HuggingFaceTB/SmolVLM-256M-Instruct
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: HuggingFaceTB/SmolVLM-256M-Instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-05 22:14:12 +08:00
commit 07d60d143e
39 changed files with 297108 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

271
config.json Normal file
View File

@@ -0,0 +1,271 @@
{
"architectures": [
"Idefics3ForConditionalGeneration"
],
"image_token_id": 49190,
"model_type": "idefics3",
"scale_factor": 4,
"text_config": {
"_attn_implementation_autoset": false,
"_flash_attn_2_enabled": true,
"_name_or_path": "None",
"add_cross_attention": false,
"architectures": [
"VLlama3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 1,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 576,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.041666666666666664,
"intermediate_size": 1536,
"is_decoder": false,
"is_encoder_decoder": false,
"is_llama_config": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 8192,
"min_length": 0,
"mlp_bias": false,
"model_type": "llama",
"neftune_noise_alpha": 0.0,
"no_repeat_ngram_size": 0,
"num_attention_heads": 9,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 30,
"num_key_value_heads": 3,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 2,
"perceiver_config": {
"_attn_implementation_autoset": false,
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "silu",
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "vllama3",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_key_value_heads": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"qk_layer_norms_perceiver": false,
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"resampler_depth": 6,
"resampler_head_dim": 96,
"resampler_n_heads": 16,
"resampler_n_latents": 64,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.46.0",
"typical_p": 1.0,
"use_bfloat16": false
},
"pixel_shuffle_factor": 4,
"prefix": null,
"pretraining_tp": 1,
"problem_type": null,
"pruned_heads": {},
"qk_layer_norms": false,
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"rms_norm_eps": 1e-05,
"rope_interleaved": false,
"rope_scaling": null,
"rope_theta": 100000,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "bfloat16",
"torchscript": false,
"transformers.js_config": {
"kv_cache_dtype": {
"fp16": "float16",
"q4f16": "float16"
}
},
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"use_resampler": false,
"vocab_size": 49280
},
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.46.0",
"transformers.js_config": {
"kv_cache_dtype": {
"q4f16": "float16",
"fp16": "float16"
}
},
"use_cache": true,
"vision_config": {
"use_base_siglip": true,
"_attn_implementation_autoset": false,
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": 512,
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-06,
"length_penalty": 1.0,
"max_image_size": {
"longest_edge": 512
},
"max_length": 20,
"min_length": 0,
"model_type": "idefics3",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 3,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 16,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"size": {
"longest_edge": 2048
},
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false
},
"vocab_size": 49280
}