Image-Text-to-Text
Safetensors
mpt
custom_code
Chitrarth / config.json
shaharukh-khan-ola's picture
Update config.json
05d2f60 verified
{
"_name_or_path": "krutrim",
"architectures": [
"ChitrarthForCausalLM"
],
"attn_config": {
"alibi": true,
"alibi_bias_max": 8,
"attn_impl": "flash",
"attn_pdrop": 0.0,
"attn_type": "grouped_query_attention",
"attn_uses_sequence_id": false,
"clip_qkv": 6,
"kv_n_heads": 8,
"prefix_lm": false,
"qk_gn": false,
"qk_ln": false,
"rope": false,
"rope_dail_config": {
"pos_idx_in_fp32": true,
"type": "original",
"xpos_scale_base": 512
},
"rope_hf_config": {
"factor": 1.0,
"type": "no_scaling"
},
"rope_impl": "dail",
"rope_theta": 10000,
"sliding_window_size": -1,
"softmax_scale": null
},
"auto_map": {
"AutoConfig": "configuration_mpt.MPTConfig",
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
},
"d_model": 4608,
"emb_pdrop": 0.0,
"embedding_fraction": 1.0,
"expansion_ratio": 4,
"fc_type": "torch",
"ffn_config": {
"fc_type": "torch",
"ffn_type": "mptmlp"
},
"freeze_mm_mlp_adapter": false,
"hidden_size": 4608,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"init_config": {
"emb_init_std": null,
"emb_init_uniform_lim": null,
"fan_mode": "fan_in",
"init_div_is_residual": true,
"init_gain": 0.0,
"init_nonlinearity": "relu",
"init_std": null,
"name": "kaiming_normal_"
},
"init_device": "cpu",
"learned_pos_emb": false,
"logit_scale": null,
"max_seq_len": 4096,
"mm_hidden_size": 1152,
"mm_projector_type": "mlp2x_gelu",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "google/siglip-so400m-patch14-384",
"model_type": "mpt",
"n_heads": 48,
"n_layers": 32,
"no_bias": true,
"norm_type": "low_precision_layernorm",
"resid_pdrop": 0.0,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"use_pad_tok_in_ffn": true,
"vocab_size": 70400
}