Views
No views yet
mistralai/Mistral-7B-Instruct-v0.1 finetuned for multimodal applications.<imagebind> in text and provide imagebinds, encoded as 4 tokens){'id': '000000334872', 'imagebinds': ['/data/llava_finetune_data/images/coco/train2017/train2017/000000334872.jpg'], 'messages': [{'content': '<imagebind>\nAre the people in the audio skiing downhill or cross-country skiing?', 'role': 'user'}, {'content': 'The people in the audio are cross-country skiing in the woods, as they are skiing on a trail rather than a steep slope.', 'role': 'assistant'}, {'content': 'How many people are in the audio?', 'role': 'user'}, {'content': 'There are two people in the audio, both on skis in the snow.', 'role': 'assistant'}, {'content': 'What kind of environment are they skiing in?', 'role': 'user'}, {'content': 'They are skiing in a wooded environment, following a trail through the trees while surrounded by snow.', 'role': 'assistant'}, {'content': 'Do the skiers have any additional gear with them besides their skis and poles?', 'role': 'user'}, {'content': 'Yes, the two male skiers are carrying backpacks while they ski through the woods. The backpacks might contain essentials for their skiing adventure, such as food, water, extra clothing, or safety equipment.', 'role': 'assistant'}]}name, pci.bus_id, vbios_version
NVIDIA GeForce RTX 4090, 00000000:03:00.0, 95.02.3C.00.8CMistralLMMForCausalLM.model =
PeftModelForCausalLM(
(base_model): LoraModel(
(model): MistralLMMForCausalLM(
(model): MistralLMMModel(
(embed_tokens): Embedding(32000, 4096)
(layers): ModuleList(
(0-31): 32 x MistralDecoderLayer(
(self_attn): MistralAttention(
(q_proj): Linear(
in_features=4096, out_features=4096, bias=False
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(k_proj): Linear(
in_features=4096, out_features=1024, bias=False
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=1024, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(v_proj): Linear(
in_features=4096, out_features=1024, bias=False
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=1024, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(o_proj): Linear(
in_features=4096, out_features=4096, bias=False
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(rotary_emb): MistralRotaryEmbedding()
)
(mlp): MistralMLP(
(gate_proj): Linear(
in_features=4096, out_features=14336, bias=False
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=14336, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(up_proj): Linear(
in_features=4096, out_features=14336, bias=False
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=14336, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(down_proj): Linear(
in_features=14336, out_features=4096, bias=False
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=14336, out_features=64, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=64, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
(act_fn): SiLUActivation()
)
(input_layernorm): MistralRMSNorm()
(post_attention_layernorm): MistralRMSNorm()
)
)
(norm): MistralRMSNorm()
(imagebind_lmm_projector): _MLPVectorProjector(
(mlps): ModuleList(
(0-3): 4 x Sequential(
(0): Linear(in_features=1024, out_features=4096, bias=True)
(1): GELU(approximate='none')
(2): Linear(in_features=4096, out_features=4096, bias=True)
)
)
)
)
(lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
)
)