Instructions to use trl-internal-testing/tiny-Gemma3ForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use trl-internal-testing/tiny-Gemma3ForConditionalGeneration with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("trl-internal-testing/tiny-Gemma3ForConditionalGeneration", dtype="auto") - Notebooks
- Google Colab
- Kaggle
File size: 1,608 Bytes
c315639 5b3dad5 c315639 ca18b3a c315639 73f1ddf c315639 ca18b3a c315639 4cb5a10 c315639 4cb5a10 c315639 ca18b3a c315639 ca18b3a c315639 ca18b3a c315639 5b3dad5 c315639 73f1ddf ca18b3a c315639 4cb5a10 c315639 4cb5a10 ca18b3a c315639 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | {
"architectures": [
"Gemma3ForConditionalGeneration"
],
"boi_token_index": 255999,
"dtype": "bfloat16",
"eoi_token_index": 256000,
"eos_token_id": [
1,
106
],
"image_token_index": 262144,
"initializer_range": 0.02,
"mm_tokens_per_image": 256,
"model_type": "gemma3",
"text_config": {
"_sliding_window_pattern": 6,
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 16,
"initializer_range": 0.02,
"intermediate_size": 10240,
"layer_types": [
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 131072,
"model_type": "gemma3_text",
"num_attention_heads": 4,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000.0,
"rope_scaling": {
"factor": 8.0,
"rope_type": "linear"
},
"rope_theta": 1000000.0,
"sliding_window": 1024,
"use_cache": true,
"vocab_size": 262208
},
"transformers_version": "4.56.1",
"vision_config": {
"attention_dropout": 0.0,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 16,
"image_size": 896,
"intermediate_size": 4304,
"layer_norm_eps": 1e-06,
"model_type": "siglip_vision_model",
"num_attention_heads": 4,
"num_channels": 3,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"patch_size": 14,
"vision_use_head": false
}
}
|