Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +204 -0
- config.json +85 -0
- model-00001-of-00023.safetensors +3 -0
- model-00002-of-00023.safetensors +3 -0
- model-00003-of-00023.safetensors +3 -0
- model-00004-of-00023.safetensors +3 -0
- model-00005-of-00023.safetensors +3 -0
- model-00006-of-00023.safetensors +3 -0
- model-00007-of-00023.safetensors +3 -0
- model-00008-of-00023.safetensors +3 -0
- model-00009-of-00023.safetensors +3 -0
- model-00010-of-00023.safetensors +3 -0
- model-00011-of-00023.safetensors +3 -0
- model-00012-of-00023.safetensors +3 -0
- model-00013-of-00023.safetensors +3 -0
- model-00014-of-00023.safetensors +3 -0
- model-00015-of-00023.safetensors +3 -0
- model-00016-of-00023.safetensors +3 -0
- model-00017-of-00023.safetensors +3 -0
- model-00018-of-00023.safetensors +3 -0
- model-00019-of-00023.safetensors +3 -0
- model-00020-of-00023.safetensors +3 -0
- model-00021-of-00023.safetensors +3 -0
- model-00022-of-00023.safetensors +3 -0
- model-00023-of-00023.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: mlx
|
| 3 |
+
language:
|
| 4 |
+
- ar
|
| 5 |
+
- de
|
| 6 |
+
- en
|
| 7 |
+
- es
|
| 8 |
+
- fr
|
| 9 |
+
- hi
|
| 10 |
+
- id
|
| 11 |
+
- it
|
| 12 |
+
- pt
|
| 13 |
+
- th
|
| 14 |
+
- tl
|
| 15 |
+
- vi
|
| 16 |
+
tags:
|
| 17 |
+
- facebook
|
| 18 |
+
- meta
|
| 19 |
+
- pytorch
|
| 20 |
+
- llama
|
| 21 |
+
- llama-4
|
| 22 |
+
- mlx
|
| 23 |
+
extra_gated_prompt: '**LLAMA 4 COMMUNITY LICENSE AGREEMENT**
|
| 24 |
+
|
| 25 |
+
Llama 4 Version Effective Date: April 5, 2025
|
| 26 |
+
|
| 27 |
+
"**Agreement**" means the terms and conditions for use, reproduction, distribution
|
| 28 |
+
and modification of the Llama Materials set forth herein.
|
| 29 |
+
|
| 30 |
+
"**Documentation**" means the specifications, manuals and documentation accompanying
|
| 31 |
+
Llama 4 distributed by Meta at [https://www.llama.com/docs/overview](https://llama.com/docs/overview).
|
| 32 |
+
|
| 33 |
+
"**Licensee**" or "**you**" means you, or your employer or any other person or entity
|
| 34 |
+
(if you are entering into this Agreement on such person or entity’s behalf), of
|
| 35 |
+
the age required under applicable laws, rules or regulations to provide legal consent
|
| 36 |
+
and that has legal authority to bind your employer or such other person or entity
|
| 37 |
+
if you are entering in this Agreement on their behalf.
|
| 38 |
+
|
| 39 |
+
"**Llama 4**" means the foundational large language models and software and algorithms,
|
| 40 |
+
including machine-learning model code, trained model weights, inference-enabling
|
| 41 |
+
code, training-enabling code, fine-tuning enabling code and other elements of the
|
| 42 |
+
foregoing distributed by Meta at [https://www.llama.com/llama-downloads](https://www.llama.com/llama-downloads).
|
| 43 |
+
|
| 44 |
+
"**Llama Materials**" means, collectively, Meta’s proprietary Llama 4 and Documentation
|
| 45 |
+
(and any portion thereof) made available under this Agreement.
|
| 46 |
+
|
| 47 |
+
"**Meta**" or "**we**" means Meta Platforms Ireland Limited (if you are located
|
| 48 |
+
in or, if you are an entity, your principal place of business is in the EEA or Switzerland)
|
| 49 |
+
and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
|
| 50 |
+
|
| 51 |
+
By clicking "I Accept" below or by using or distributing any portion or element
|
| 52 |
+
of the Llama Materials, you agree to be bound by this Agreement.
|
| 53 |
+
|
| 54 |
+
1\. **License Rights and Redistribution**.
|
| 55 |
+
|
| 56 |
+
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable
|
| 57 |
+
and royalty-free limited license under Meta’s intellectual property or other rights
|
| 58 |
+
owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy,
|
| 59 |
+
create derivative works of, and make modifications to the Llama Materials.
|
| 60 |
+
|
| 61 |
+
b. Redistribution and Use.
|
| 62 |
+
|
| 63 |
+
i. If you distribute or make available the Llama Materials (or any derivative works
|
| 64 |
+
thereof), or a product or service (including another AI model) that contains any
|
| 65 |
+
of them, you shall (A) provide a copy of this Agreement with any such Llama Materials;
|
| 66 |
+
and (B) prominently display "Built with Llama" on a related website, user interface,
|
| 67 |
+
blogpost, about page, or product documentation. If you use the Llama Materials or
|
| 68 |
+
any outputs or results of the Llama Materials to create, train, fine tune, or otherwise
|
| 69 |
+
improve an AI model, which is distributed or made available, you shall also include
|
| 70 |
+
"Llama" at the beginning of any such AI model name.
|
| 71 |
+
|
| 72 |
+
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee
|
| 73 |
+
as part of an integrated end user product, then Section 2 of this Agreement will
|
| 74 |
+
not apply to you.
|
| 75 |
+
|
| 76 |
+
iii. You must retain in all copies of the Llama Materials that you distribute the
|
| 77 |
+
following attribution notice within a "Notice" text file distributed as a part of
|
| 78 |
+
such copies: "Llama 4 is licensed under the Llama 4 Community License, Copyright
|
| 79 |
+
© Meta Platforms, Inc. All Rights Reserved."
|
| 80 |
+
|
| 81 |
+
iv. Your use of the Llama Materials must comply with applicable laws and regulations
|
| 82 |
+
(including trade compliance laws and regulations) and adhere to the Acceptable Use
|
| 83 |
+
Policy for the Llama Materials (available at [https://www.llama.com/llama4/use-policy](https://www.llama.com/llama4/use-policy)),
|
| 84 |
+
which is hereby incorporated by reference into this Agreement. 2\. **Additional
|
| 85 |
+
Commercial Terms**. If, on the Llama 4 version release date, the monthly active
|
| 86 |
+
users of the products or services made available by or for Licensee, or Licensee’s
|
| 87 |
+
affiliates, is greater than 700 million monthly active users in the preceding calendar
|
| 88 |
+
month, you must request a license from Meta, which Meta may grant to you in its
|
| 89 |
+
sole discretion, and you are not authorized to exercise any of the rights under
|
| 90 |
+
this Agreement unless or until Meta otherwise expressly grants you such rights.
|
| 91 |
+
|
| 92 |
+
3**. Disclaimer of Warranty**. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS
|
| 93 |
+
AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES
|
| 94 |
+
OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
|
| 95 |
+
INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,
|
| 96 |
+
OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING
|
| 97 |
+
THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY
|
| 98 |
+
RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
|
| 99 |
+
|
| 100 |
+
4\. **Limitation of Liability**. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE
|
| 101 |
+
UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,
|
| 102 |
+
OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,
|
| 103 |
+
SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META
|
| 104 |
+
OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
|
| 105 |
+
|
| 106 |
+
5\. **Intellectual Property**.
|
| 107 |
+
|
| 108 |
+
a. No trademark licenses are granted under this Agreement, and in connection with
|
| 109 |
+
the Llama Materials, neither Meta nor Licensee may use any name or mark owned by
|
| 110 |
+
or associated with the other or any of its affiliates, except as required for reasonable
|
| 111 |
+
and customary use in describing and redistributing the Llama Materials or as set
|
| 112 |
+
forth in this Section 5(a). Meta hereby grants you a license to use "Llama" (the
|
| 113 |
+
"Mark") solely as required to comply with the last sentence of Section 1.b.i. You
|
| 114 |
+
will comply with Meta’s brand guidelines (currently accessible at [https://about.meta.com/brand/resources/meta/company-brand/](https://about.meta.com/brand/resources/meta/company-brand/)[)](https://en.facebookbrand.com/).
|
| 115 |
+
All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
|
| 116 |
+
|
| 117 |
+
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for
|
| 118 |
+
Meta, with respect to any derivative works and modifications of the Llama Materials
|
| 119 |
+
that are made by you, as between you and Meta, you are and will be the owner of
|
| 120 |
+
such derivative works and modifications.
|
| 121 |
+
|
| 122 |
+
c. If you institute litigation or other proceedings against Meta or any entity (including
|
| 123 |
+
a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or
|
| 124 |
+
Llama 4 outputs or results, or any portion of any of the foregoing, constitutes
|
| 125 |
+
infringement of intellectual property or other rights owned or licensable by you,
|
| 126 |
+
then any licenses granted to you under this Agreement shall terminate as of the
|
| 127 |
+
date such litigation or claim is filed or instituted. You will indemnify and hold
|
| 128 |
+
harmless Meta from and against any claim by any third party arising out of or related
|
| 129 |
+
to your use or distribution of the Llama Materials.
|
| 130 |
+
|
| 131 |
+
6\. **Term and Termination**. The term of this Agreement will commence upon your
|
| 132 |
+
acceptance of this Agreement or access to the Llama Materials and will continue
|
| 133 |
+
in full force and effect until terminated in accordance with the terms and conditions
|
| 134 |
+
herein. Meta may terminate this Agreement if you are in breach of any term or condition
|
| 135 |
+
of this Agreement. Upon termination of this Agreement, you shall delete and cease
|
| 136 |
+
use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of
|
| 137 |
+
this Agreement.
|
| 138 |
+
|
| 139 |
+
7\. **Governing Law and Jurisdiction**. This Agreement will be governed and construed
|
| 140 |
+
under the laws of the State of California without regard to choice of law principles,
|
| 141 |
+
and the UN Convention on Contracts for the International Sale of Goods does not
|
| 142 |
+
apply to this Agreement. The courts of California shall have exclusive jurisdiction
|
| 143 |
+
of any dispute arising out of this Agreement.'
|
| 144 |
+
extra_gated_fields:
|
| 145 |
+
First Name: text
|
| 146 |
+
Last Name: text
|
| 147 |
+
Date of birth: date_picker
|
| 148 |
+
Country: country
|
| 149 |
+
Affiliation: text
|
| 150 |
+
Job title:
|
| 151 |
+
type: select
|
| 152 |
+
options:
|
| 153 |
+
- Student
|
| 154 |
+
- Research Graduate
|
| 155 |
+
- AI researcher
|
| 156 |
+
- AI developer/engineer
|
| 157 |
+
- Reporter
|
| 158 |
+
- Other
|
| 159 |
+
geo: ip_location
|
| 160 |
+
? By clicking Submit below I accept the terms of the license and acknowledge that
|
| 161 |
+
the information I provide will be collected stored processed and shared in accordance
|
| 162 |
+
with the Meta Privacy Policy
|
| 163 |
+
: checkbox
|
| 164 |
+
extra_gated_description: The information you provide will be collected, stored, processed
|
| 165 |
+
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
|
| 166 |
+
extra_gated_button_content: Submit
|
| 167 |
+
extra_gated_heading: Please be sure to provide your full legal name, date of birth,
|
| 168 |
+
and full organization name with all corporate identifiers. Avoid the use of acronyms
|
| 169 |
+
and special characters. Failure to follow these instructions may prevent you from
|
| 170 |
+
accessing this model and others on Hugging Face. You will not have the ability to
|
| 171 |
+
edit this form after submission, so please ensure all information is accurate.
|
| 172 |
+
license: other
|
| 173 |
+
license_name: llama4
|
| 174 |
+
base_model: meta-llama/Llama-4-Scout-17B-16E
|
| 175 |
+
pipeline_tag: text-generation
|
| 176 |
+
---
|
| 177 |
+
|
| 178 |
+
# mlx-community/meta-llama-Llama-4-Scout-17B-16E-8bit
|
| 179 |
+
|
| 180 |
+
This model [mlx-community/meta-llama-Llama-4-Scout-17B-16E-8bit](https://huggingface.co/mlx-community/meta-llama-Llama-4-Scout-17B-16E-8bit) was
|
| 181 |
+
converted to MLX format from [meta-llama/Llama-4-Scout-17B-16E](https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E)
|
| 182 |
+
using mlx-lm version **0.22.3**.
|
| 183 |
+
|
| 184 |
+
## Use with mlx
|
| 185 |
+
|
| 186 |
+
```bash
|
| 187 |
+
pip install mlx-lm
|
| 188 |
+
```
|
| 189 |
+
|
| 190 |
+
```python
|
| 191 |
+
from mlx_lm import load, generate
|
| 192 |
+
|
| 193 |
+
model, tokenizer = load("mlx-community/meta-llama-Llama-4-Scout-17B-16E-8bit")
|
| 194 |
+
|
| 195 |
+
prompt = "hello"
|
| 196 |
+
|
| 197 |
+
if tokenizer.chat_template is not None:
|
| 198 |
+
messages = [{"role": "user", "content": prompt}]
|
| 199 |
+
prompt = tokenizer.apply_chat_template(
|
| 200 |
+
messages, add_generation_prompt=True
|
| 201 |
+
)
|
| 202 |
+
|
| 203 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 204 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Llama4ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 200080,
|
| 6 |
+
"eoi_token_index": 200081,
|
| 7 |
+
"image_token_index": 200092,
|
| 8 |
+
"model_type": "llama4",
|
| 9 |
+
"quantization": {
|
| 10 |
+
"group_size": 64,
|
| 11 |
+
"bits": 8
|
| 12 |
+
},
|
| 13 |
+
"quantization_config": {
|
| 14 |
+
"group_size": 64,
|
| 15 |
+
"bits": 8
|
| 16 |
+
},
|
| 17 |
+
"text_config": {
|
| 18 |
+
"attention_bias": false,
|
| 19 |
+
"attention_chunk_size": 8192,
|
| 20 |
+
"attention_dropout": 0.0,
|
| 21 |
+
"bos_token_id": 200000,
|
| 22 |
+
"eos_token_id": [
|
| 23 |
+
200001,
|
| 24 |
+
200007,
|
| 25 |
+
200008
|
| 26 |
+
],
|
| 27 |
+
"for_llm_compressor": false,
|
| 28 |
+
"head_dim": 128,
|
| 29 |
+
"hidden_act": "silu",
|
| 30 |
+
"hidden_size": 5120,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"interleave_moe_layer_step": 1,
|
| 33 |
+
"intermediate_size": 8192,
|
| 34 |
+
"intermediate_size_mlp": 16384,
|
| 35 |
+
"max_position_embeddings": 262144,
|
| 36 |
+
"model_type": "llama4_text",
|
| 37 |
+
"no_rope_layers": [],
|
| 38 |
+
"num_attention_heads": 40,
|
| 39 |
+
"num_experts_per_tok": 1,
|
| 40 |
+
"num_hidden_layers": 48,
|
| 41 |
+
"num_key_value_heads": 8,
|
| 42 |
+
"num_local_experts": 16,
|
| 43 |
+
"output_router_logits": false,
|
| 44 |
+
"pad_token_id": 200018,
|
| 45 |
+
"rms_norm_eps": 1e-05,
|
| 46 |
+
"rope_scaling": {
|
| 47 |
+
"factor": 8.0,
|
| 48 |
+
"high_freq_factor": 4.0,
|
| 49 |
+
"low_freq_factor": 1.0,
|
| 50 |
+
"original_max_position_embeddings": 8192,
|
| 51 |
+
"rope_type": "llama3"
|
| 52 |
+
},
|
| 53 |
+
"rope_theta": 500000.0,
|
| 54 |
+
"router_aux_loss_coef": 0.001,
|
| 55 |
+
"router_jitter_noise": 0.0,
|
| 56 |
+
"torch_dtype": "bfloat16",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"use_qk_norm": true,
|
| 59 |
+
"vocab_size": 202048
|
| 60 |
+
},
|
| 61 |
+
"transformers_version": "4.51.0.dev0",
|
| 62 |
+
"vision_config": {
|
| 63 |
+
"attention_dropout": 0.0,
|
| 64 |
+
"hidden_act": "gelu",
|
| 65 |
+
"hidden_size": 1408,
|
| 66 |
+
"image_size": 336,
|
| 67 |
+
"initializer_range": 0.02,
|
| 68 |
+
"intermediate_size": 5632,
|
| 69 |
+
"model_type": "llama4_vision_model",
|
| 70 |
+
"multi_modal_projector_bias": false,
|
| 71 |
+
"norm_eps": 1e-05,
|
| 72 |
+
"num_attention_heads": 16,
|
| 73 |
+
"num_channels": 3,
|
| 74 |
+
"num_hidden_layers": 34,
|
| 75 |
+
"patch_size": 14,
|
| 76 |
+
"pixel_shuffle_ratio": 0.5,
|
| 77 |
+
"projector_dropout": 0.0,
|
| 78 |
+
"projector_input_dim": 4096,
|
| 79 |
+
"projector_output_dim": 4096,
|
| 80 |
+
"rope_theta": 10000,
|
| 81 |
+
"vision_feature_layer": -1,
|
| 82 |
+
"vision_feature_select_strategy": "default",
|
| 83 |
+
"vision_output_dim": 4096
|
| 84 |
+
}
|
| 85 |
+
}
|
model-00001-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7957a7eea5278001c054b9b10f21d66402634ccc1ff6aae2eea4068781c84d2
|
| 3 |
+
size 4931801590
|
model-00002-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0655fcf15b035e6d68fa8f344e1446004bd2c6e75f4ff51f07016fc2fe904216
|
| 3 |
+
size 5350583948
|
model-00003-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:436acee90c15e7a1ba662edb5598c3a527f3d575301543f9ab50dedaf5978e60
|
| 3 |
+
size 4922089698
|
model-00004-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43b7230b0daa52bd0dcc41e12ac3fdd3c04be63d7e1f461c008fca723d3b5a98
|
| 3 |
+
size 5350583958
|
model-00005-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a91970ec13f8883a3c8aa2a7953d73387fcdd6a6a08e92a7866cc7d76d07b0d0
|
| 3 |
+
size 4721438501
|
model-00006-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2fab2113283420863c96dcc7e18b02955742ddc6013be4b8bc8ca973c8d2bf5
|
| 3 |
+
size 5350584015
|
model-00007-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39a3ab3909c1fe69670589d54ac58c0d011ed38be31e0707025728c5ec08332d
|
| 3 |
+
size 4721438580
|
model-00008-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2eed72a138c8655faaae6d95422aac2f662589a1c426d781069c9145b0da92ef
|
| 3 |
+
size 5350584057
|
model-00009-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baf07304eb9559dded61e078153c8580c9a0f4e8f6c9866a43cfa97dca656aa8
|
| 3 |
+
size 4922089776
|
model-00010-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94cfc18bcc0dc0224ab352b8814fcfddee148f27dedb81f0d344533ef49c75d9
|
| 3 |
+
size 5350584035
|
model-00011-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41e0f8b4d973270ad032648a20a36d1df4c49f23f7908d8ebc074855c2201790
|
| 3 |
+
size 4721438530
|
model-00012-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af57afeda9818c288df3aa4af5e5efc2289f9531ca74077094d2d38d435c384a
|
| 3 |
+
size 5350584059
|
model-00013-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c34d2541aec5abbf34334bab927e89d1a6c545a3afb0fb78c12c4f5e5579b2d
|
| 3 |
+
size 4721438582
|
model-00014-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:578adf130c292580e4e8ecd2595f4dd924236cce1eac048fde736ae2a4ceceef
|
| 3 |
+
size 5350584061
|
model-00015-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99bc02fa71808ad169c82489ebf803bb828d02e10f3120a8774b21561ffad48f
|
| 3 |
+
size 4922089744
|
model-00016-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99fc943c650be698564db49dbb5c311852572634447abdc97e459819a35e9f6c
|
| 3 |
+
size 5350584025
|
model-00017-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6d9011620134a1b1ee5df4233c78b4fd98a06fd285c74abd9b06e00531b8120
|
| 3 |
+
size 4721438558
|
model-00018-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ad06a0e8ec65a2e804d1acd5ec957cd73eb9faaa261670c7506be76b2cba1b5
|
| 3 |
+
size 5350583983
|
model-00019-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92bf7a089e609c1bd48b9efc7814e57767676970541a39d6381dfe5104f024b4
|
| 3 |
+
size 4721438554
|
model-00020-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d1516e8f311d87ad205695e7cfce1a49b3272ff054b7882c0c07268084711d4
|
| 3 |
+
size 5350584051
|
model-00021-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c63c5e8dba009ed85b2ef73279f6ef6f33e288a1d8c55643fbe92660373efc2
|
| 3 |
+
size 4922089766
|
model-00022-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:933636a0f53edbdbf0cad88d19b838ebb8a73582bba62f4cc4edb6bf602573e3
|
| 3 |
+
size 5350583971
|
model-00023-of-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b1b5fe8ea9e0a2ac14c861e8c567c8338006caca2e9c5fa230ade8ba1fed234
|
| 3 |
+
size 2700962360
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|finetune_right_pad_id|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:172c9eb4beafc72601690da3ccfcede5c2e6806a8d5ec1fca33e22acea8023a4
|
| 3 |
+
size 27948578
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|