tiny-random-vllama-clip

{ "additional_vocab_size": 2, "alpha_initializer": "ones", "alpha_type": "vector", "alphas_initializer_range": 0.0, "architectures": [ "VLlamaForCausalLM" ], "bos_token_id": 1, "cross_layer_activation_function": "swiglu", "cross_layer_interval": 1, "dropout": 0.0, "eos_token_id": 2, "ffn_dim": 64, "freeze_lm_head": false, "freeze_text_layers": true, "freeze_text_module_exceptions": [], "freeze_vision_layers": true, "freeze_vision_module_exceptions": [], "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 11008, "max_new_tokens": 100, "max_position_embeddings": 128, "model_type": "vllama", "num_attention_heads": 4, "num_hidden_layers": 2, "pad_token_id": 0, "qk_layer_norms": false, "qk_layer_norms_perceiver": false, "resampler_depth": 2, "resampler_head_dim": 8, "resampler_n_heads": 2, "resampler_n_latents": 16, "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.27.0.dev0", "use_cache": true, "use_resampler": true, "vision_embed_dim": 32, "vision_image_size": 30, "vision_model_name": "hf-internal-testing/tiny-random-clip", "vision_model_params": "{}", "vocab_size": 32000, "word_embed_proj_dim": 16 }