初始化项目，由ModelHub XC社区提供模型
Model: pa5haw/Phi-4-mini-instruct-mlx-fp16 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
67
README.md
Normal file
67
README.md
Normal file
@@ -0,0 +1,67 @@
|
||||
---
|
||||
language:
|
||||
- multilingual
|
||||
- ar
|
||||
- zh
|
||||
- cs
|
||||
- da
|
||||
- nl
|
||||
- en
|
||||
- fi
|
||||
- fr
|
||||
- de
|
||||
- he
|
||||
- hu
|
||||
- it
|
||||
- ja
|
||||
- ko
|
||||
- 'no'
|
||||
- pl
|
||||
- pt
|
||||
- ru
|
||||
- es
|
||||
- sv
|
||||
- th
|
||||
- tr
|
||||
- uk
|
||||
library_name: transformers
|
||||
license: mit
|
||||
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/LICENSE
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- nlp
|
||||
- code
|
||||
- mlx
|
||||
- mlx-my-repo
|
||||
widget:
|
||||
- messages:
|
||||
- role: user
|
||||
content: Can you provide ways to eat combinations of bananas and dragonfruits?
|
||||
base_model: microsoft/Phi-4-mini-instruct
|
||||
---
|
||||
|
||||
# pa5haw/Phi-4-mini-instruct-mlx-fp16
|
||||
|
||||
The Model [pa5haw/Phi-4-mini-instruct-mlx-fp16](https://huggingface.co/pa5haw/Phi-4-mini-instruct-mlx-fp16) was converted to MLX format from [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) using mlx-lm version **0.31.2**.
|
||||
|
||||
## Use with mlx
|
||||
|
||||
```bash
|
||||
pip install mlx-lm
|
||||
```
|
||||
|
||||
```python
|
||||
from mlx_lm import load, generate
|
||||
|
||||
model, tokenizer = load("pa5haw/Phi-4-mini-instruct-mlx-fp16")
|
||||
|
||||
prompt="hello"
|
||||
|
||||
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
|
||||
messages = [{"role": "user", "content": prompt}]
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages, tokenize=False, add_generation_prompt=True
|
||||
)
|
||||
|
||||
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||||
```
|
||||
1
chat_template.jinja
Normal file
1
chat_template.jinja
Normal file
@@ -0,0 +1 @@
|
||||
{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
|
||||
146
config.json
Normal file
146
config.json
Normal file
@@ -0,0 +1,146 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Phi3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_phi3.Phi3Config",
|
||||
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
|
||||
"AutoTokenizer": "Xenova/gpt-4o"
|
||||
},
|
||||
"bos_token_id": 199999,
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": [
|
||||
200020,
|
||||
199999
|
||||
],
|
||||
"full_attn_mod": 1,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"interpolate_factor": 1,
|
||||
"lm_head_bias": false,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "phi3",
|
||||
"num_attention_heads": 24,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"original_max_position_embeddings": 4096,
|
||||
"pad_token_id": 199999,
|
||||
"partial_rotary_factor": 0.75,
|
||||
"resid_pdrop": 0.0,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"long_factor": [
|
||||
1,
|
||||
1.118320672,
|
||||
1.250641126,
|
||||
1.398617824,
|
||||
1.564103225,
|
||||
1.74916897,
|
||||
1.956131817,
|
||||
2.187582649,
|
||||
2.446418898,
|
||||
2.735880826,
|
||||
3.059592084,
|
||||
3.421605075,
|
||||
3.826451687,
|
||||
4.279200023,
|
||||
4.785517845,
|
||||
5.351743533,
|
||||
5.984965424,
|
||||
6.693110555,
|
||||
7.485043894,
|
||||
8.370679318,
|
||||
9.36110372,
|
||||
10.4687158,
|
||||
11.70738129,
|
||||
13.09260651,
|
||||
14.64173252,
|
||||
16.37415215,
|
||||
18.31155283,
|
||||
20.47818807,
|
||||
22.90118105,
|
||||
25.61086418,
|
||||
28.64115884,
|
||||
32.03,
|
||||
32.1,
|
||||
32.13,
|
||||
32.23,
|
||||
32.6,
|
||||
32.61,
|
||||
32.64,
|
||||
32.66,
|
||||
32.7,
|
||||
32.71,
|
||||
32.93,
|
||||
32.97,
|
||||
33.28,
|
||||
33.49,
|
||||
33.5,
|
||||
44.16,
|
||||
47.77
|
||||
],
|
||||
"short_factor": [
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0,
|
||||
1.0
|
||||
],
|
||||
"type": "longrope"
|
||||
},
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 262144,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 200064
|
||||
}
|
||||
226
configuration_phi3.py
Normal file
226
configuration_phi3.py
Normal file
@@ -0,0 +1,226 @@
|
||||
# coding=utf-8
|
||||
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
"""Phi-3 model configuration"""
|
||||
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.utils import logging
|
||||
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class Phi3Config(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
||||
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
||||
defaults will yield a similar configuration to that of the
|
||||
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
||||
|
||||
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
||||
documentation from [`PretrainedConfig`] for more information.
|
||||
|
||||
Args:
|
||||
vocab_size (`int`, *optional*, defaults to 32064):
|
||||
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
||||
`inputs_ids` passed when calling [`Phi3Model`].
|
||||
hidden_size (`int`, *optional*, defaults to 3072):
|
||||
Dimension of the hidden representations.
|
||||
intermediate_size (`int`, *optional*, defaults to 8192):
|
||||
Dimension of the MLP representations.
|
||||
num_hidden_layers (`int`, *optional*, defaults to 32):
|
||||
Number of hidden layers in the Transformer decoder.
|
||||
num_attention_heads (`int`, *optional*, defaults to 32):
|
||||
Number of attention heads for each attention layer in the Transformer decoder.
|
||||
num_key_value_heads (`int`, *optional*):
|
||||
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
||||
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
||||
`num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
||||
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
||||
by meanpooling all the original heads within that group. For more details checkout [this
|
||||
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
||||
`num_attention_heads`.
|
||||
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
||||
Dropout probability for mlp outputs.
|
||||
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
||||
The dropout ratio for the embeddings.
|
||||
attention_dropout (`float`, *optional*, defaults to 0.0):
|
||||
The dropout ratio after computing the attention scores.
|
||||
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
||||
The non-linear activation function (function or string) in the decoder.
|
||||
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
||||
The maximum sequence length that this model might ever be used with.
|
||||
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
||||
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
||||
original RoPE embeddings when using long scaling.
|
||||
initializer_range (`float`, *optional*, defaults to 0.02):
|
||||
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
||||
The epsilon value used for the RMSNorm.
|
||||
use_cache (`bool`, *optional*, defaults to `True`):
|
||||
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
||||
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
||||
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
||||
Whether to tie weight embeddings
|
||||
rope_theta (`float`, *optional*, defaults to 10000.0):
|
||||
The base period of the RoPE embeddings.
|
||||
rope_scaling (`dict`, *optional*):
|
||||
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
||||
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
||||
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
||||
divided by the number of attention heads divided by 2.
|
||||
partial_rotary_factor (`float`, *optional*, defaults to 1.0):
|
||||
Percentage of the query and keys which will have rotary embedding. Must be between 0.0 and 1.0.
|
||||
bos_token_id (`int`, *optional*, defaults to 1):
|
||||
The id of the "beginning-of-sequence" token.
|
||||
eos_token_id (`int`, *optional*, defaults to 32000):
|
||||
The id of the "end-of-sequence" token.
|
||||
pad_token_id (`int`, *optional*, defaults to 32000):
|
||||
The id of the padding token.
|
||||
sliding_window (`int`, *optional*):
|
||||
Sliding window attention window size. If `None`, no sliding window is applied.
|
||||
|
||||
Example:
|
||||
|
||||
```python
|
||||
>>> from transformers import Phi3Model, Phi3Config
|
||||
|
||||
>>> # Initializing a Phi-3 style configuration
|
||||
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
||||
|
||||
>>> # Initializing a model from the configuration
|
||||
>>> model = Phi3Model(configuration)
|
||||
|
||||
>>> # Accessing the model configuration
|
||||
>>> configuration = model.config
|
||||
```"""
|
||||
|
||||
model_type = "phi3"
|
||||
keys_to_ignore_at_inference = ["past_key_values"]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_size=32064,
|
||||
hidden_size=3072,
|
||||
intermediate_size=8192,
|
||||
num_hidden_layers=32,
|
||||
num_attention_heads=32,
|
||||
num_key_value_heads=None,
|
||||
resid_pdrop=0.0,
|
||||
embd_pdrop=0.0,
|
||||
attention_dropout=0.0,
|
||||
hidden_act="silu",
|
||||
max_position_embeddings=4096,
|
||||
original_max_position_embeddings=4096,
|
||||
initializer_range=0.02,
|
||||
rms_norm_eps=1e-5,
|
||||
use_cache=True,
|
||||
tie_word_embeddings=False,
|
||||
rope_theta=10000.0,
|
||||
rope_scaling=None,
|
||||
partial_rotary_factor=1.0,
|
||||
bos_token_id=1,
|
||||
eos_token_id=32000,
|
||||
pad_token_id=32000,
|
||||
sliding_window=None,
|
||||
**kwargs,
|
||||
):
|
||||
self.vocab_size = vocab_size
|
||||
self.hidden_size = hidden_size
|
||||
self.intermediate_size = intermediate_size
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
|
||||
if num_key_value_heads is None:
|
||||
num_key_value_heads = num_attention_heads
|
||||
|
||||
self.num_key_value_heads = num_key_value_heads
|
||||
self.resid_pdrop = resid_pdrop
|
||||
self.embd_pdrop = embd_pdrop
|
||||
self.attention_dropout = attention_dropout
|
||||
self.hidden_act = hidden_act
|
||||
self.max_position_embeddings = max_position_embeddings
|
||||
self.original_max_position_embeddings = original_max_position_embeddings
|
||||
self.initializer_range = initializer_range
|
||||
self.rms_norm_eps = rms_norm_eps
|
||||
self.use_cache = use_cache
|
||||
self.rope_theta = rope_theta
|
||||
self.rope_scaling = rope_scaling
|
||||
self.partial_rotary_factor = partial_rotary_factor
|
||||
self._rope_scaling_adjustment()
|
||||
self._rope_scaling_validation()
|
||||
self.sliding_window = sliding_window
|
||||
|
||||
super().__init__(
|
||||
bos_token_id=bos_token_id,
|
||||
eos_token_id=eos_token_id,
|
||||
pad_token_id=pad_token_id,
|
||||
tie_word_embeddings=tie_word_embeddings,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
def _rope_scaling_adjustment(self):
|
||||
"""
|
||||
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
||||
"""
|
||||
if self.rope_scaling is None:
|
||||
return
|
||||
|
||||
rope_scaling_type = self.rope_scaling.get("type", None)
|
||||
|
||||
# For backward compatibility if previous version used "su" or "yarn"
|
||||
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
||||
self.rope_scaling["type"] = "longrope"
|
||||
|
||||
def _rope_scaling_validation(self):
|
||||
"""
|
||||
Validate the `rope_scaling` configuration.
|
||||
"""
|
||||
if self.rope_scaling is None:
|
||||
return
|
||||
|
||||
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
||||
raise ValueError(
|
||||
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
||||
f"got {self.rope_scaling}"
|
||||
)
|
||||
rope_scaling_type = self.rope_scaling.get("type", None)
|
||||
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
||||
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
||||
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
||||
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
||||
if not (
|
||||
isinstance(rope_scaling_short_factor, list)
|
||||
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
||||
):
|
||||
raise ValueError(
|
||||
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
||||
)
|
||||
rotary_ndims = int(self.hidden_size // self.num_attention_heads * self.partial_rotary_factor)
|
||||
if not len(rope_scaling_short_factor) == rotary_ndims // 2:
|
||||
raise ValueError(
|
||||
f"`rope_scaling`'s short_factor field must have length {rotary_ndims // 2}, got {len(rope_scaling_short_factor)}"
|
||||
)
|
||||
if not (
|
||||
isinstance(rope_scaling_long_factor, list)
|
||||
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
||||
):
|
||||
raise ValueError(
|
||||
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
||||
)
|
||||
if not len(rope_scaling_long_factor) == rotary_ndims // 2:
|
||||
raise ValueError(
|
||||
f"`rope_scaling`'s long_factor field must have length {rotary_ndims // 2}, got {len(rope_scaling_long_factor)}"
|
||||
)
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 199999,
|
||||
"eos_token_id": [
|
||||
200020,
|
||||
199999
|
||||
],
|
||||
"pad_token_id": 199999,
|
||||
"transformers_version": "4.45.0"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d006053a54d48237488883d4cb5bf1ddb3bafcf5f35a1085b0583f20b0948464
|
||||
size 5306316717
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aaa6502400a5576a4ad23869d87ef660b51ea3afe32420a285e32a7ea3d823ea
|
||||
size 2365749254
|
||||
202
model.safetensors.index.json
Normal file
202
model.safetensors.index.json
Normal file
@@ -0,0 +1,202 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 7672043520,
|
||||
"total_parameters": 3836021760
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
1180
modeling_phi3.py
Normal file
1180
modeling_phi3.py
Normal file
File diff suppressed because it is too large
Load Diff
214
sample_finetune.py
Normal file
214
sample_finetune.py
Normal file
@@ -0,0 +1,214 @@
|
||||
import sys
|
||||
import logging
|
||||
|
||||
import datasets
|
||||
from datasets import load_dataset
|
||||
from peft import LoraConfig
|
||||
import torch
|
||||
import transformers
|
||||
from trl import SFTTrainer
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, BitsAndBytesConfig
|
||||
|
||||
"""
|
||||
A simple example on using SFTTrainer and Accelerate to finetune Phi-4-Mini-Instruct model. For
|
||||
a more advanced example, please follow HF alignment-handbook/scripts/run_sft.py.
|
||||
This example has utilized DeepSpeed ZeRO3 offload to reduce the memory usage. The
|
||||
script can be run on V100 or later generation GPUs. Here are some suggestions on
|
||||
futher reducing memory consumption:
|
||||
- reduce batch size
|
||||
- decrease lora dimension
|
||||
- restrict lora target modules
|
||||
Please follow these steps to run the script:
|
||||
1. Install dependencies:
|
||||
conda install -c conda-forge accelerate=1.3.0
|
||||
pip3 install -i https://pypi.org/simple/ bitsandbytes
|
||||
pip3 install peft==0.14.0
|
||||
pip3 install transformers==4.48.1
|
||||
pip3 install trl datasets
|
||||
pip3 install deepspeed
|
||||
2. Setup accelerate and deepspeed config based on the machine used:
|
||||
accelerate config
|
||||
Here is a sample config for deepspeed zero3:
|
||||
compute_environment: LOCAL_MACHINE
|
||||
debug: false
|
||||
deepspeed_config:
|
||||
gradient_accumulation_steps: 1
|
||||
offload_optimizer_device: none
|
||||
offload_param_device: none
|
||||
zero3_init_flag: true
|
||||
zero3_save_16bit_model: true
|
||||
zero_stage: 3
|
||||
distributed_type: DEEPSPEED
|
||||
downcast_bf16: 'no'
|
||||
enable_cpu_affinity: false
|
||||
machine_rank: 0
|
||||
main_training_function: main
|
||||
mixed_precision: bf16
|
||||
num_machines: 1
|
||||
num_processes: 4
|
||||
rdzv_backend: static
|
||||
same_network: true
|
||||
tpu_env: []
|
||||
tpu_use_cluster: false
|
||||
tpu_use_sudo: false
|
||||
use_cpu: false
|
||||
3. check accelerate config:
|
||||
accelerate env
|
||||
4. Run the code:
|
||||
accelerate launch sample_finetune.py
|
||||
"""
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
###################
|
||||
# Hyper-parameters
|
||||
###################
|
||||
training_config = {
|
||||
"bf16": True,
|
||||
"do_eval": False,
|
||||
"learning_rate": 5.0e-06,
|
||||
"log_level": "info",
|
||||
"logging_steps": 20,
|
||||
"logging_strategy": "steps",
|
||||
"lr_scheduler_type": "cosine",
|
||||
"num_train_epochs": 1,
|
||||
"max_steps": -1,
|
||||
"output_dir": "./checkpoint_dir",
|
||||
"overwrite_output_dir": True,
|
||||
"per_device_eval_batch_size": 4,
|
||||
"per_device_train_batch_size": 4,
|
||||
"remove_unused_columns": True,
|
||||
"save_steps": 100,
|
||||
"save_total_limit": 1,
|
||||
"seed": 0,
|
||||
"gradient_checkpointing": True,
|
||||
"gradient_checkpointing_kwargs":{"use_reentrant": False},
|
||||
"gradient_accumulation_steps": 1,
|
||||
"warmup_ratio": 0.2,
|
||||
}
|
||||
|
||||
peft_config = {
|
||||
"r": 16,
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.05,
|
||||
"bias": "none",
|
||||
"task_type": "CAUSAL_LM",
|
||||
"target_modules": "all-linear",
|
||||
"modules_to_save": None,
|
||||
}
|
||||
train_conf = TrainingArguments(**training_config)
|
||||
peft_conf = LoraConfig(**peft_config)
|
||||
|
||||
|
||||
###############
|
||||
# Setup logging
|
||||
###############
|
||||
logging.basicConfig(
|
||||
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
|
||||
datefmt="%Y-%m-%d %H:%M:%S",
|
||||
handlers=[logging.StreamHandler(sys.stdout)],
|
||||
)
|
||||
log_level = train_conf.get_process_log_level()
|
||||
logger.setLevel(log_level)
|
||||
datasets.utils.logging.set_verbosity(log_level)
|
||||
transformers.utils.logging.set_verbosity(log_level)
|
||||
transformers.utils.logging.enable_default_handler()
|
||||
transformers.utils.logging.enable_explicit_format()
|
||||
|
||||
# Log on each process a small summary
|
||||
logger.warning(
|
||||
f"Process rank: {train_conf.local_rank}, device: {train_conf.device}, n_gpu: {train_conf.n_gpu}"
|
||||
+ f" distributed training: {bool(train_conf.local_rank != -1)}, 16-bits training: {train_conf.fp16}"
|
||||
)
|
||||
logger.info(f"Training/evaluation parameters {train_conf}")
|
||||
logger.info(f"PEFT parameters {peft_conf}")
|
||||
|
||||
|
||||
################
|
||||
# Model Loading
|
||||
################
|
||||
checkpoint_path = "microsoft/Phi-4-mini-instruct"
|
||||
model_kwargs = dict(
|
||||
use_cache=False,
|
||||
trust_remote_code=True,
|
||||
attn_implementation="flash_attention_2", # loading the model with flash-attention support
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map=None
|
||||
)
|
||||
model = AutoModelForCausalLM.from_pretrained(checkpoint_path, **model_kwargs)
|
||||
tokenizer = AutoTokenizer.from_pretrained(checkpoint_path)
|
||||
tokenizer.model_max_length = 2048
|
||||
tokenizer.pad_token = tokenizer.unk_token # use unk rather than eos token to prevent endless generation
|
||||
tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids(tokenizer.pad_token)
|
||||
tokenizer.padding_side = 'right'
|
||||
|
||||
|
||||
##################
|
||||
# Data Processing
|
||||
##################
|
||||
def apply_chat_template(
|
||||
example,
|
||||
tokenizer,
|
||||
):
|
||||
messages = example["messages"]
|
||||
example["text"] = tokenizer.apply_chat_template(
|
||||
messages, tokenize=False, add_generation_prompt=False)
|
||||
return example
|
||||
|
||||
|
||||
train_dataset, test_dataset = load_dataset("HuggingFaceH4/ultrachat_200k", split=["train_sft", "test_sft"])
|
||||
column_names = list(train_dataset.features)
|
||||
|
||||
processed_train_dataset = train_dataset.map(
|
||||
apply_chat_template,
|
||||
fn_kwargs={"tokenizer": tokenizer},
|
||||
num_proc=10,
|
||||
remove_columns=column_names,
|
||||
desc="Applying chat template to train_sft",
|
||||
)
|
||||
|
||||
processed_test_dataset = test_dataset.map(
|
||||
apply_chat_template,
|
||||
fn_kwargs={"tokenizer": tokenizer},
|
||||
num_proc=10,
|
||||
remove_columns=column_names,
|
||||
desc="Applying chat template to test_sft",
|
||||
)
|
||||
|
||||
|
||||
###########
|
||||
# Training
|
||||
###########
|
||||
trainer = SFTTrainer(
|
||||
model=model,
|
||||
args=train_conf,
|
||||
peft_config=peft_conf,
|
||||
train_dataset=processed_train_dataset,
|
||||
eval_dataset=processed_test_dataset,
|
||||
max_seq_length=2048,
|
||||
dataset_text_field="text",
|
||||
tokenizer=tokenizer,
|
||||
packing=True
|
||||
)
|
||||
train_result = trainer.train()
|
||||
metrics = train_result.metrics
|
||||
trainer.log_metrics("train", metrics)
|
||||
trainer.save_metrics("train", metrics)
|
||||
trainer.save_state()
|
||||
|
||||
|
||||
#############
|
||||
# Evaluation
|
||||
#############
|
||||
tokenizer.padding_side = 'left'
|
||||
metrics = trainer.evaluate()
|
||||
metrics["eval_samples"] = len(processed_test_dataset)
|
||||
trainer.log_metrics("eval", metrics)
|
||||
trainer.save_metrics("eval", metrics)
|
||||
|
||||
|
||||
# ############
|
||||
# # Save model
|
||||
# ############
|
||||
trainer.save_model(train_conf.output_dir)
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7ea8bdf68c3e7549a3fb4342523288ce628f6ab56a618f9a4dfb234a0b4d46a8
|
||||
size 15524476
|
||||
12
tokenizer_config.json
Normal file
12
tokenizer_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"is_local": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user