nvidia/NV-Embed-v1 #239
Labels
new model
Make a model compatible
Comments
|
What’s the error message? |
|
This is the error message. + infinity_emb --model-name-or-path /mnt/cache/zhangxingyan/hub/model/nvidia/NV-Embed-v1 --port 20052 --trust-remote-code
INFO: Started server process [8]
INFO: Waiting for application startup.
INFO 2024-05-31 13:07:47,181 infinity_emb INFO: select_model.py:54
model=`/mnt/cache/zhangxingyan/hub/model/nvidia/NV-E
mbed-v1` selected, using engine=`torch` and
device=`None`
INFO 2024-05-31 13:07:47,193 SentenceTransformer.py:107
sentence_transformers.SentenceTransformer
INFO: Load pretrained SentenceTransformer:
/mnt/cache/zhangxingyan/hub/model/nvidia/NV-
Embed-v1
WARNING 2024-05-31 13:07:47,195 SentenceTransformer.py:1129
sentence_transformers.SentenceTransformer
WARNING: No sentence-transformers model
found with name
/mnt/cache/zhangxingyan/hub/model/nvidia/NV
-Embed-v1. Creating a new one with MEAN
pooling.
ERROR: Traceback (most recent call last):
File "/app/.venv/lib/python3.10/site-packages/starlette/routing.py", line 677, in lifespan
async with self.lifespan_context(app) as maybe_state:
File "/usr/lib/python3.10/contextlib.py", line 199, in __aenter__
return await anext(self.gen)
File "/app/infinity_emb/infinity_server.py", line 46, in lifespan
app.model = AsyncEmbeddingEngine.from_args(engine_args) # type: ignore
File "/app/infinity_emb/engine.py", line 49, in from_args
engine = cls(**asdict(engine_args), _show_deprecation_warning=False)
File "/app/infinity_emb/engine.py", line 40, in __init__
self._model, self._min_inference_t, self._max_inference_t = select_model(
File "/app/infinity_emb/inference/select_model.py", line 62, in select_model
loaded_engine = unloaded_engine.value(engine_args=engine_args)
File "/app/infinity_emb/transformer/embedder/sentence_transformer.py", line 47, in __init__
super().__init__(
File "/app/.venv/lib/python3.10/site-packages/sentence_transformers/SentenceTransformer.py", line 199, in __init__
modules = self._load_auto_model(
File "/app/.venv/lib/python3.10/site-packages/sentence_transformers/SentenceTransformer.py", line 1134, in _load_auto_model
transformer_model = Transformer(
File "/app/.venv/lib/python3.10/site-packages/sentence_transformers/models/Transformer.py", line 36, in __init__
self._load_model(model_name_or_path, config, cache_dir, **model_args)
File "/app/.venv/lib/python3.10/site-packages/sentence_transformers/models/Transformer.py", line 65, in _load_model
self.auto_model = AutoModel.from_pretrained(
File "/app/.venv/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 550, in from_pretrained
model_class = get_class_from_dynamic_module(
File "/app/.venv/lib/python3.10/site-packages/transformers/dynamic_module_utils.py", line 489, in get_class_from_dynamic_module
final_module = get_cached_module_file(
File "/app/.venv/lib/python3.10/site-packages/transformers/dynamic_module_utils.py", line 315, in get_cached_module_file
modules_needed = check_imports(resolved_module_file)
File "/app/.venv/lib/python3.10/site-packages/transformers/dynamic_module_utils.py", line 180, in check_imports
raise ImportError(
ImportError: This modeling file requires the following packages that were not found in your environment: einops. Run `pip install einops`
ERROR: Application startup failed. Exiting.This is because the model configuration is different from other models. The model configuration is located in the "text_config". {
"add_eos": true,
"add_pad_token": true,
"architectures": [
"NVEmbedModel"
],
"auto_map": {
"AutoConfig": "configuration_nvembed.NVEmbedConfig",
"AutoModel": "modeling_nvembed.NVEmbedModel"
},
"is_mask_instruction": true,
"latent_attention_config": {
"model_type": "latent_attention"
},
"mask_type": "b",
"model_type": "nvembed",
"padding_side": "right",
"text_config": {
"_name_or_path": "nvidia/NV-Embed-v1",
"add_cross_attention": false,
"architectures": [
"MistralModel"
],
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 1,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "silu",
"hidden_size": 4096,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 14336,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 32768,
"min_length": 0,
"model_type": "bidir_mistral",
"no_repeat_ngram_size": 0,
"num_attention_heads": 32,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sep_token_id": null,
"sliding_window": 4096,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 32000
},
"torch_dtype": "float16",
"transformers_version": "4.37.2"
} |
|
Can you please install |
|
Sorry, I pasted the wrong log. This is the correct one. Thanks for your work. I also think that NVIDIA/NV-Emberd-v1 should consider changing their model. |
|
I assume fixed now .closing |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Model description
https://huggingface.co/nvidia/NV-Embed-v1
NV-Embed-v1 ranks first on the MTEB. However, it cannot be loaded using the SentenceTransformer library.
Open source status
Provide useful links for the implementation
https://huggingface.co/nvidia/NV-Embed-v1
The text was updated successfully, but these errors were encountered: