Add link to tech report. Fix typo in usage example #2
This commit is contained in:
ai-modelscope
28
.gitattributes
vendored
28
.gitattributes
vendored
@@ -1,37 +1,39 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin 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
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* 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
|
||||
*.nemo filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
lfs -text
|
||||
|
||||
5
NOTICE
Normal file
5
NOTICE
Normal file
@@ -0,0 +1,5 @@
|
||||
Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
||||
|
||||
NVIDIA CORPORATION, its affiliates and licensors retain all intellectual property and proprietary rights in and to this material, related documentation and any modifications thereto. Any use, reproduction, disclosure or distribution of this material and related documentation without an express license agreement from NVIDIA CORPORATION or its affiliates is strictly prohibited.
|
||||
|
||||
Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
|
||||
181
README.md
181
README.md
@@ -1,47 +1,148 @@
|
||||
---
|
||||
license: Apache License 2.0
|
||||
|
||||
#model-type:
|
||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
||||
#- gpt
|
||||
|
||||
#domain:
|
||||
##如 nlp、cv、audio、multi-modal
|
||||
#- nlp
|
||||
|
||||
#language:
|
||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
||||
#- cn
|
||||
|
||||
#metrics:
|
||||
##如 CIDEr、Blue、ROUGE 等
|
||||
#- CIDEr
|
||||
|
||||
#tags:
|
||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
||||
#- pretrained
|
||||
|
||||
#tools:
|
||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
||||
#- vllm
|
||||
license: other
|
||||
license_name: nvidia-open-model-license
|
||||
license_link: >-
|
||||
https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
|
||||
---
|
||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
||||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
||||
# Llama-3.1-Minitron-4B-Width-Base
|
||||
|
||||
SDK下载
|
||||
```bash
|
||||
#安装ModelScope
|
||||
pip install modelscope
|
||||
## Model Overview
|
||||
|
||||
Llama-3.1-Minitron-4B-Width-Base is a base text-to-text model that can be adopted for a variety of natural language generation tasks.
|
||||
It is obtained by pruning Llama-3.1-8B; specifically, we prune model embedding size and MLP intermediate dimension.
|
||||
Following pruning, we perform continued training with distillation using 94 billion tokens to arrive at the final model; we use the continuous pre-training data corpus used in Nemotron-4 15B for this purpose. Please refer to our [technical report](https://arxiv.org/abs/2408.11796) for more details.
|
||||
|
||||
This model is ready for commercial use.
|
||||
|
||||
**Model Developer:** NVIDIA
|
||||
|
||||
**Model Dates:** Llama-3.1-Minitron-4B-Width-Base was trained between July 29, 2024 and Aug 3, 2024.
|
||||
|
||||
## License
|
||||
|
||||
This model is released under the [NVIDIA Open Model License Agreement](https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf).
|
||||
|
||||
## Model Architecture
|
||||
|
||||
Llama-3.1-Minitron-4B-Width-Base uses a model embedding size of 3072, 32 attention heads, MLP intermediate dimension of 9216, with 32 layers in total. Additionally, it uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE).
|
||||
|
||||
**Architecture Type:** Transformer Decoder (Auto-Regressive Language Model)
|
||||
|
||||
**Network Architecture:** Llama-3.1
|
||||
|
||||
**Input Type(s):** Text
|
||||
|
||||
**Input Format(s):** String
|
||||
|
||||
**Input Parameters:** None
|
||||
|
||||
**Other Properties Related to Input:** Works well within 8k characters or less.
|
||||
|
||||
**Output Type(s):** Text
|
||||
|
||||
**Output Format:** String
|
||||
|
||||
**Output Parameters:** 1D
|
||||
|
||||
**Other Properties Related to Output:** None
|
||||
|
||||
|
||||
## Usage
|
||||
Support for this model will be added in the upcoming `transformers` release. In the meantime, please install the library from source:
|
||||
```
|
||||
pip install git+https://github.com/huggingface/transformers
|
||||
```
|
||||
We can now run inference on this model:
|
||||
|
||||
```python
|
||||
#SDK模型下载
|
||||
from modelscope import snapshot_download
|
||||
model_dir = snapshot_download('AI-ModelScope/Llama-3.1-Minitron-4B-Width-Base')
|
||||
```
|
||||
Git下载
|
||||
```
|
||||
#Git模型下载
|
||||
git clone https://www.modelscope.cn/AI-ModelScope/Llama-3.1-Minitron-4B-Width-Base.git
|
||||
import torch
|
||||
from transformers import AutoTokenizer, LlamaForCausalLM
|
||||
|
||||
# Load the tokenizer and model
|
||||
model_path = "nvidia/Llama-3.1-Minitron-4B-Width-Base"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
||||
|
||||
device = 'cuda'
|
||||
dtype = torch.bfloat16
|
||||
model = LlamaForCausalLM.from_pretrained(model_path, torch_dtype=dtype, device_map=device)
|
||||
|
||||
# Prepare the input text
|
||||
prompt = 'Complete the paragraph: our solar system is'
|
||||
inputs = tokenizer.encode(prompt, return_tensors='pt').to(model.device)
|
||||
|
||||
# Generate the output
|
||||
outputs = model.generate(inputs, max_length=20)
|
||||
|
||||
# Decode and print the output
|
||||
output_text = tokenizer.decode(outputs[0])
|
||||
print(output_text)
|
||||
```
|
||||
|
||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
||||
## Software Integration
|
||||
**Runtime Engine(s):**
|
||||
* NeMo 24.05
|
||||
|
||||
**Supported Hardware Microarchitecture Compatibility:** <br>
|
||||
* NVIDIA Ampere
|
||||
* NVIDIA Blackwell
|
||||
* NVIDIA Hopper
|
||||
* NVIDIA Lovelace
|
||||
|
||||
|
||||
**[Preferred/Supported] Operating System(s):** <br>
|
||||
* Linux
|
||||
|
||||
## Dataset & Training
|
||||
|
||||
**Data Collection Method by Dataset:** Automated
|
||||
|
||||
**Labeling Method by Dataset:** Not Applicable
|
||||
|
||||
**Properties:**
|
||||
The training corpus for Llama-3.1-Minitron-4B-Width-Base consists of English and multilingual text, as well as code. Our sources cover a variety of document types such as: webpages, dialogue, articles, and other written materials. The corpus spans domains including legal, math, science, finance, and more. In our continued training set, we introduce a small portion of question-answering, and alignment style data to improve model performance.
|
||||
|
||||
**Data Freshness:** The pretraining data has a cutoff of June 2023.
|
||||
|
||||
## Evaluation Results
|
||||
|
||||
### Overview
|
||||
_5-shot performance._ Language Understanding evaluated using [Massive Multitask Language Understanding](https://arxiv.org/abs/2009.03300):
|
||||
|
||||
| Average |
|
||||
| :---- |
|
||||
| 60.5 |
|
||||
|
||||
_Zero-shot performance._ Evaluated using select datasets from the [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) with additions:
|
||||
|
||||
| HellaSwag | Winogrande | GSM8K| ARC-Challenge | XLSum |
|
||||
| :---- | :---- | :---- | :---- | :---- |
|
||||
| 76.1 | 73.5 | 41.2 | 55.6 | 28.7
|
||||
|
||||
_Code generation performance._ Evaluated using [MBPP](https://github.com/google-research/google-research/tree/master/mbpp):
|
||||
| Score |
|
||||
| :---- |
|
||||
| 32.0 |
|
||||
|
||||
## Inference
|
||||
|
||||
**Engine:** TensorRT-LLM
|
||||
|
||||
**Test Hardware:** NVIDIA A100
|
||||
|
||||
**DType:** BFloat16
|
||||
|
||||
|
||||
## Limitations
|
||||
|
||||
The model was trained on data that contains toxic language, unsafe content, and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.
|
||||
|
||||
## Ethical Considerations
|
||||
|
||||
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
|
||||
|
||||
Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
|
||||
|
||||
## References
|
||||
|
||||
* [Compact Language Models via Pruning and Knowledge Distillation](https://arxiv.org/abs/2407.14679)
|
||||
* [LLM Pruning and Distillation in Practice: The Minitron Approach](https://arxiv.org/abs/2408.11796)
|
||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"_name_or_path": "nvidia/Llama-3.1-Minitron-4B-Width-Base",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9216,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"transformers_version": "4.45.0.dev0"
|
||||
}
|
||||
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 sha256:585da9fc8ad7692fbf64a89148a424ab6c4907f1ed25881cf1e0b55070a9bff3
|
||||
size 4978354640
|
||||
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 sha256:5ec2029c584b3bef522e6f0d0027eff94c9b9db08d7fb543847b69abbe2dbe49
|
||||
size 4047172128
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 9025492992
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_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_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.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.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
3
nemo/llama-3.1-minitron-4b-width-base.nemo
Normal file
3
nemo/llama-3.1-minitron-4b-width-base.nemo
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:579c17bf2ac9672d85daaae74693e9fecbd15f79dcb3205d120b2f17d7fdbd8e
|
||||
size 9037537280
|
||||
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"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 sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
|
||||
size 9085657
|
||||
2061
tokenizer_config.json
Normal file
2061
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user