Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +10 -0
- LICENSE.txt +126 -0
- README.md +60 -0
- checkpoint/config.json +27 -0
- checkpoint/generation_config.json +10 -0
- checkpoint/pytorch_model.bin/key_to_filename.json +3 -0
- checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight +3 -0
- checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p114.model.layers.12.mlp.up_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p115.model.layers.12.mlp.down_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p116.model.layers.12.input_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p117.model.layers.12.post_attention_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p118.model.layers.13.self_attn.q_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p119.model.layers.13.self_attn.k_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p12.model.layers.1.self_attn.v_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p120.model.layers.13.self_attn.v_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p121.model.layers.13.self_attn.o_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p122.model.layers.13.mlp.gate_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p123.model.layers.13.mlp.up_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p124.model.layers.13.mlp.down_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p125.model.layers.13.input_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p126.model.layers.13.post_attention_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p127.model.layers.14.self_attn.q_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p128.model.layers.14.self_attn.k_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p129.model.layers.14.self_attn.v_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p13.model.layers.1.self_attn.o_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p130.model.layers.14.self_attn.o_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p131.model.layers.14.mlp.gate_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p132.model.layers.14.mlp.up_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p133.model.layers.14.mlp.down_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p134.model.layers.14.input_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p135.model.layers.14.post_attention_layernorm.weight +3 -0
- checkpoint/pytorch_model.bin/p136.model.layers.15.self_attn.q_proj.weight +3 -0
- checkpoint/pytorch_model.bin/p137.model.layers.15.self_attn.k_proj.weight +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
compiled/157da229375c206ab7ef.neff filter=lfs diff=lfs merge=lfs -text
|
37 |
+
compiled/1b51e03f5e884a90f2ef.neff filter=lfs diff=lfs merge=lfs -text
|
38 |
+
compiled/3114efb5a11fc402a894.neff filter=lfs diff=lfs merge=lfs -text
|
39 |
+
compiled/46114601e479a3ab86d5.neff filter=lfs diff=lfs merge=lfs -text
|
40 |
+
compiled/7addf9d4ce2c4f32bcbc.neff filter=lfs diff=lfs merge=lfs -text
|
41 |
+
compiled/b7a3add84c081da2eb6d.neff filter=lfs diff=lfs merge=lfs -text
|
42 |
+
compiled/bde1bac5ad2a892268b0.neff filter=lfs diff=lfs merge=lfs -text
|
43 |
+
compiled/cd329e9e234371dd1be8.neff filter=lfs diff=lfs merge=lfs -text
|
44 |
+
compiled/cf14444e182904ed3fd6.neff filter=lfs diff=lfs merge=lfs -text
|
45 |
+
compiled/e85e95c0cd23bcd18b0e.neff filter=lfs diff=lfs merge=lfs -text
|
LICENSE.txt
ADDED
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
LLAMA 2 COMMUNITY LICENSE AGREEMENT
|
2 |
+
Llama 2 Version Release Date: July 18, 2023
|
3 |
+
|
4 |
+
"Agreement" means the terms and conditions for use, reproduction, distribution and
|
5 |
+
modification of the Llama Materials set forth herein.
|
6 |
+
|
7 |
+
"Documentation" means the specifications, manuals and documentation
|
8 |
+
accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
|
9 |
+
libraries/llama-downloads/.
|
10 |
+
|
11 |
+
"Licensee" or "you" means you, or your employer or any other person or entity (if
|
12 |
+
you are entering into this Agreement on such person or entity's behalf), of the age
|
13 |
+
required under applicable laws, rules or regulations to provide legal consent and that
|
14 |
+
has legal authority to bind your employer or such other person or entity if you are
|
15 |
+
entering in this Agreement on their behalf.
|
16 |
+
|
17 |
+
"Llama 2" means the foundational large language models and software and
|
18 |
+
algorithms, including machine-learning model code, trained model weights,
|
19 |
+
inference-enabling code, training-enabling code, fine-tuning enabling code and other
|
20 |
+
elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
|
21 |
+
libraries/llama-downloads/.
|
22 |
+
|
23 |
+
"Llama Materials" means, collectively, Meta's proprietary Llama 2 and
|
24 |
+
Documentation (and any portion thereof) made available under this Agreement.
|
25 |
+
|
26 |
+
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you
|
27 |
+
are an entity, your principal place of business is in the EEA or Switzerland) and Meta
|
28 |
+
Platforms, Inc. (if you are located outside of the EEA or Switzerland).
|
29 |
+
|
30 |
+
By clicking "I Accept" below or by using or distributing any portion or element of the
|
31 |
+
Llama Materials, you agree to be bound by this Agreement.
|
32 |
+
|
33 |
+
1. License Rights and Redistribution.
|
34 |
+
|
35 |
+
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
|
36 |
+
transferable and royalty-free limited license under Meta's intellectual property or
|
37 |
+
other rights owned by Meta embodied in the Llama Materials to use, reproduce,
|
38 |
+
distribute, copy, create derivative works of, and make modifications to the Llama
|
39 |
+
Materials.
|
40 |
+
|
41 |
+
b. Redistribution and Use.
|
42 |
+
|
43 |
+
i. If you distribute or make the Llama Materials, or any derivative works
|
44 |
+
thereof, available to a third party, you shall provide a copy of this Agreement to such
|
45 |
+
third party.
|
46 |
+
ii. If you receive Llama Materials, or any derivative works thereof, from
|
47 |
+
a Licensee as part of an integrated end user product, then Section 2 of this
|
48 |
+
Agreement will not apply to you.
|
49 |
+
|
50 |
+
iii. You must retain in all copies of the Llama Materials that you
|
51 |
+
distribute the following attribution notice within a "Notice" text file distributed as a
|
52 |
+
part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License,
|
53 |
+
Copyright (c) Meta Platforms, Inc. All Rights Reserved."
|
54 |
+
|
55 |
+
iv. Your use of the Llama Materials must comply with applicable laws
|
56 |
+
and regulations (including trade compliance laws and regulations) and adhere to the
|
57 |
+
Acceptable Use Policy for the Llama Materials (available at
|
58 |
+
https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into
|
59 |
+
this Agreement.
|
60 |
+
|
61 |
+
v. You will not use the Llama Materials or any output or results of the
|
62 |
+
Llama Materials to improve any other large language model (excluding Llama 2 or
|
63 |
+
derivative works thereof).
|
64 |
+
|
65 |
+
2. Additional Commercial Terms. If, on the Llama 2 version release date, the
|
66 |
+
monthly active users of the products or services made available by or for Licensee,
|
67 |
+
or Licensee's affiliates, is greater than 700 million monthly active users in the
|
68 |
+
preceding calendar month, you must request a license from Meta, which Meta may
|
69 |
+
grant to you in its sole discretion, and you are not authorized to exercise any of the
|
70 |
+
rights under this Agreement unless or until Meta otherwise expressly grants you
|
71 |
+
such rights.
|
72 |
+
|
73 |
+
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE
|
74 |
+
LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE
|
75 |
+
PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
|
76 |
+
EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY
|
77 |
+
WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR
|
78 |
+
FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
|
79 |
+
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING
|
80 |
+
THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
|
81 |
+
USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
|
82 |
+
|
83 |
+
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE
|
84 |
+
LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT,
|
85 |
+
NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS
|
86 |
+
AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL,
|
87 |
+
CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
|
88 |
+
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF
|
89 |
+
ANY OF THE FOREGOING.
|
90 |
+
|
91 |
+
5. Intellectual Property.
|
92 |
+
|
93 |
+
a. No trademark licenses are granted under this Agreement, and in
|
94 |
+
connection with the Llama Materials, neither Meta nor Licensee may use any name
|
95 |
+
or mark owned by or associated with the other or any of its affiliates, except as
|
96 |
+
required for reasonable and customary use in describing and redistributing the
|
97 |
+
Llama Materials.
|
98 |
+
|
99 |
+
b. Subject to Meta's ownership of Llama Materials and derivatives made by or
|
100 |
+
for Meta, with respect to any derivative works and modifications of the Llama
|
101 |
+
Materials that are made by you, as between you and Meta, you are and will be the
|
102 |
+
owner of such derivative works and modifications.
|
103 |
+
|
104 |
+
c. If you institute litigation or other proceedings against Meta or any entity
|
105 |
+
(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama
|
106 |
+
Materials or Llama 2 outputs or results, or any portion of any of the foregoing,
|
107 |
+
constitutes infringement of intellectual property or other rights owned or licensable
|
108 |
+
by you, then any licenses granted to you under this Agreement shall terminate as of
|
109 |
+
the date such litigation or claim is filed or instituted. You will indemnify and hold
|
110 |
+
harmless Meta from and against any claim by any third party arising out of or related
|
111 |
+
to your use or distribution of the Llama Materials.
|
112 |
+
|
113 |
+
6. Term and Termination. The term of this Agreement will commence upon your
|
114 |
+
acceptance of this Agreement or access to the Llama Materials and will continue in
|
115 |
+
full force and effect until terminated in accordance with the terms and conditions
|
116 |
+
herein. Meta may terminate this Agreement if you are in breach of any term or
|
117 |
+
condition of this Agreement. Upon termination of this Agreement, you shall delete
|
118 |
+
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the
|
119 |
+
termination of this Agreement.
|
120 |
+
|
121 |
+
7. Governing Law and Jurisdiction. This Agreement will be governed and
|
122 |
+
construed under the laws of the State of California without regard to choice of law
|
123 |
+
principles, and the UN Convention on Contracts for the International Sale of Goods
|
124 |
+
does not apply to this Agreement. The courts of California shall have exclusive
|
125 |
+
jurisdiction of any dispute arising out of this Agreement.
|
126 |
+
|
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
inference: false
|
6 |
+
tags:
|
7 |
+
- facebook
|
8 |
+
- meta
|
9 |
+
- pytorch
|
10 |
+
- llama
|
11 |
+
- llama-2
|
12 |
+
- inferentia2
|
13 |
+
- neuron
|
14 |
+
---
|
15 |
+
# Neuronx model for [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)
|
16 |
+
|
17 |
+
This repository contains [**AWS Inferentia2**](https://aws.amazon.com/ec2/instance-types/inf2/) and [`neuronx`](https://awsdocs-neuron.readthedocs-hosted.com/en/latest/) compatible checkpoints for [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf).
|
18 |
+
You can find detailed information about the base model on its [Model Card](https://huggingface.co/meta-llama/Llama-2-7b-hf).
|
19 |
+
|
20 |
+
This model has been exported to the `neuron` format using specific `input_shapes` and `compiler` parameters detailed in the paragraphs below.
|
21 |
+
|
22 |
+
Please refer to the 🤗 `optimum-neuron` [documentation](https://huggingface.co/docs/optimum-neuron/main/en/guides/models#configuring-the-export-of-a-generative-model) for an explanation of these parameters.
|
23 |
+
|
24 |
+
## Usage on Amazon SageMaker
|
25 |
+
|
26 |
+
_coming soon_
|
27 |
+
|
28 |
+
## Usage with 🤗 `optimum-neuron`
|
29 |
+
|
30 |
+
```python
|
31 |
+
>>> from optimum.neuron import pipeline
|
32 |
+
|
33 |
+
>>> p = pipeline('text-generation', 'aws-neuron/Llama-2-7b-hf-neuron-latency')
|
34 |
+
>>> p("My favorite place on earth is", max_new_tokens=64, do_sample=True, top_k=50)
|
35 |
+
[{'generated_text': 'My favorite place on earth is the ocean. It is where I feel most
|
36 |
+
at peace. I love to travel and see new places. I have a'}]
|
37 |
+
```
|
38 |
+
|
39 |
+
This repository contains tags specific to versions of `neuronx`. When using with 🤗 `optimum-neuron`, use the repo revision specific to the version of `neuronx` you are using, to load the right serialized checkpoints.
|
40 |
+
|
41 |
+
## Arguments passed during export
|
42 |
+
|
43 |
+
**input_shapes**
|
44 |
+
|
45 |
+
```json
|
46 |
+
{
|
47 |
+
"batch_size": 1,
|
48 |
+
"sequence_length": 2048,
|
49 |
+
}
|
50 |
+
```
|
51 |
+
|
52 |
+
**compiler_args**
|
53 |
+
|
54 |
+
```json
|
55 |
+
{
|
56 |
+
"auto_cast_type": "fp16",
|
57 |
+
"num_cores": 24,
|
58 |
+
}
|
59 |
+
```
|
60 |
+
|
checkpoint/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-2-7b-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 11008,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 32,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.34.1",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
checkpoint/generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.6,
|
8 |
+
"top_p": 0.9,
|
9 |
+
"transformers_version": "4.34.1"
|
10 |
+
}
|
checkpoint/pytorch_model.bin/key_to_filename.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:825d20f4a18183eff3963e805edd13ef7eb35b0aff7a850e8153ca1eeeb37970
|
3 |
+
size 26397
|
checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da5c4acb278381b1fc040ff34ca7cdfa8264895cfad4fee5c90436c423a8f459
|
3 |
+
size 524288789
|
checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e4486401b9f7b27193d310385d3468fdd234936513b93a4d2e9662d745b9b74
|
3 |
+
size 67109756
|
checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43a22f8644d0a6940f854aaf7882e60579972973c97575f7e25622f97280f977
|
3 |
+
size 67109759
|
checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de5c80fae90ca3476520a485c29d07121eb270e0534cb2c9ce08f4aa764e90fd
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c7b3eefbb663e184e8ee804ea11b02ac98f29a30abdf361eab46e4da7983a00
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b58bd301b57fc9e3c23375ed119c0ceecd9962e1aa714cea3722885e08c9d6a
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ed98fdbfda7fc25acc4f80728f69e7cc647477ed659009d9339a16fd780bd34
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75b7a49d0bb826f91c9547c1494367d5273678c2d221de9080ccec9ba1befc56
|
3 |
+
size 180355964
|
checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a54b7365baf60a919654b1f2f4feb8991a700459769a779c95094018a08c5291
|
3 |
+
size 180355958
|
checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c079b1f4963c658c0dd95c54ab6f31e55e95cb40b0242465cd78388631c6302
|
3 |
+
size 180355964
|
checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08b697c974c581a4b64024f0dfa328941f597fa5b93312fff8dbe2140988b6f1
|
3 |
+
size 17282
|
checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:440dd212bb2e67c2ff83a2d42135f13589a04f622f41d523c241941e008ec1b8
|
3 |
+
size 17309
|
checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3046b38eb5f0dbd87c7c9cc320dfc3374311930d38ee43a03169c61a8b6eb19f
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4afe803e9188698fe5b29e551e418da34e536dd5fc42d53f2d4d02acb06780a0
|
3 |
+
size 67109759
|
checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b3ef1f510bd1955a076e2bbc7c509f1f28479bcf17755469e2ad201c70362cb
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5dc6f96ead6b19d38d2bf5fdcb98dbc2baa34487ffb416029ad6bed9d37baf0
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46267dfe1859f8a4fd450e43523fb9603c849162eb53a5f72445daec88730607
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d874134d19b3a5e0c28b4cb14a5c6ce416592cc0b280d22e6893c178f0bc4890
|
3 |
+
size 180355964
|
checkpoint/pytorch_model.bin/p114.model.layers.12.mlp.up_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c6dbe94e47a28ab08e80a8069e06d9a6f31e16306ea138a356e90f90ff0139e
|
3 |
+
size 180355958
|
checkpoint/pytorch_model.bin/p115.model.layers.12.mlp.down_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5afc26b5261f3c992c3a9e9b84cf42d9e5e6365c6d0dfb2a0397f52fdcf611ab
|
3 |
+
size 180355964
|
checkpoint/pytorch_model.bin/p116.model.layers.12.input_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af688ecb35a5f33863c2ea72f697027bc01e19ae891d13c878a9bb077aef9eaf
|
3 |
+
size 17282
|
checkpoint/pytorch_model.bin/p117.model.layers.12.post_attention_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f42abe22e1afc5696515dfb5e91d0541aaf789bb8777d5f47c48726f7425c326
|
3 |
+
size 17309
|
checkpoint/pytorch_model.bin/p118.model.layers.13.self_attn.q_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d57fbe0a4df894dbd3f98e744ad1775a43693b4ce7992991616576f66af86964
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p119.model.layers.13.self_attn.k_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7e1fb093b541409c38ec658f77bf301eba121873d557d8037b569a2a82b947c
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p12.model.layers.1.self_attn.v_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c67935134cf42385cfc6ee23d9c41f3e0e146cf620fdfbfb7d61993332867779
|
3 |
+
size 67109759
|
checkpoint/pytorch_model.bin/p120.model.layers.13.self_attn.v_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7762b921206e6b9548e584537cd2634724d909ed2d73ed5a0342344a698d8528
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p121.model.layers.13.self_attn.o_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28120f754e95324e127cca63a761d124d834fd56cced2fd38d27e15ce7e4691b
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p122.model.layers.13.mlp.gate_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60f749c15d65ba3b6456e058611e0fd0dbcfce4d38041d814e0b778bb8a74593
|
3 |
+
size 180355964
|
checkpoint/pytorch_model.bin/p123.model.layers.13.mlp.up_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ef1b6504ed2fb7f3d0b515a3ae3fb06e59fd2a2c92f107c89b8727e74dc9bcc
|
3 |
+
size 180355958
|
checkpoint/pytorch_model.bin/p124.model.layers.13.mlp.down_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bd51d04347f173637b730826633a263f1b25370bd446a1ff34c8f03c7c51e79
|
3 |
+
size 180355964
|
checkpoint/pytorch_model.bin/p125.model.layers.13.input_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d96cfb55f2a0edd518209aed60673eb2cdbd5e6aee6c8cb51ef3ec618ff15bc
|
3 |
+
size 17282
|
checkpoint/pytorch_model.bin/p126.model.layers.13.post_attention_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14703c6f0d6c692a048a16ec17d3bd5bb8e925dc6024558931041df48fa6d46c
|
3 |
+
size 17309
|
checkpoint/pytorch_model.bin/p127.model.layers.14.self_attn.q_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75fc137e6fac484eb99a764320706ab7de62b162e12a40e4af706f33a916c2e0
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p128.model.layers.14.self_attn.k_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:963cc6b708a5b9beb5c7648797394e8897e5bb7f3502602563e33fdb4731c5bd
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p129.model.layers.14.self_attn.v_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f156177fd8262b098c5f477bbeaa1137933ea23062c87c9d7b6f5e531fbbbb5f
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p13.model.layers.1.self_attn.o_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b774652267c782b295972d3ad5a80cd9b8726460798c63b155cbbed629d5ee95
|
3 |
+
size 67109759
|
checkpoint/pytorch_model.bin/p130.model.layers.14.self_attn.o_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12cec480791ecd87866ee79de6b6929135451fb948a6eaea47b52e21c5168e16
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p131.model.layers.14.mlp.gate_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8ae779c065179df5c262ef305c227ef4d8fbe4ea8fa673e18955e3d09c40bae
|
3 |
+
size 180355964
|
checkpoint/pytorch_model.bin/p132.model.layers.14.mlp.up_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6e4498fb9eb95f190b8304c5e57acf6a4a8f1aa44b4adbbbed14eda5dc6fe83
|
3 |
+
size 180355958
|
checkpoint/pytorch_model.bin/p133.model.layers.14.mlp.down_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5a2321a7081de7f76b053a22b5fcd1fdb854e5fbb15d298a8e2fd48b02c7abc
|
3 |
+
size 180355964
|
checkpoint/pytorch_model.bin/p134.model.layers.14.input_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37f5642ad300b1225a3f0f195317d674cc8b3a443b2145b39abc912b3e8f7e60
|
3 |
+
size 17282
|
checkpoint/pytorch_model.bin/p135.model.layers.14.post_attention_layernorm.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b7ed46e4eafb9182394036bdc4980359ca7770a8fd7d739eedf232ecd89de23
|
3 |
+
size 17309
|
checkpoint/pytorch_model.bin/p136.model.layers.15.self_attn.q_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b8645153a8338589fafb0d6143e5b57d56d4298a424123c4c212e488b28b803
|
3 |
+
size 67109765
|
checkpoint/pytorch_model.bin/p137.model.layers.15.self_attn.k_proj.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08ff0b29c8f6b08fe3a14ac6f08deee7a28c195afa9ddd05cecbba506875cf91
|
3 |
+
size 67109765
|