63 lines
2.1 KiB
Markdown
63 lines
2.1 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
tags: []
|
||
|
|
---
|
||
|
|
|
||
|
|
This repository contains the text-only LLM portion of `meta-llama/Llama-3.2-11B-Vision-Instruct`
|
||
|
|
|
||
|
|
**How it was done**
|
||
|
|
|
||
|
|
```python
|
||
|
|
from collections import OrderedDict
|
||
|
|
from transformers import MllamaForConditionalGeneration, AutoModelForCausalLM
|
||
|
|
from transformers.models.mllama.modeling_mllama import MllamaCrossAttentionDecoderLayer
|
||
|
|
llama32_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
|
||
|
|
llama32 = MllamaForConditionalGeneration.from_pretrained(
|
||
|
|
llama32_id,
|
||
|
|
torch_dtype=torch.bfloat16,
|
||
|
|
device_map="cuda:0",
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
new_layers = []
|
||
|
|
for idx, layer in enumerate(llama32.language_model.model.layers):
|
||
|
|
if isinstance(layer, MllamaCrossAttentionDecoderLayer):
|
||
|
|
# CrossAttention layers are only take effect when image is provided.
|
||
|
|
# Ignore here since we want text-only model
|
||
|
|
pass
|
||
|
|
else:
|
||
|
|
new_layers.append(layer)
|
||
|
|
llama32.language_model.model.cross_attention_layers = []
|
||
|
|
llama32.language_model.model.layers = torch.nn.ModuleList(new_layers)
|
||
|
|
|
||
|
|
|
||
|
|
# Now llama32.language_model is identical to Llama3.1-8B-Instruct, except the embedding size(+8)
|
||
|
|
# see: https://github.com/huggingface/transformers/blob/a22a4378d97d06b7a1d9abad6e0086d30fdea199/src/transformers/models/mllama/modeling_mllama.py#L1667C9-L1667C26
|
||
|
|
new_llama32_state_dict = OrderedDict()
|
||
|
|
for k, v in llama32.language_model.state_dict().items():
|
||
|
|
if k == "model.embed_tokens.weight":
|
||
|
|
v = v[:128256, :]
|
||
|
|
new_llama32_state_dict[k] = v
|
||
|
|
|
||
|
|
|
||
|
|
# Load a llama31 for the architecture
|
||
|
|
llama31_id = "meta-llama/Llama-3.1-8B-Instruct"
|
||
|
|
llama31 = AutoModelForCausalLM.from_pretrained(
|
||
|
|
llama31_id,
|
||
|
|
torch_dtype=torch.bfloat16,
|
||
|
|
device_map="cuda:1",
|
||
|
|
)
|
||
|
|
|
||
|
|
llama31.load_state_dict(new_llama32_state_dict)
|
||
|
|
# <All keys matched successfully>
|
||
|
|
|
||
|
|
llama31.save_pretrained("./my-cool-llama3.2")
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
**Note:**
|
||
|
|
|
||
|
|
In the original tokenizer, there are `date_string` in `tokenizer.chat_template` (which append the current date when calling `tokenizer.apply_chat_template(messages)`).
|
||
|
|
|
||
|
|
I removed this behavior in this repo. Please be aware when you use `AutoTokenizer.from_pretrained(this_repo)`.
|