metadata
license: apache-2.0
library_name: peft
tags:
- finetuned
- multimodal
- llava
base_model: mistralai/Mistral-7B-Instruct-v0.1
dataset: sshh12/llava-gpt-multi-image-and-llava-finetune-merged
inference: false
pipeline_tag: image-text-to-text
These are weights for a version of mistralai/Mistral-7B-Instruct-v0.1 finetuned for multimodal applications.
Modalities
- CLIPVisionModality (use
<image>in text and provideimages, encoded as 10 tokens)
Usage
GitHub: https://github.com/sshh12/multi_token (includes training scripts and basic inference server)
Dataset
sshh12/llava-gpt-multi-image-and-llava-finetune-merged (744610 examples)
{'images': ['/data/llava_finetune_data/images/coco/train2017/train2017/000000499538.jpg'], 'messages': [{'content': '<image>\nWhat is the name of the book?\nAnswer the question using a single word or phrase.', 'role': 'user'}, {'content': 'World changing', 'role': 'assistant'}, {'content': 'What color is the bird?', 'role': 'user'}, {'content': 'Red', 'role': 'assistant'}, {'content': 'What type of bird is this?', 'role': 'user'}, {'content': 'Robin', 'role': 'assistant'}], 'id': '000000499538'}
Training Device(s)
name, pci.bus_id, vbios_version
NVIDIA RTX A6000, 00000000:02:00.0, 94.02.5C.00.02
Model
MistralLMMForCausalLM.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): lora.Linear(
(base_layer): 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): lora.Linear(
(base_layer): 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): lora.Linear(
(base_layer): 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): lora.Linear(
(base_layer): 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): lora.Linear(
(base_layer): 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): lora.Linear(
(base_layer): 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): lora.Linear(
(base_layer): 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()
(vision_clip_lmm_projector): _MLPVectorProjector(
(mlps): ModuleList(
(0-9): 10 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)
)
)
)
Framework versions
- PEFT 0.7.0