Lifting check_unitialized. (#325)

# What does this PR do?

Lifting check_unitialized.

<!--
Congratulations! You've made it this far! You're not quite done yet
though.

Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.

Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.

Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->

<!-- Remove if not applicable -->

Fixes # (issue)


## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
      Pull Request section?
- [ ] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/)? Please add a link
      to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
- [ ] Did you write any new necessary tests?


## Who can review?

Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.

<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @


@OlivierDehaene OR @Narsil

 -->

server/text_generation_server/models/bloom.py

@@ -238,15 +238,6 @@ class BLOOMSharded(BLOOM):
                     if name == "word_embeddings.weight":
                         model.lm_head._parameters["weight"] = tensor
 
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
     def forward(
         self, input_ids, attention_mask, position_ids, past_key_values: Optional = None
     ):

server/text_generation_server/models/flash_llama.py

@@ -139,15 +139,6 @@ class FlashLlama(FlashCausalLM):
 
                 del value
 
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
         torch.cuda.empty_cache()
         model.post_load_weights(quantize)
 
@@ -315,14 +306,5 @@ class FlashLlamaSharded(FlashLlama):
                     else:
                         module._buffers[param_name] = tensor
 
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
         torch.cuda.empty_cache()
         model.post_load_weights(quantize)

server/text_generation_server/models/flash_neox.py

@@ -152,13 +152,4 @@ class FlashNeoXSharded(FlashNeoX):
                     else:
                         module._buffers[param_name] = tensor
 
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
         model.post_load_weights(quantize)

server/text_generation_server/models/flash_santacoder.py

@@ -376,17 +376,6 @@ class FlashSantacoderSharded(FlashSantacoder):
                     else:
                         module._buffers[param_name] = tensor
 
-
         model.lm_head.weight = torch.nn.Parameter(model.transformer.wte.weight)
-
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
         torch.cuda.empty_cache()
         model.post_load_weights(quantize)

server/text_generation_server/models/galactica.py

@@ -365,15 +365,6 @@ class GalacticaSharded(Galactica):
                     if name == "model.decoder.embed_tokens.weight":
                         model.lm_head._parameters["weight"] = tensor
 
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
     def forward(
         self, input_ids, attention_mask, position_ids, past_key_values: Optional = None
     ):

server/text_generation_server/models/gpt_neox.py

@@ -215,15 +215,6 @@ class GPTNeoxSharded(CausalLM):
                     else:
                         module._buffers[param_name] = tensor
 
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
     def forward(
         self, input_ids, attention_mask, position_ids, past_key_values: Optional = None
     ):

server/text_generation_server/models/model.py

@@ -32,6 +32,7 @@ class Model(ABC):
         self.decode_buffer = decode_buffer
         self.rank = rank
         self.world_size = world_size
+        self.check_initialized()
 
     @property
     def info(self) -> InfoResponse:
@@ -99,3 +100,13 @@ class Model(ABC):
             return token_text, None, None
         else:
             return "", offset, token_offset
+
+    def check_initialized(self):
+        uninitialized_parameters = []
+        for n, p in self.model.named_parameters():
+            if p.data.device == torch.device("meta"):
+                uninitialized_parameters.append(n)
+        if uninitialized_parameters:
+            raise RuntimeError(
+                f"found uninitialized parameters in model {self.__class__.__name__}: {uninitialized_parameters}"
+            )

server/text_generation_server/models/opt.py

@@ -212,15 +212,6 @@ class OPTSharded(OPT):
                     if name == "model.decoder.embed_tokens.weight":
                         model.lm_head._parameters["weight"] = tensor
 
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
     def forward(
         self, input_ids, attention_mask, position_ids, past_key_values: Optional = None
     ):

server/text_generation_server/models/t5.py

@@ -222,15 +222,6 @@ class T5Sharded(Seq2SeqLM):
                     else:
                         module._buffers[param_name] = tensor
 
-        uninitialized_parameters = []
-        for n, p in model.named_parameters():
-            if p.data.device == torch.device("meta"):
-                uninitialized_parameters.append(n)
-        if uninitialized_parameters:
-            raise RuntimeError(
-                f"found uninitialized parameters in model: {uninitialized_parameters}"
-            )
-
     def forward(
         self,
         input_ids,