File size: 1,583 Bytes
154c305 36acf33 154c305 90e82e3 b987274 90e82e3 b987274 90e82e3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
---
library_name: transformers
license: llama3.2
base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
---
# creation
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from datasets import load_dataset
from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
model_id = "huihui-ai/Llama-3.2-3B-Instruct-abliterated"
model_out = "Llama-3.2-3B-Instruct-abliterated.w8a8"
num_samples = 64
max_seq_len = 4096
tokenizer = AutoTokenizer.from_pretrained(model_id)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.shuffle().select(range(num_samples))
ds = ds.map(preprocess_fn)
recipe = [
SmoothQuantModifier(
smoothing_strength=0.7,
mappings=[
[["re:.*q_proj", "re:.*k_proj", "re:.*v_proj"], "re:.*input_layernorm"],
[["re:.*gate_proj", "re:.*up_proj"], "re:.*post_attention_layernorm"],
[["re:.*down_proj"], "re:.*up_proj"],
],
),
GPTQModifier(
sequential=True,
targets="Linear",
scheme="W8A8",
ignore=["lm_head"],
dampening_frac=0.01,
)
]
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
torch_dtype="bfloat16",
)
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
model.save_pretrained(model_out)
```
|