|
| 36 |
+
"padding_value": 0.0,
|
| 37 |
+
"per_bin_mean": null,
|
| 38 |
+
"per_bin_stddev": null,
|
| 39 |
+
"preemphasis": 0.97,
|
| 40 |
+
"preemphasis_htk_flavor": true,
|
| 41 |
+
"processor_class": "Gemma3nProcessor",
|
| 42 |
+
"resample": 2,
|
| 43 |
+
"rescale_factor": 0.00392156862745098,
|
| 44 |
+
"return_attention_mask": true,
|
| 45 |
+
"return_tensors": null,
|
| 46 |
+
"sampling_rate": 16000,
|
| 47 |
+
"size": {
|
| 48 |
+
"height": 768,
|
| 49 |
+
"width": 768
|
| 50 |
+
}
|
| 51 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_seq_length": 188,
|
| 3 |
+
"image_seq_length": 256,
|
| 4 |
+
"processor_class": "Gemma3nProcessor"
|
| 5 |
+
}
|
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": "<end_of_turn>",
|
| 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.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea5f0cc48abfbfc04d14562270a32e02149a3e7035f368cc5a462786f4a59961
|
| 3 |
+
size 4696020
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|