Comments (6)
Hi @DifferentComputers, sorry that I just saw this comment. It is not a normal behavior of an empty model list. You need to start the gradio demo after the worker is fully loaded, so as to get the model list. Please let me know if you have further concerns.
from llava.
This seems to be an error in the backend.
- can you see the model list on the top left?
- There may be an error in the model worker, can you paste the error message here?
from llava.
I get the same error but I suspect it's because I may be running it on entirely inadequate hardware. Alternately, I may not have the model data installed correctly.
I don't see any model worker error. that would be appearing on the command line process, correct?
I don't see any "model list", at least not on the webpage where the "NETWORK ERROR" appears as every response to an attempt to use the chatBot.
from llava.
I met the same problem "NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.", but my model list is not empty, there is a model I have applied the delta before, but still the error, some details are as follow:
thank you!
from llava.
@corleytd Hi please see my response in #89, thanks.
from llava.
I have the folowing problem; actually I want load model from my pc
(llava) C:\Users\aymen\LLaVA>python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path C:/Users/aymen/llava-1.5-7b-hf
2024-03-04 12:43:53 | INFO | model_worker | args: Namespace(host='0.0.0.0', port=40000, worker_address='http://localhost:40000', controller_address='http://localhost:10000', model_path='C:/Users/aymen/llava-1.5-7b-hf', model_base=None, model_name=None, device='cuda', multi_modal=False, limit_model_concurrency=5, stream_interval=1, no_register=False, load_8bit=False, load_4bit=False, use_flash_attn=False)
2024-03-04 12:43:53 | INFO | model_worker | Loading the model llava-1.5-7b-hf on worker 62e548 ...
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
You are using a model of type llava to instantiate a model of type llava_llama. This is not supported for all configurations of models and can yield errors.
2024-03-04 12:43:53 | INFO | accelerate.utils.modeling | We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set max_memory
in to a higher value to use more memory (at your own risk).
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 33%|█████████████████████████████████████████████████▎ | 1/3 [00:00<00:00, 5.88it/s]
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 8.46it/s]
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 8.10it/s]
2024-03-04 12:54:33 | ERROR | stderr |
Some weights of LlavaLlamaForCausalLM were not initialized from the model checkpoint at C:/Users/aymen/llava-1.5-7b-hf and are newly initialized: ['layers.8.self_attn.o_proj.weight', 'layers.3.self_attn.o_proj.weight', 'layers.22.mlp.down_proj.weight', 'layers.29.mlp.gate_proj.weight', 'layers.1.self_attn.k_proj.weight', 'layers.0.mlp.up_proj.weight', 'layers.18.mlp.up_proj.weight', 'layers.19.mlp.down_proj.weight', 'layers.19.mlp.up_proj.weight', 'layers.22.mlp.gate_proj.weight', 'layers.27.self_attn.v_proj.weight', 'layers.18.mlp.gate_proj.weight', 'layers.8.mlp.down_proj.weight', 'layers.2.mlp.gate_proj.weight', 'layers.26.mlp.up_proj.weight', 'layers.0.self_attn.k_proj.weight', 'layers.17.self_attn.k_proj.weight', 'layers.20.mlp.up_proj.weight', 'layers.29.mlp.up_proj.weight', 'layers.23.self_attn.q_proj.weight', 'layers.19.self_attn.k_proj.weight', 'layers.20.post_attention_layernorm.weight', 'layers.24.mlp.up_proj.weight', 'layers.0.self_attn.o_proj.weight', 'layers.5.mlp.gate_proj.weight', 'layers.21.input_layernorm.weight', 'layers.12.input_layernorm.weight', 'layers.16.input_layernorm.weight', 'layers.31.self_attn.k_proj.weight', 'layers.19.self_attn.o_proj.weight', 'layers.9.self_attn.k_proj.weight', 'layers.2.post_attention_layernorm.weight', 'layers.15.self_attn.v_proj.weight', 'layers.20.mlp.down_proj.weight', 'layers.28.self_attn.k_proj.weight', 'layers.16.self_attn.q_proj.weight', 'layers.12.self_attn.k_proj.weight', 'layers.29.self_attn.q_proj.weight', 'layers.24.self_attn.k_proj.weight', 'layers.13.self_attn.q_proj.weight', 'layers.30.self_attn.k_proj.weight', 'layers.20.self_attn.o_proj.weight', 'layers.11.self_attn.v_proj.weight', 'layers.28.self_attn.v_proj.weight', 'layers.17.mlp.up_proj.weight', 'layers.24.self_attn.v_proj.weight', 'layers.1.self_attn.q_proj.weight', 'layers.6.mlp.down_proj.weight', 'layers.27.post_attention_layernorm.weight', 'layers.30.mlp.gate_proj.weight', 'layers.18.self_attn.o_proj.weight', 'layers.28.self_attn.q_proj.weight', 'layers.0.self_attn.v_proj.weight', 'layers.12.mlp.gate_proj.weight', 'layers.9.self_attn.q_proj.weight', 'layers.4.self_attn.q_proj.weight', 'layers.6.self_attn.o_proj.weight', 'layers.2.self_attn.v_proj.weight', 'layers.21.mlp.down_proj.weight', 'layers.31.self_attn.q_proj.weight', 'layers.14.self_attn.v_proj.weight', 'layers.11.mlp.up_proj.weight', 'layers.24.post_attention_layernorm.weight', 'layers.22.self_attn.k_proj.weight', 'layers.11.self_attn.k_proj.weight', 'layers.19.self_attn.q_proj.weight', 'layers.10.mlp.up_proj.weight', 'layers.22.mlp.up_proj.weight', 'layers.1.mlp.gate_proj.weight', 'layers.2.mlp.down_proj.weight', 'layers.24.input_layernorm.weight', 'layers.25.post_attention_layernorm.weight', 'layers.9.post_attention_layernorm.weight', 'layers.22.input_layernorm.weight', 'layers.3.self_attn.v_proj.weight', 'layers.5.self_attn.k_proj.weight', 'layers.12.self_attn.o_proj.weight', 'layers.15.self_attn.o_proj.weight', 'layers.12.self_attn.v_proj.weight', 'layers.24.self_attn.o_proj.weight', 'layers.23.self_attn.v_proj.weight', 'layers.28.mlp.gate_proj.weight', 'layers.14.self_attn.o_proj.weight', 'layers.10.self_attn.q_proj.weight', 'layers.11.mlp.down_proj.weight', 'layers.16.self_attn.k_proj.weight', 'layers.5.self_attn.o_proj.weight', 'layers.13.mlp.gate_proj.weight', 'layers.10.self_attn.v_proj.weight', 'layers.1.post_attention_layernorm.weight', 'layers.12.mlp.down_proj.weight', 'layers.13.self_attn.o_proj.weight', 'layers.8.mlp.up_proj.weight', 'layers.22.self_attn.v_proj.weight', 'layers.9.input_layernorm.weight', 'layers.25.self_attn.v_proj.weight', 'layers.23.input_layernorm.weight', 'layers.6.mlp.up_proj.weight', 'layers.7.mlp.up_proj.weight', 'layers.16.mlp.gate_proj.weight', 'layers.25.self_attn.k_proj.weight', 'layers.16.self_attn.o_proj.weight', 'layers.16.mlp.down_proj.weight', 'layers.9.mlp.up_proj.weight', 'layers.21.post_attention_layernorm.weight', 'layers.13.post_attention_layernorm.weight', 'layers.23.mlp.up_proj.weight', 'layers.30.self_attn.q_proj.weight', 'layers.30.self_attn.v_proj.weight', 'layers.1.self_attn.o_proj.weight', 'layers.11.self_attn.q_proj.weight', 'layers.6.self_attn.q_proj.weight', 'layers.7.self_attn.o_proj.weight', 'layers.20.input_layernorm.weight', 'layers.31.self_attn.v_proj.weight', 'layers.4.self_attn.o_proj.weight', 'layers.21.self_attn.q_proj.weight', 'layers.21.self_attn.k_proj.weight', 'layers.14.mlp.gate_proj.weight', 'layers.15.mlp.up_proj.weight', 'layers.15.mlp.down_proj.weight', 'layers.24.mlp.gate_proj.weight', 'layers.4.self_attn.k_proj.weight', 'layers.8.post_attention_layernorm.weight', 'layers.23.mlp.down_proj.weight', 'layers.8.input_layernorm.weight', 'layers.25.self_attn.o_proj.weight', 'layers.12.mlp.up_proj.weight', 'layers.25.mlp.gate_proj.weight', 'layers.29.mlp.down_proj.weight', 'layers.7.mlp.down_proj.weight', 'layers.1.input_layernorm.weight', 'layers.23.self_attn.k_proj.weight', 'layers.30.mlp.up_proj.weight', 'layers.22.post_attention_layernorm.weight', 'layers.26.self_attn.v_proj.weight', 'layers.3.input_layernorm.weight', 'layers.13.mlp.up_proj.weight', 'layers.18.mlp.down_proj.weight', 'layers.13.input_layernorm.weight', 'layers.16.mlp.up_proj.weight', 'layers.26.self_attn.o_proj.weight', 'layers.20.self_attn.q_proj.weight', 'layers.3.self_attn.q_proj.weight', 'layers.15.input_layernorm.weight', 'layers.0.mlp.down_proj.weight', 'layers.15.mlp.gate_proj.weight', 'layers.11.self_attn.o_proj.weight', 'layers.2.self_attn.q_proj.weight', 'layers.29.input_layernorm.weight', 'layers.9.self_attn.o_proj.weight', 'layers.24.self_attn.q_proj.weight', 'layers.5.self_attn.q_proj.weight', 'layers.19.input_layernorm.weight', 'layers.14.input_layernorm.weight', 'layers.3.self_attn.k_proj.weight', 'layers.23.self_attn.o_proj.weight', 'layers.17.mlp.gate_proj.weight', 'layers.31.post_attention_layernorm.weight', 'layers.3.mlp.up_proj.weight', 'layers.19.self_attn.v_proj.weight', 'layers.27.self_attn.q_proj.weight', 'layers.19.post_attention_layernorm.weight', 'layers.2.self_attn.o_proj.weight', 'layers.5.input_layernorm.weight', 'layers.14.post_attention_layernorm.weight', 'layers.6.mlp.gate_proj.weight', 'layers.2.input_layernorm.weight', 'layers.2.self_attn.k_proj.weight', 'layers.7.mlp.gate_proj.weight', 'layers.27.mlp.gate_proj.weight', 'layers.9.self_attn.v_proj.weight', 'layers.28.self_attn.o_proj.weight', 'layers.17.self_attn.v_proj.weight', 'layers.31.input_layernorm.weight', 'layers.24.mlp.down_proj.weight', 'layers.5.mlp.up_proj.weight', 'layers.3.mlp.down_proj.weight', 'layers.18.post_attention_layernorm.weight', 'lm_head.weight', 'layers.7.self_attn.v_proj.weight', 'layers.14.self_attn.k_proj.weight', 'layers.10.mlp.down_proj.weight', 'layers.28.post_attention_layernorm.weight', 'layers.8.self_attn.v_proj.weight', 'layers.4.post_attention_layernorm.weight', 'layers.8.self_attn.q_proj.weight', 'layers.27.input_layernorm.weight', 'layers.2.mlp.up_proj.weight', 'layers.29.self_attn.o_proj.weight', 'layers.4.mlp.gate_proj.weight', 'layers.29.post_attention_layernorm.weight', 'layers.31.mlp.gate_proj.weight', 'layers.26.post_attention_layernorm.weight', 'layers.26.input_layernorm.weight', 'layers.8.mlp.gate_proj.weight', 'layers.7.input_layernorm.weight', 'layers.9.mlp.down_proj.weight', 'layers.0.self_attn.q_proj.weight', 'layers.17.mlp.down_proj.weight', 'layers.5.self_attn.v_proj.weight', 'layers.11.post_attention_layernorm.weight', 'layers.17.self_attn.q_proj.weight', 'layers.13.self_attn.v_proj.weight', 'layers.21.mlp.gate_proj.weight', 'layers.27.mlp.up_proj.weight', 'layers.10.self_attn.k_proj.weight', 'layers.5.mlp.down_proj.weight', 'layers.27.mlp.down_proj.weight', 'layers.7.self_attn.k_proj.weight', 'layers.30.post_attention_layernorm.weight', 'layers.7.post_attention_layernorm.weight', 'layers.6.self_attn.v_proj.weight', 'layers.11.input_layernorm.weight', 'layers.17.post_attention_layernorm.weight', 'layers.29.self_attn.v_proj.weight', 'layers.12.post_attention_layernorm.weight', 'layers.6.self_attn.k_proj.weight', 'layers.26.self_attn.k_proj.weight', 'layers.1.mlp.down_proj.weight', 'layers.1.mlp.up_proj.weight', 'layers.3.post_attention_layernorm.weight', 'layers.18.input_layernorm.weight', 'layers.19.mlp.gate_proj.weight', 'layers.6.input_layernorm.weight', 'layers.29.self_attn.k_proj.weight', 'layers.1.self_attn.v_proj.weight', 'layers.23.mlp.gate_proj.weight', 'layers.22.self_attn.q_proj.weight', 'layers.21.self_attn.o_proj.weight', 'layers.25.mlp.down_proj.weight', 'layers.5.post_attention_layernorm.weight', 'layers.22.self_attn.o_proj.weight', 'layers.15.self_attn.k_proj.weight', 'layers.18.self_attn.v_proj.weight', 'layers.0.input_layernorm.weight', 'layers.15.post_attention_layernorm.weight', 'layers.31.self_attn.o_proj.weight', 'layers.30.self_attn.o_proj.weight', 'layers.14.mlp.up_proj.weight', 'layers.4.mlp.up_proj.weight', 'layers.20.self_attn.k_proj.weight', 'layers.9.mlp.gate_proj.weight', 'layers.31.mlp.down_proj.weight', 'layers.0.mlp.gate_proj.weight', 'layers.16.self_attn.v_proj.weight', 'layers.16.post_attention_layernorm.weight', 'layers.27.self_attn.k_proj.weight', 'layers.30.mlp.down_proj.weight', 'layers.20.mlp.gate_proj.weight', 'layers.14.mlp.down_proj.weight', 'layers.3.mlp.gate_proj.weight', 'layers.6.post_attention_layernorm.weight', 'layers.13.mlp.down_proj.weight', 'layers.25.mlp.up_proj.weight', 'layers.12.self_attn.q_proj.weight', 'layers.17.self_attn.o_proj.weight', 'layers.26.self_attn.q_proj.weight', 'layers.30.input_layernorm.weight', 'layers.0.post_attention_layernorm.weight', 'layers.14.self_attn.q_proj.weight', 'layers.31.mlp.up_proj.weight', 'embed_tokens.weight', 'layers.23.post_attention_layernorm.weight', 'layers.7.self_attn.q_proj.weight', 'layers.21.self_attn.v_proj.weight', 'layers.17.input_layernorm.weight', 'layers.10.self_attn.o_proj.weight', 'layers.26.mlp.down_proj.weight', 'layers.11.mlp.gate_proj.weight', 'layers.13.self_attn.k_proj.weight', 'layers.26.mlp.gate_proj.weight', 'layers.4.mlp.down_proj.weight', 'layers.4.self_attn.v_proj.weight', 'layers.18.self_attn.q_proj.weight', 'layers.21.mlp.up_proj.weight', 'layers.28.mlp.up_proj.weight', 'norm.weight', 'layers.10.mlp.gate_proj.weight', 'layers.8.self_attn.k_proj.weight', 'layers.15.self_attn.q_proj.weight', 'layers.10.post_attention_layernorm.weight', 'layers.25.self_attn.q_proj.weight', 'layers.25.input_layernorm.weight', 'layers.27.self_attn.o_proj.weight', 'layers.10.input_layernorm.weight', 'layers.28.input_layernorm.weight', 'layers.28.mlp.down_proj.weight', 'layers.4.input_layernorm.weight', 'layers.20.self_attn.v_proj.weight', 'layers.18.self_attn.k_proj.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
2024-03-04 12:54:35 | WARNING | root | Some parameters are on the meta device device because they were offloaded to the cpu.
2024-03-04 12:54:35 | ERROR | stderr | Traceback (most recent call last):
2024-03-04 12:54:35 | ERROR | stderr | File "C:\ProgramData\anaconda3\envs\llava\lib\runpy.py", line 196, in _run_module_as_main
2024-03-04 12:54:35 | ERROR | stderr | return _run_code(code, main_globals, None,
2024-03-04 12:54:35 | ERROR | stderr | File "C:\ProgramData\anaconda3\envs\llava\lib\runpy.py", line 86, in _run_code
2024-03-04 12:54:35 | ERROR | stderr | exec(code, run_globals)
2024-03-04 12:54:35 | ERROR | stderr | File "C:\Users\aymen\LLaVA\llava\serve\model_worker.py", line 277, in
2024-03-04 12:54:35 | ERROR | stderr | worker = ModelWorker(args.controller_address,
2024-03-04 12:54:35 | ERROR | stderr | File "C:\Users\aymen\LLaVA\llava\serve\model_worker.py", line 65, in init
2024-03-04 12:54:35 | ERROR | stderr | self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model(
2024-03-04 12:54:35 | ERROR | stderr | File "C:\Users\aymen\LLaVA\llava\model\builder.py", line 156, in load_pretrained_model
2024-03-04 12:54:35 | ERROR | stderr | if not vision_tower.is_loaded:
2024-03-04 12:54:35 | ERROR | stderr | AttributeError: 'NoneType' object has no attribute '
from llava.
Related Issues (20)
- [Usage] Deepspeed Zero Stage 3 not able to shard the model
- [Usage] Extremely Slow Inference Speed
- [ERROR]: RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'
- [Question] How to extract embeddings from llava?
- [Usage] Must I reload the model when I want to inference on a new image?
- 同样的需求,可以分享下思路吗?
- [Question] pretrain_mm_mlp_adapter of llava v1.6 7B not found HOT 1
- [Usage] errors when restore checkpoint using lora finetuning HOT 5
- [Question] Why I got nothing when I tested my lora finetune model HOT 1
- [Question] confusion on finetuning HOT 1
- Issue about pretraining[return code = -8 ], anyone can help me?
- [Usage] Continue training from pre-trained checkpoint
- [Question] The results of the local model are inconsistent with the web ui in the demo HOT 2
- Is this a bug ?
- [Question] Minimum Memory for Fine Tune LLaVA 1.5 7B without LoRA
- [Question] About TextVQA evaluation
- [Question] LLaVA-Next (Stronger) checkpoint 404 error HOT 1
- [Usage] How to run inference for llava-next-72b? HOT 8
- [Usage] About finetuning llama 2 with liuhaotian/llava-pretrain-llama-2-7b-chat HOT 2
- Training LLaVA MPT from scratch. Few Questions
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llava.