初始化项目，由ModelHub XC社区提供模型
Model: silma-ai/SILMA-9B-Instruct-v1.0 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
|
||||
758
README.md
Normal file
758
README.md
Normal file
@@ -0,0 +1,758 @@
|
||||
---
|
||||
license: gemma
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
extra_gated_button_content: Acknowledge license
|
||||
tags:
|
||||
- conversational
|
||||
language:
|
||||
- ar
|
||||
- en
|
||||
model-index:
|
||||
- name: SILMA-9B-Instruct-v1.0
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: Arabic Broad Benchmark (ABB)
|
||||
type: silma-ai/arabic-broad-benchmark
|
||||
metrics:
|
||||
- name: benchmark_score
|
||||
type: acc (1-10)
|
||||
value: 6.15
|
||||
source:
|
||||
name: Arabic Broad Leaderboard (ABL)
|
||||
url: https://huggingface.co/spaces/silma-ai/Arabic-LLM-Broad-Leaderboard
|
||||
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: MMLU (Arabic)
|
||||
type: OALL/Arabic_MMLU
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 52.55
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: AlGhafa
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Native
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 71.85
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: ARC Challenge (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 78.19
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: ACVA
|
||||
type: OALL/ACVA
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 78.89
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: Arabic_EXAMS
|
||||
type: OALL/Arabic_EXAMS
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 51.4
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: ARC Easy
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 86
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: BOOLQ (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 64.05
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: COPA (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 78.89
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: HELLASWAG (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 47.64
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OPENBOOK QA (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 72.93
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: PIQA (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 71.96
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: RACE (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 75.55
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: SCIQ (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 91.26
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: TOXIGEN (Arabic)
|
||||
type: OALL/AlGhafa-Arabic-LLM-Benchmark-Translated
|
||||
metrics:
|
||||
- name: acc_norm
|
||||
type: loglikelihood_acc_norm
|
||||
value: 67.59
|
||||
source:
|
||||
name: Open Arabic LLM Leaderboard
|
||||
url: https://huggingface.co/spaces/OALL/Open-Arabic-LLM-Leaderboard-v1
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: IFEval (0-Shot)
|
||||
type: HuggingFaceH4/ifeval
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: inst_level_strict_acc and prompt_level_strict_acc
|
||||
value: 58.42
|
||||
name: strict accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=silma-ai/SILMA-9B-Instruct-v1.0
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: BBH (3-Shot)
|
||||
type: BBH
|
||||
args:
|
||||
num_few_shot: 3
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 30.71
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=silma-ai/SILMA-9B-Instruct-v1.0
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MATH Lvl 5 (4-Shot)
|
||||
type: hendrycks/competition_math
|
||||
args:
|
||||
num_few_shot: 4
|
||||
metrics:
|
||||
- type: exact_match
|
||||
value: 0.0
|
||||
name: exact match
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=silma-ai/SILMA-9B-Instruct-v1.0
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GPQA (0-shot)
|
||||
type: Idavidrein/gpqa
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 7.38
|
||||
name: acc_norm
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=silma-ai/SILMA-9B-Instruct-v1.0
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MuSR (0-shot)
|
||||
type: TAUR-Lab/MuSR
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 17.26
|
||||
name: acc_norm
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=silma-ai/SILMA-9B-Instruct-v1.0
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU-PRO (5-shot)
|
||||
type: TIGER-Lab/MMLU-Pro
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 32.44
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=silma-ai/SILMA-9B-Instruct-v1.0
|
||||
name: Open LLM Leaderboard
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
|
||||
# SILMA AI
|
||||
|
||||
SILMA.AI is a leading Generative AI startup dedicated to empowering Arabic speakers with state-of-the-art AI solutions.
|
||||
|
||||
|
||||
## 🚀 Our Flagship Model: SILMA 1.0 🚀
|
||||
|
||||
* **SILMA 1.0** was the **TOP-RANKED** open-weights Arabic LLM (Until February 2025) with an impressive **9 billion parameter size**, surpassing models that are over seven times larger 🏆
|
||||
|
||||
**Important Tip:** 💡 For RAG use-cases please use [SILMA Kashif v1.0](https://huggingface.co/silma-ai/SILMA-Kashif-2B-Instruct-v1.0) as it has been specifically trained for Question Answering tasks.
|
||||
|
||||
|
||||
## What makes SILMA exceptional?
|
||||
|
||||
* SIMLA is a small language model outperforming 72B models in most arabic language tasks, thus more practical for business use-cases
|
||||
* SILMA is built over the robust foundational models of Google Gemma, combining the strengths of both to provide you with unparalleled performance
|
||||
* SILMA is an open-weight model, free to use in accordance with our open license
|
||||
|
||||
|
||||
## 👥 Our Team
|
||||
|
||||
We are a team of seasoned **Arabic AI experts** who understand the nuances of the language and cultural considerations, enabling us to build solutions that truly resonate with Arabic users.
|
||||
|
||||
**Authors**: [silma.ai](https://silma.ai)
|
||||
|
||||
|
||||
### Usage
|
||||
|
||||
Below we share some code snippets on how to get quickly started with running the model. First, install the Transformers library with:
|
||||
|
||||
```sh
|
||||
pip install -U transformers sentencepiece
|
||||
```
|
||||
|
||||
Then, copy the snippet from the section that is relevant for your usecase.
|
||||
|
||||
#### Running with the `pipeline` API
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import pipeline
|
||||
|
||||
pipe = pipeline(
|
||||
"text-generation",
|
||||
model="silma-ai/SILMA-9B-Instruct-v1.0",
|
||||
model_kwargs={"torch_dtype": torch.bfloat16},
|
||||
device="cuda", # replace with "mps" to run on a Mac device
|
||||
)
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "اكتب رسالة تعتذر فيها لمديري في العمل عن الحضور اليوم لأسباب مرضية."},
|
||||
]
|
||||
|
||||
outputs = pipe(messages, max_new_tokens=256)
|
||||
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
|
||||
print(assistant_response)
|
||||
```
|
||||
|
||||
- Response:
|
||||
|
||||
```text
|
||||
السلام عليكم ورحمة الله وبركاته
|
||||
|
||||
أودّ أن أعتذر عن عدم الحضور إلى العمل اليوم بسبب مرضي. أشعر بالسوء الشديد وأحتاج إلى الراحة. سأعود إلى العمل فور تعافيي.
|
||||
شكراً لتفهمكم.
|
||||
|
||||
مع تحياتي،
|
||||
[اسمك]
|
||||
```
|
||||
|
||||
#### Running the model on a single / multi GPU
|
||||
|
||||
```sh
|
||||
pip install accelerate
|
||||
```
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
model_id = "silma-ai/SILMA-9B-Instruct-v1.0"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
device_map="auto",
|
||||
torch_dtype=torch.bfloat16,
|
||||
)
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "أنت مساعد ذكي للإجابة عن أسئلة المستخدمين."},
|
||||
{"role": "user", "content": "أيهما أبعد عن الأرض, الشمس أم القمر؟"},
|
||||
]
|
||||
|
||||
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
|
||||
|
||||
outputs = model.generate(**input_ids, max_new_tokens=256)
|
||||
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
- Response:
|
||||
```text
|
||||
الشمس
|
||||
```
|
||||
|
||||
You can ensure the correct chat template is applied by using `tokenizer.apply_chat_template` as follows:
|
||||
```python
|
||||
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
model_id = "silma-ai/SILMA-9B-Instruct-v1.0"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
device_map="auto",
|
||||
torch_dtype=torch.bfloat16,
|
||||
)
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "أنت مساعد ذكي للإجابة عن أسئلة المستخدمين."},
|
||||
{"role": "user", "content": "اكتب كود بايثون لتوليد متسلسلة أرقام زوجية."},
|
||||
]
|
||||
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
|
||||
|
||||
outputs = model.generate(**input_ids, max_new_tokens=256)
|
||||
print(tokenizer.decode(outputs[0]).split("<start_of_turn>model")[-1])
|
||||
```
|
||||
|
||||
- Response:
|
||||
```python
|
||||
def generate_even_numbers(n):
|
||||
"""
|
||||
This function generates a list of even numbers from 1 to n.
|
||||
Args:
|
||||
n: The upper limit of the range.
|
||||
|
||||
Returns:
|
||||
A list of even numbers.
|
||||
"""
|
||||
return [i for i in range(1, n + 1) if i % 2 == 0]
|
||||
|
||||
# Example usage
|
||||
n = 10
|
||||
even_numbers = generate_even_numbers(n)
|
||||
print(f"The first {n} even numbers are: {even_numbers}")
|
||||
```
|
||||
|
||||
#### Quantized Versions through `bitsandbytes`
|
||||
|
||||
<details>
|
||||
<summary>
|
||||
Using 8-bit precision (int8)
|
||||
</summary>
|
||||
|
||||
```sh
|
||||
pip install bitsandbytes accelerate
|
||||
```
|
||||
|
||||
```python
|
||||
# pip install bitsandbytes accelerate
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
||||
|
||||
model_id = "silma-ai/SILMA-9B-Instruct-v1.0"
|
||||
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
quantization_config=quantization_config,
|
||||
)
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "أنت مساعد ذكي للإجابة عن أسئلة المستخدمين."},
|
||||
{"role": "user", "content": "اذكر خمس انواع فواكه بها نسب عالية من فيتامين ج."},
|
||||
]
|
||||
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
|
||||
|
||||
outputs = model.generate(**input_ids, max_new_tokens=256)
|
||||
print(tokenizer.decode(outputs[0]).split("<start_of_turn>model")[-1])
|
||||
```
|
||||
|
||||
- Response:
|
||||
```text
|
||||
الليمون، البرتقال، الموز، الكيوي، الفراولة
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>
|
||||
Using 4-bit precision
|
||||
</summary>
|
||||
|
||||
```python
|
||||
# pip install bitsandbytes accelerate
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
||||
|
||||
model_id = "silma-ai/SILMA-9B-Instruct-v1.0"
|
||||
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
quantization_config=quantization_config,
|
||||
)
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "أنت مساعد ذكي للإجابة عن أسئلة المستخدمين."},
|
||||
{"role": "user", "content": "في أي عام توفى صلاح الدين الأيوبي؟"},
|
||||
]
|
||||
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
|
||||
|
||||
outputs = model.generate(**input_ids, max_new_tokens=256)
|
||||
print(tokenizer.decode(outputs[0]).split("<start_of_turn>model")[-1])
|
||||
```
|
||||
|
||||
- Response:
|
||||
```text
|
||||
1193
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
#### Advanced Usage
|
||||
|
||||
<details>
|
||||
<summary>
|
||||
Torch compile
|
||||
</summary>
|
||||
|
||||
[Torch compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) is a method for speeding-up the
|
||||
inference of PyTorch modules. The Silma model can be run up to 6x faster by leveraging torch compile.
|
||||
|
||||
Note that two warm-up steps are required before the full inference speed is realised:
|
||||
|
||||
```python
|
||||
import os
|
||||
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
||||
|
||||
from transformers import AutoTokenizer, Gemma2ForCausalLM
|
||||
from transformers.cache_utils import HybridCache
|
||||
import torch
|
||||
|
||||
torch.set_float32_matmul_precision("high")
|
||||
|
||||
# load the model + tokenizer
|
||||
model_id = "silma-ai/SILMA-9B-Instruct-v1.0"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = Gemma2ForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
|
||||
model.to("cuda")
|
||||
|
||||
# apply the torch compile transformation
|
||||
model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True)
|
||||
|
||||
# pre-process inputs
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "أنت مساعد ذكي للإجابة عن أسئلة المستخدمين."},
|
||||
{"role": "user", "content": "من الرئيس الذي تولى المنصب في أمريكا بعد دونالد ترامب؟"},
|
||||
]
|
||||
model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")
|
||||
|
||||
input_text = "من الرئيس الذي تولى المنصب في أمريكا بعد دونالد ترامب؟"
|
||||
model_inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
|
||||
prompt_length = model_inputs.input_ids.shape[1]
|
||||
|
||||
# set-up k/v cache
|
||||
past_key_values = HybridCache(
|
||||
config=model.config,
|
||||
max_batch_size=1,
|
||||
max_cache_len=model.config.max_position_embeddings,
|
||||
device=model.device,
|
||||
dtype=model.dtype
|
||||
)
|
||||
|
||||
# enable passing kv cache to generate
|
||||
model._supports_cache_class = True
|
||||
model.generation_config.cache_implementation = None
|
||||
|
||||
# two warm-up steps
|
||||
for idx in range(2):
|
||||
outputs = model.generate(**model_inputs, past_key_values=past_key_values, do_sample=True, temperature=1.0, max_new_tokens=128)
|
||||
past_key_values.reset()
|
||||
|
||||
# fast run
|
||||
outputs = model.generate(**model_inputs, past_key_values=past_key_values, do_sample=True, temperature=1.0, max_new_tokens=128)
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
- Response:
|
||||
```text
|
||||
جو بايدن
|
||||
```
|
||||
|
||||
For more details, refer to the [Transformers documentation](https://huggingface.co/docs/transformers/main/en/llm_optims?static-kv=basic+usage%3A+generation_config).
|
||||
|
||||
</details>
|
||||
|
||||
### Chat Template
|
||||
|
||||
The instruction-tuned models use a chat template that must be adhered to for conversational use.
|
||||
The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.
|
||||
|
||||
Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import transformers
|
||||
import torch
|
||||
|
||||
model_id = "silma-ai/SILMA-9B-Instruct-v1.0"
|
||||
dtype = torch.bfloat16
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
device_map="cuda",
|
||||
torch_dtype=dtype,)
|
||||
|
||||
chat = [
|
||||
{ "role": "user", "content": "ما اشهر اطارات العمل في البايثون لبناء نماذج الذكاء الاصطناعي؟" },
|
||||
]
|
||||
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
|
||||
```
|
||||
|
||||
At this point, the prompt contains the following text:
|
||||
|
||||
```
|
||||
<bos><start_of_turn>user
|
||||
ما اشهر اطارات العمل في البايثون لبناء نماذج الذكاء الاصطناعي؟<end_of_turn>
|
||||
<start_of_turn>model
|
||||
```
|
||||
|
||||
As you can see, each turn is preceded by a `<start_of_turn>` delimiter and then the role of the entity
|
||||
(either `user`, for content supplied by the user, or `model` for LLM responses). Turns finish with
|
||||
the `<end_of_turn>` token.
|
||||
|
||||
You can follow this format to build the prompt manually, if you need to do it without the tokenizer's
|
||||
chat template.
|
||||
|
||||
After the prompt is ready, generation can be performed like this:
|
||||
|
||||
```python
|
||||
inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
|
||||
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
### Inputs and outputs
|
||||
|
||||
* **Input:** Text string, such as a question, a prompt, or a document to be
|
||||
summarized.
|
||||
* **Output:** Generated Arabic or English text in response to the input, such
|
||||
as an answer to a question, or a summary of a document.
|
||||
|
||||
|
||||
### GPU Requirements
|
||||
|
||||
The following are the minimum/recommended GPU requirements for running inference:
|
||||
|
||||
* Recommended
|
||||
* At least one GPU with a minimum of 48 GB of GPU memory
|
||||
* Examples: Nvidia A40, L40, RTX A6000
|
||||
|
||||
* Minimum
|
||||
|
||||
* At least one GPU with 16-24 GB of GPU memory
|
||||
* Examples: Nvidia RTX 4090, RTX 4000, L4
|
||||
* Assuming that the model is loaded in either 8-bit or 4-bit [Quantization mode](https://huggingface.co/silma-ai/SILMA-9B-Instruct-v1.0#quantized-versions-through-bitsandbytes)
|
||||
|
||||
|
||||
### Citation
|
||||
|
||||
```bibtex
|
||||
@misc{silma-9b-2024,
|
||||
author = {{silma-ai}},
|
||||
title = {SILMA 9B Instruct v1.0},
|
||||
year = {2024},
|
||||
howpublished = {\url{https://huggingface.co/silma-ai/SILMA-9B-Instruct-v1.0}}
|
||||
}
|
||||
```
|
||||
|
||||
## Usage and Limitations
|
||||
|
||||
These models have certain limitations that users should be aware of.
|
||||
|
||||
### Intended Usage
|
||||
|
||||
Open Large Language Models (LLMs) have a wide range of applications across
|
||||
various industries and domains. The following list of potential uses is not
|
||||
comprehensive. The purpose of this list is to provide contextual information
|
||||
about the possible use-cases that the model creators considered as part of model
|
||||
training and development.
|
||||
|
||||
* Content Creation and Communication
|
||||
* Text Generation: These models can be used to generate creative text formats
|
||||
such as poems, scripts, code, marketing copy, and email drafts.
|
||||
* Chatbots and Conversational AI: Power conversational interfaces for customer
|
||||
service, virtual assistants, or interactive applications.
|
||||
* Text Summarization: Generate concise summaries of a text corpus, research
|
||||
papers, or reports.
|
||||
* Research and Education
|
||||
* Natural Language Processing (NLP) Research: These models can serve as a
|
||||
foundation for researchers to experiment with NLP techniques, develop
|
||||
algorithms, and contribute to the advancement of the field.
|
||||
* Language Learning Tools: Support interactive language learning experiences,
|
||||
aiding in grammar correction or providing writing practice.
|
||||
* Knowledge Exploration: Assist researchers in exploring large bodies of text
|
||||
by generating summaries or answering questions about specific topics.
|
||||
|
||||
### Limitations
|
||||
|
||||
* Training Data
|
||||
* The quality and diversity of the training data significantly influence the
|
||||
model's capabilities. Biases or gaps in the training data can lead to
|
||||
limitations in the model's responses.
|
||||
* The scope of the training dataset determines the subject areas the model can
|
||||
handle effectively.
|
||||
* Context and Task Complexity
|
||||
* LLMs are better at tasks that can be framed with clear prompts and
|
||||
instructions. Open-ended or highly complex tasks might be challenging.
|
||||
* A model's performance can be influenced by the amount of context provided
|
||||
(longer context generally leads to better outputs, up to a certain point).
|
||||
* Language Ambiguity and Nuance
|
||||
* Natural language is inherently complex. LLMs might struggle to grasp subtle
|
||||
nuances, sarcasm, or figurative language.
|
||||
* Factual Accuracy
|
||||
* LLMs generate responses based on information they learned from their
|
||||
training datasets, but they are not knowledge bases. They may generate
|
||||
incorrect or outdated factual statements.
|
||||
* Common Sense
|
||||
* LLMs rely on statistical patterns in language. They might lack the ability
|
||||
to apply common sense reasoning in certain situations.
|
||||
|
||||
### Ethical Considerations and Risks
|
||||
|
||||
The development of large language models (LLMs) raises several ethical concerns.
|
||||
In creating an open model, we have carefully considered the following:
|
||||
|
||||
* Bias and Fairness
|
||||
* LLMs trained on large-scale, real-world text data can reflect socio-cultural
|
||||
biases embedded in the training material.
|
||||
* Misinformation and Misuse
|
||||
* LLMs can be misused to generate text that is false, misleading, or harmful.
|
||||
* Guidelines are provided for responsible use with the model, see the
|
||||
[Responsible Generative AI Toolkit][rai-toolkit].
|
||||
* Transparency and Accountability:
|
||||
* This model card summarizes details on the models' architecture,
|
||||
capabilities, limitations, and evaluation processes.
|
||||
* A responsibly developed open model offers the opportunity to share
|
||||
innovation by making LLM technology accessible to developers and researchers
|
||||
across the AI ecosystem.
|
||||
|
||||
Risks identified and mitigations:
|
||||
|
||||
* Perpetuation of biases: It's encouraged to perform continuous monitoring
|
||||
(using evaluation metrics, human review) and the exploration of de-biasing
|
||||
techniques during model training, fine-tuning, and other use cases.
|
||||
* Generation of harmful content: Mechanisms and guidelines for content safety
|
||||
are essential. Developers are encouraged to exercise caution and implement
|
||||
appropriate content safety safeguards based on their specific product policies
|
||||
and application use cases.
|
||||
* Privacy violations: Models were trained on data filtered for removal of PII
|
||||
(Personally Identifiable Information). Developers are encouraged to adhere to
|
||||
privacy regulations with privacy-preserving techniques.
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"_name_or_path": "google/gemma-2-9b-it",
|
||||
"architectures": [
|
||||
"Gemma2ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": 50.0,
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"eos_token_id": 1,
|
||||
"final_logit_softcapping": 30.0,
|
||||
"head_dim": 256,
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_activation": "gelu_pytorch_tanh",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "gemma2",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 42,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"query_pre_attn_scalar": 256,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"sliding_window_size": 4096,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.43.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 256000
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"eos_token_id": 1,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.43.4"
|
||||
}
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:19272e9ca490cf69f9bdd24f2462a0a4780293924fb227cf9e0f84c95b01cf75
|
||||
size 3905047416
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c381199444389df9d3a1d2248162a7860dd64441867b9e278ae1f884812c2520
|
||||
size 3963916880
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1daeca3f9390dc018802cbd52443b8119eb91ca13ced79812bf88293c6610b54
|
||||
size 3963916944
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:84ab792378aa37fb5383a8959cb1262e563d119f944c805c09aede00da4c76e2
|
||||
size 3963916944
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a5eac2cf8eb3bf0d9b833ef9cfa91c94ffcd6bf4fcfba13d0542359bfb97095a
|
||||
size 2686668256
|
||||
471
model.safetensors.index.json
Normal file
471
model.safetensors.index.json
Normal file
@@ -0,0 +1,471 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 18483411968
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||
}
|
||||
}
|
||||
1
notice.txt
Normal file
1
notice.txt
Normal file
@@ -0,0 +1 @@
|
||||
Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms
|
||||
34
special_tokens_map.json
Normal file
34
special_tokens_map.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<start_of_turn>",
|
||||
"<end_of_turn>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<bos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<eos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
|
||||
size 17525357
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
||||
size 4241003
|
||||
2015
tokenizer_config.json
Normal file
2015
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user