Upload README.md with huggingface_hub

#1
.gitattributes CHANGED
@@ -33,4 +33,3 @@ 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
36
- tokenizer.json 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
 
COMPANY.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # RaxCore
2
+
3
+ **A leading developer company in Africa and beyond**
4
+
5
+ 🌐 **Website**: [www.raxcore.dev](https://www.raxcore.dev/)
6
+ 🤗 **Hugging Face**: [raxcore-dev](https://huggingface.co/raxcore-dev)
7
+
8
+ RaxCore is at the forefront of AI and software development, creating innovative solutions that bridge technology gaps across Africa and the global market.
9
+
10
+ ## About RaxCore
11
+
12
+ RaxCore specializes in:
13
+ - Advanced AI model development and fine-tuning
14
+ - Conversational AI systems
15
+ - Custom software solutions
16
+ - Technology consulting and implementation
17
+
18
+ ## Our Mission
19
+
20
+ To democratize access to cutting-edge AI technology while fostering innovation across Africa and beyond.
21
+
22
+ ## Rax 3.5 Chat
23
+
24
+ Rax 3.5 Chat represents RaxCore's commitment to developing high-quality, accessible AI models that serve diverse communities and use cases.
25
+
26
+ ---
27
+
28
+ **Contact RaxCore**
29
+ Visit [www.raxcore.dev](https://www.raxcore.dev/) for enterprise solutions, custom model development, and AI consulting services.
DEPLOYMENT.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Rax 3.5 Chat - Deployment Guide
2
+
3
+ ## Uploading to Hugging Face
4
+
5
+ ### Prerequisites
6
+ 1. Install required packages:
7
+ ```bash
8
+ pip install huggingface_hub transformers
9
+ ```
10
+
11
+ 2. Login to Hugging Face:
12
+ ```bash
13
+ huggingface-cli login
14
+ ```
15
+
16
+ ### Upload Steps
17
+
18
+ 1. **Initialize Git LFS** (if not already done):
19
+ ```bash
20
+ cd /home/ogega/Projects/models/rax-3.5-chat
21
+ git lfs install
22
+ ```
23
+
24
+ 2. **Add all files**:
25
+ ```bash
26
+ git add .
27
+ git commit -m "Initial commit: Rax 3.5 Chat model"
28
+ ```
29
+
30
+ 3. **Create repository on Hugging Face**:
31
+ - Go to https://huggingface.co/new
32
+ - Create a new model repository named "rax-3.5-chat" under raxcore-dev
33
+ - Choose "Public" or "Private" as needed
34
+
35
+ 4. **Push to Hugging Face**:
36
+ ```bash
37
+ git remote add origin https://huggingface.co/raxcore-dev/rax-3.5-chat
38
+ git branch -M main
39
+ git push -u origin main
40
+ ```
41
+
42
+ ### Alternative: Using huggingface_hub
43
+
44
+ ```python
45
+ from huggingface_hub import HfApi
46
+
47
+ api = HfApi()
48
+ api.upload_folder(
49
+ folder_path="/home/ogega/Projects/models/rax-3.5-chat",
50
+ repo_id="raxcore-dev/rax-3.5-chat",
51
+ repo_type="model"
52
+ )
53
+ ```
54
+
55
+ ## Model Testing
56
+
57
+ Run the included test script:
58
+ ```bash
59
+ cd /home/ogega/Projects/models/rax-3.5-chat
60
+ python test_rax.py
61
+ ```
62
+
63
+ ## Files Included
64
+
65
+ - `config.json` - Model configuration
66
+ - `tokenizer_config.json` - Tokenizer configuration
67
+ - `model.safetensors` - Model weights
68
+ - `tokenizer.json` - Tokenizer data
69
+ - `tokenizer.model` - SentencePiece model
70
+ - `generation_config.json` - Generation parameters
71
+ - `README.md` - Comprehensive documentation
72
+ - `model_card.md` - Hugging Face model card
73
+ - `test_rax.py` - Test script
74
+ - `.gitattributes` - Git LFS configuration
75
+
76
+ ## Ready for Release!
77
+
78
+ Your Rax 3.5 Chat model is now fully rebranded and ready for upload to Hugging Face.
LICENSE DELETED
@@ -1,202 +0,0 @@
1
-
2
- Apache License
3
- Version 2.0, January 2004
4
- http://www.apache.org/licenses/
5
-
6
- TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
-
8
- 1. Definitions.
9
-
10
- "License" shall mean the terms and conditions for use, reproduction,
11
- and distribution as defined by Sections 1 through 9 of this document.
12
-
13
- "Licensor" shall mean the copyright owner or entity authorized by
14
- the copyright owner that is granting the License.
15
-
16
- "Legal Entity" shall mean the union of the acting entity and all
17
- other entities that control, are controlled by, or are under common
18
- control with that entity. For the purposes of this definition,
19
- "control" means (i) the power, direct or indirect, to cause the
20
- direction or management of such entity, whether by contract or
21
- otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
- outstanding shares, or (iii) beneficial ownership of such entity.
23
-
24
- "You" (or "Your") shall mean an individual or Legal Entity
25
- exercising permissions granted by this License.
26
-
27
- "Source" form shall mean the preferred form for making modifications,
28
- including but not limited to software source code, documentation
29
- source, and configuration files.
30
-
31
- "Object" form shall mean any form resulting from mechanical
32
- transformation or translation of a Source form, including but
33
- not limited to compiled object code, generated documentation,
34
- and conversions to other media types.
35
-
36
- "Work" shall mean the work of authorship, whether in Source or
37
- Object form, made available under the License, as indicated by a
38
- copyright notice that is included in or attached to the work
39
- (an example is provided in the Appendix below).
40
-
41
- "Derivative Works" shall mean any work, whether in Source or Object
42
- form, that is based on (or derived from) the Work and for which the
43
- editorial revisions, annotations, elaborations, or other modifications
44
- represent, as a whole, an original work of authorship. For the purposes
45
- of this License, Derivative Works shall not include works that remain
46
- separable from, or merely link (or bind by name) to the interfaces of,
47
- the Work and Derivative Works thereof.
48
-
49
- "Contribution" shall mean any work of authorship, including
50
- the original version of the Work and any modifications or additions
51
- to that Work or Derivative Works thereof, that is intentionally
52
- submitted to Licensor for inclusion in the Work by the copyright owner
53
- or by an individual or Legal Entity authorized to submit on behalf of
54
- the copyright owner. For the purposes of this definition, "submitted"
55
- means any form of electronic, verbal, or written communication sent
56
- to the Licensor or its representatives, including but not limited to
57
- communication on electronic mailing lists, source code control systems,
58
- and issue tracking systems that are managed by, or on behalf of, the
59
- Licensor for the purpose of discussing and improving the Work, but
60
- excluding communication that is conspicuously marked or otherwise
61
- designated in writing by the copyright owner as "Not a Contribution."
62
-
63
- "Contributor" shall mean Licensor and any individual or Legal Entity
64
- on behalf of whom a Contribution has been received by Licensor and
65
- subsequently incorporated within the Work.
66
-
67
- 2. Grant of Copyright License. Subject to the terms and conditions of
68
- this License, each Contributor hereby grants to You a perpetual,
69
- worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
- copyright license to reproduce, prepare Derivative Works of,
71
- publicly display, publicly perform, sublicense, and distribute the
72
- Work and such Derivative Works in Source or Object form.
73
-
74
- 3. Grant of Patent License. Subject to the terms and conditions of
75
- this License, each Contributor hereby grants to You a perpetual,
76
- worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
- (except as stated in this section) patent license to make, have made,
78
- use, offer to sell, sell, import, and otherwise transfer the Work,
79
- where such license applies only to those patent claims licensable
80
- by such Contributor that are necessarily infringed by their
81
- Contribution(s) alone or by combination of their Contribution(s)
82
- with the Work to which such Contribution(s) was submitted. If You
83
- institute patent litigation against any entity (including a
84
- cross-claim or counterclaim in a lawsuit) alleging that the Work
85
- or a Contribution incorporated within the Work constitutes direct
86
- or contributory patent infringement, then any patent licenses
87
- granted to You under this License for that Work shall terminate
88
- as of the date such litigation is filed.
89
-
90
- 4. Redistribution. You may reproduce and distribute copies of the
91
- Work or Derivative Works thereof in any medium, with or without
92
- modifications, and in Source or Object form, provided that You
93
- meet the following conditions:
94
-
95
- (a) You must give any other recipients of the Work or
96
- Derivative Works a copy of this License; and
97
-
98
- (b) You must cause any modified files to carry prominent notices
99
- stating that You changed the files; and
100
-
101
- (c) You must retain, in the Source form of any Derivative Works
102
- that You distribute, all copyright, patent, trademark, and
103
- attribution notices from the Source form of the Work,
104
- excluding those notices that do not pertain to any part of
105
- the Derivative Works; and
106
-
107
- (d) If the Work includes a "NOTICE" text file as part of its
108
- distribution, then any Derivative Works that You distribute must
109
- include a readable copy of the attribution notices contained
110
- within such NOTICE file, excluding those notices that do not
111
- pertain to any part of the Derivative Works, in at least one
112
- of the following places: within a NOTICE text file distributed
113
- as part of the Derivative Works; within the Source form or
114
- documentation, if provided along with the Derivative Works; or,
115
- within a display generated by the Derivative Works, if and
116
- wherever such third-party notices normally appear. The contents
117
- of the NOTICE file are for informational purposes only and
118
- do not modify the License. You may add Your own attribution
119
- notices within Derivative Works that You distribute, alongside
120
- or as an addendum to the NOTICE text from the Work, provided
121
- that such additional attribution notices cannot be construed
122
- as modifying the License.
123
-
124
- You may add Your own copyright statement to Your modifications and
125
- may provide additional or different license terms and conditions
126
- for use, reproduction, or distribution of Your modifications, or
127
- for any such Derivative Works as a whole, provided Your use,
128
- reproduction, and distribution of the Work otherwise complies with
129
- the conditions stated in this License.
130
-
131
- 5. Submission of Contributions. Unless You explicitly state otherwise,
132
- any Contribution intentionally submitted for inclusion in the Work
133
- by You to the Licensor shall be under the terms and conditions of
134
- this License, without any additional terms or conditions.
135
- Notwithstanding the above, nothing herein shall supersede or modify
136
- the terms of any separate license agreement you may have executed
137
- with Licensor regarding such Contributions.
138
-
139
- 6. Trademarks. This License does not grant permission to use the trade
140
- names, trademarks, service marks, or product names of the Licensor,
141
- except as required for reasonable and customary use in describing the
142
- origin of the Work and reproducing the content of the NOTICE file.
143
-
144
- 7. Disclaimer of Warranty. Unless required by applicable law or
145
- agreed to in writing, Licensor provides the Work (and each
146
- Contributor provides its Contributions) on an "AS IS" BASIS,
147
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
- implied, including, without limitation, any warranties or conditions
149
- of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
- PARTICULAR PURPOSE. You are solely responsible for determining the
151
- appropriateness of using or redistributing the Work and assume any
152
- risks associated with Your exercise of permissions under this License.
153
-
154
- 8. Limitation of Liability. In no event and under no legal theory,
155
- whether in tort (including negligence), contract, or otherwise,
156
- unless required by applicable law (such as deliberate and grossly
157
- negligent acts) or agreed to in writing, shall any Contributor be
158
- liable to You for damages, including any direct, indirect, special,
159
- incidental, or consequential damages of any character arising as a
160
- result of this License or out of the use or inability to use the
161
- Work (including but not limited to damages for loss of goodwill,
162
- work stoppage, computer failure or malfunction, or any and all
163
- other commercial damages or losses), even if such Contributor
164
- has been advised of the possibility of such damages.
165
-
166
- 9. Accepting Warranty or Additional Liability. While redistributing
167
- the Work or Derivative Works thereof, You may choose to offer,
168
- and charge a fee for, acceptance of support, warranty, indemnity,
169
- or other liability obligations and/or rights consistent with this
170
- License. However, in accepting such obligations, You may act only
171
- on Your own behalf and on Your sole responsibility, not on behalf
172
- of any other Contributor, and only if You agree to indemnify,
173
- defend, and hold each Contributor harmless for any liability
174
- incurred by, or claims asserted against, such Contributor by reason
175
- of your accepting any such warranty or additional liability.
176
-
177
- END OF TERMS AND CONDITIONS
178
-
179
- APPENDIX: How to apply the Apache License to your work.
180
-
181
- To apply the Apache License to your work, attach the following
182
- boilerplate notice, with the fields enclosed by brackets "[]"
183
- replaced with your own identifying information. (Don't include
184
- the brackets!) The text should be enclosed in the appropriate
185
- comment syntax for the file format. We also recommend that a
186
- file or class name and description of purpose be included on the
187
- same "printed page" as the copyright notice for easier
188
- identification within third-party archives.
189
-
190
- Copyright 2026 Alibaba Cloud
191
-
192
- Licensed under the Apache License, Version 2.0 (the "License");
193
- you may not use this file except in compliance with the License.
194
- You may obtain a copy of the License at
195
-
196
- http://www.apache.org/licenses/LICENSE-2.0
197
-
198
- Unless required by applicable law or agreed to in writing, software
199
- distributed under the License is distributed on an "AS IS" BASIS,
200
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
- See the License for the specific language governing permissions and
202
- limitations under the License.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
README.md CHANGED
@@ -5,181 +5,105 @@ pipeline_tag: image-text-to-text
5
  tags:
6
  - multimodal
7
  - vision-language
8
- - vision
9
- - image-to-text
10
- - llm
11
- - vision-language-model
12
- - computer-vision
13
- - deep-learning
14
- - pytorch
15
- - transformers
16
- - vlm
17
- - 2b
18
- - efficient
19
- - production
20
- inference: true
21
  ---
22
 
23
- # Rax 4.5 - Efficient 2B Vision Language Model
24
 
25
- Rax 4.5 is a state-of-the-art 2 billion parameter multimodal vision-language model optimized for production use. Process images and text together with up to 262K token context length.
26
 
27
- ## Key Features
28
-
29
- - Fast & Efficient: Only 2B parameters for quick inference
30
- - Vision + Text: True multimodal understanding of images and language
31
- - Long Context: 262,144 token context window for complex tasks
32
- - Production Ready: Works with vLLM, SGLang, Transformers out of the box
33
- - Memory Efficient: Hybrid attention architecture reduces VRAM usage
34
-
35
- ## Model Specifications
36
-
37
- | Feature | Details |
38
- |---------|---------|
39
- | **Parameters** | ~2 Billion |
40
- | **Context Length** | 262,144 tokens |
41
- | **Input Types** | Text + Images |
42
- | **Architecture** | Hybrid Linear + Full Attention (24 layers) |
43
- | **Vision Encoder** | 24-layer ViT, 1024 hidden size |
44
- | **Text Hidden Size** | 2048 |
45
- | **Precision** | BFloat16 |
46
- | **License** | Apache 2.0 |
47
-
48
- ## Capabilities
49
 
50
- - Image Understanding: Analyze, describe, and answer questions about images
51
- - Visual Question Answering: Extract information from screenshots, documents, charts
52
- - Multimodal Reasoning: Combine visual and textual information for complex tasks
53
- - Long Context Processing: Handle extensive documents with visual elements
54
- - Production Deployment: Optimized for real-world applications
 
 
55
 
56
- ## Quick Start
57
 
58
- ### Installation
 
 
 
59
 
60
- \`\`\`bash
61
- pip install transformers pillow torch accelerate
62
- \`\`\`
63
 
64
- ### Basic Usage with Transformers
65
 
66
- \`\`\`python
67
  from transformers import AutoModelForVision2Seq, AutoProcessor
68
  from PIL import Image
69
 
70
- # Load model
71
- model = AutoModelForVision2Seq.from_pretrained(
72
- "raxcore-dev/rax-3.5-chat",
73
- trust_remote_code=True
74
- )
75
- processor = AutoProcessor.from_pretrained(
76
- "raxcore-dev/rax-3.5-chat",
77
- trust_remote_code=True
78
- )
79
 
80
- # Text generation
81
- messages = [{"role": "user", "content": "Explain quantum computing"}]
82
  text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
83
  inputs = processor(text=text, return_tensors="pt")
84
  outputs = model.generate(**inputs, max_new_tokens=512)
85
  print(processor.decode(outputs[0], skip_special_tokens=True))
86
 
87
- # Image analysis
88
- image = Image.open("photo.jpg")
89
- messages = [{
90
- "role": "user",
91
- "content": [
92
- {"type": "image"},
93
- {"type": "text", "text": "What's in this image? Be detailed."}
94
- ]
95
- }]
96
  text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
97
  inputs = processor(text=text, images=image, return_tensors="pt")
98
  outputs = model.generate(**inputs, max_new_tokens=512)
99
  print(processor.decode(outputs[0], skip_special_tokens=True))
100
- \`\`\`
101
 
102
- ### Deploy with vLLM
103
 
104
- \`\`\`bash
105
- vllm serve raxcore-dev/rax-3.5-chat --port 8000 --max-model-len 8192
106
- \`\`\`
107
 
108
- \`\`\`python
109
  from openai import OpenAI
110
-
111
  client = OpenAI(base_url="http://localhost:8000/v1", api_key="token")
112
 
113
  response = client.chat.completions.create(
114
- model="raxcore-dev/rax-3.5-chat",
115
- messages=[
116
- {"role": "system", "content": "You are a helpful AI assistant."},
117
- {"role": "user", "content": "Write a Python function to sort a list."}
118
- ],
119
  temperature=0.7,
120
- max_tokens=1024
121
  )
122
-
123
  print(response.choices[0].message.content)
124
- \`\`\`
125
 
126
- ## Architecture Details
127
 
128
- - Hybrid Attention Mechanism: Alternates between linear and full attention for efficiency
129
- - Vision Transformer: 24-layer encoder with 16x16 patch size, 2x2 spatial merging
130
- - Optimized KV Cache: 2 key-value heads for 75% memory reduction
131
- - Multi-Resolution Position Embeddings: Handles various image sizes and long sequences
132
- - Cross-Modal Fusion: Advanced alignment between vision and language representations
133
 
134
- ## Use Cases
135
 
136
- - Document Analysis: Extract data from invoices, receipts, forms
137
- - Visual QA Systems: Build AI that answers questions about images
138
- - Content Moderation: Analyze images with contextual understanding
139
- - Educational Tools: Explain diagrams, charts, and scientific images
140
- - Accessibility: Generate detailed image descriptions for visually impaired users
141
- - E-commerce: Product analysis and description generation
142
- - Medical Imaging: Assist with image interpretation (not diagnostic)
143
-
144
- ## Performance Tips
145
-
146
- - Temperature: Use 0.6-0.8 for factual tasks, 0.8-1.0 for creative content
147
- - Context Window: For >32K tokens, ensure 24GB+ VRAM
148
- - Batch Processing: Process multiple images/texts together for efficiency
149
- - Quantization: Use 4-bit/8-bit quantization for lower memory footprint
150
- - GPU Requirements: Minimum 12GB VRAM (16GB recommended)
151
 
152
  ## Limitations
153
 
154
- - 2B parameters may struggle with highly complex reasoning vs larger models
155
- - Vision encoder optimized for natural images (not specialized medical/satellite imagery)
156
- - Long context (>100K tokens) requires significant GPU memory
157
- - Not fine-tuned for specific domains without additional training
158
 
159
- ## Model Comparison
160
 
161
- | Model | Params | Context | Multimodal | Speed |
162
- |-------|--------|---------|------------|-------|
163
- | Rax 4.5 | 2B | 262K | Yes | Fast |
164
- | LLaVA 1.5 | 7B | 4K | Yes | Medium |
165
- | GPT-4V | - | 128K | Yes | Slow |
166
- | Qwen-VL | 7B | 32K | Yes | Medium |
167
 
168
  ## Citation
169
 
170
- \`\`\`bibtex
171
- @misc{rax4.5,
172
- title={Rax 4.5: Efficient Multimodal Vision-Language Model},
173
  author={Raxcore},
174
- year={2026},
175
- url={https://huggingface.co/raxcore-dev/rax-3.5-chat}
176
  }
177
- \`\`\`
178
-
179
- ## License
180
-
181
- Apache 2.0 - Free for commercial and research use
182
-
183
- ---
184
-
185
- Keywords: vision language model, multimodal AI, image to text, VLM, computer vision, transformers, efficient LLM, 2B parameters, long context, production AI, visual question answering, image understanding, open source AI model
 
5
  tags:
6
  - multimodal
7
  - vision-language
8
+ - chat
 
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
+ # Rax 3.5 Chat
12
 
13
+ Rax 3.5 Chat is a compact 2B parameter multimodal model for vision-language understanding and conversational AI. It supports text and image inputs with extended context up to 262K tokens.
14
 
15
+ ## Model Details
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
+ - **Parameters**: ~2B
18
+ - **Context Length**: 262,144 tokens
19
+ - **Input Modalities**: Text + Images
20
+ - **Attention**: Hybrid linear + full attention (24 layers)
21
+ - **Vision Encoder**: 24-layer transformer with 1024 hidden size
22
+ - **Text Hidden Size**: 2048
23
+ - **Precision**: BFloat16
24
 
25
+ ## Key Features
26
 
27
+ - **Multimodal Understanding**: Processes text and images in unified reasoning
28
+ - **Long Context**: Supports up to 262K tokens for extended conversations
29
+ - **Efficient Architecture**: Hybrid attention mechanism for optimal performance
30
+ - **Production Ready**: Compatible with vLLM, SGLang, and Transformers
31
 
32
+ ## Usage
 
 
33
 
34
+ ### With Transformers
35
 
36
+ ```python
37
  from transformers import AutoModelForVision2Seq, AutoProcessor
38
  from PIL import Image
39
 
40
+ model = AutoModelForVision2Seq.from_pretrained("raxcore/Rax-3.5-Chat", trust_remote_code=True)
41
+ processor = AutoProcessor.from_pretrained("raxcore/Rax-3.5-Chat", trust_remote_code=True)
 
 
 
 
 
 
 
42
 
43
+ # Text-only conversation
44
+ messages = [{"role": "user", "content": "What is the capital of France?"}]
45
  text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
46
  inputs = processor(text=text, return_tensors="pt")
47
  outputs = model.generate(**inputs, max_new_tokens=512)
48
  print(processor.decode(outputs[0], skip_special_tokens=True))
49
 
50
+ # With image
51
+ image = Image.open("image.jpg")
52
+ messages = [{"role": "user", "content": [{"type": "image"}, {"type": "text", "text": "Describe this image."}]}]
 
 
 
 
 
 
53
  text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
54
  inputs = processor(text=text, images=image, return_tensors="pt")
55
  outputs = model.generate(**inputs, max_new_tokens=512)
56
  print(processor.decode(outputs[0], skip_special_tokens=True))
57
+ ```
58
 
59
+ ### With vLLM
60
 
61
+ ```bash
62
+ vllm serve raxcore/Rax-3.5-Chat --port 8000 --max-model-len 8192
63
+ ```
64
 
65
+ ```python
66
  from openai import OpenAI
 
67
  client = OpenAI(base_url="http://localhost:8000/v1", api_key="token")
68
 
69
  response = client.chat.completions.create(
70
+ model="raxcore/Rax-3.5-Chat",
71
+ messages=[{"role": "user", "content": "Hello!"}],
 
 
 
72
  temperature=0.7,
73
+ max_tokens=512
74
  )
 
75
  print(response.choices[0].message.content)
76
+ ```
77
 
78
+ ## Architecture Highlights
79
 
80
+ - **Hybrid Attention**: Alternates between linear attention and full attention layers for efficiency
81
+ - **Vision Encoder**: 24-layer transformer with patch size 16 and spatial merge 2x2
82
+ - **Efficient KV Cache**: 2 key-value heads for reduced memory footprint
83
+ - **Multi-resolution Position Embeddings**: Optimized for long-context understanding
 
84
 
85
+ ## Best Practices
86
 
87
+ - Use temperature 0.6–0.8 for factual tasks, 0.8–1.0 for creative tasks
88
+ - For long context (>32K tokens), ensure sufficient GPU memory
89
+ - Enable trust_remote_code when loading the model
 
 
 
 
 
 
 
 
 
 
 
 
90
 
91
  ## Limitations
92
 
93
+ - 2B parameters may limit complex reasoning compared to larger models
94
+ - Vision understanding optimized for natural images
95
+ - Long context requires significant memory resources
 
96
 
97
+ ## License
98
 
99
+ Apache 2.0
 
 
 
 
 
100
 
101
  ## Citation
102
 
103
+ ```bibtex
104
+ @misc{rax3.5chat,
105
+ title={Rax 3.5 Chat: Efficient Multimodal Assistant Model},
106
  author={Raxcore},
107
+ year={2026}
 
108
  }
109
+ ```
 
 
 
 
 
 
 
 
chat_template.jinja DELETED
@@ -1,154 +0,0 @@
1
- {%- set image_count = namespace(value=0) %}
2
- {%- set video_count = namespace(value=0) %}
3
- {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
- {%- if content is string %}
5
- {{- content }}
6
- {%- elif content is iterable and content is not mapping %}
7
- {%- for item in content %}
8
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
- {%- if is_system_content %}
10
- {{- raise_exception('System message cannot contain images.') }}
11
- {%- endif %}
12
- {%- if do_vision_count %}
13
- {%- set image_count.value = image_count.value + 1 %}
14
- {%- endif %}
15
- {%- if add_vision_id %}
16
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
- {%- endif %}
18
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
- {%- elif 'video' in item or item.type == 'video' %}
20
- {%- if is_system_content %}
21
- {{- raise_exception('System message cannot contain videos.') }}
22
- {%- endif %}
23
- {%- if do_vision_count %}
24
- {%- set video_count.value = video_count.value + 1 %}
25
- {%- endif %}
26
- {%- if add_vision_id %}
27
- {{- 'Video ' ~ video_count.value ~ ': ' }}
28
- {%- endif %}
29
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
- {%- elif 'text' in item %}
31
- {{- item.text }}
32
- {%- else %}
33
- {{- raise_exception('Unexpected item type in content.') }}
34
- {%- endif %}
35
- {%- endfor %}
36
- {%- elif content is none or content is undefined %}
37
- {{- '' }}
38
- {%- else %}
39
- {{- raise_exception('Unexpected content type.') }}
40
- {%- endif %}
41
- {%- endmacro %}
42
- {%- if not messages %}
43
- {{- raise_exception('No messages provided.') }}
44
- {%- endif %}
45
- {%- if tools and tools is iterable and tools is not mapping %}
46
- {{- '<|im_start|>system\n' }}
47
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
- {%- for tool in tools %}
49
- {{- "\n" }}
50
- {{- tool | tojson }}
51
- {%- endfor %}
52
- {{- "\n</tools>" }}
53
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
- {%- if messages[0].role == 'system' %}
55
- {%- set content = render_content(messages[0].content, false, true)|trim %}
56
- {%- if content %}
57
- {{- '\n\n' + content }}
58
- {%- endif %}
59
- {%- endif %}
60
- {{- '<|im_end|>\n' }}
61
- {%- else %}
62
- {%- if messages[0].role == 'system' %}
63
- {%- set content = render_content(messages[0].content, false, true)|trim %}
64
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
- {%- endif %}
66
- {%- endif %}
67
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
- {%- for message in messages[::-1] %}
69
- {%- set index = (messages|length - 1) - loop.index0 %}
70
- {%- if ns.multi_step_tool and message.role == "user" %}
71
- {%- set content = render_content(message.content, false)|trim %}
72
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
- {%- set ns.multi_step_tool = false %}
74
- {%- set ns.last_query_index = index %}
75
- {%- endif %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- if ns.multi_step_tool %}
79
- {{- raise_exception('No user query found in messages.') }}
80
- {%- endif %}
81
- {%- for message in messages %}
82
- {%- set content = render_content(message.content, true)|trim %}
83
- {%- if message.role == "system" %}
84
- {%- if not loop.first %}
85
- {{- raise_exception('System message must be at the beginning.') }}
86
- {%- endif %}
87
- {%- elif message.role == "user" %}
88
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
- {%- elif message.role == "assistant" %}
90
- {%- set reasoning_content = '' %}
91
- {%- if message.reasoning_content is string %}
92
- {%- set reasoning_content = message.reasoning_content %}
93
- {%- else %}
94
- {%- if '</think>' in content %}
95
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
- {%- endif %}
98
- {%- endif %}
99
- {%- set reasoning_content = reasoning_content|trim %}
100
- {%- if loop.index0 > ns.last_query_index %}
101
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
- {%- else %}
103
- {{- '<|im_start|>' + message.role + '\n' + content }}
104
- {%- endif %}
105
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
- {%- for tool_call in message.tool_calls %}
107
- {%- if tool_call.function is defined %}
108
- {%- set tool_call = tool_call.function %}
109
- {%- endif %}
110
- {%- if loop.first %}
111
- {%- if content|trim %}
112
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
- {%- else %}
114
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
- {%- endif %}
116
- {%- else %}
117
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
- {%- endif %}
119
- {%- if tool_call.arguments is defined %}
120
- {%- for args_name, args_value in tool_call.arguments|items %}
121
- {{- '<parameter=' + args_name + '>\n' }}
122
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
- {{- args_value }}
124
- {{- '\n</parameter>\n' }}
125
- {%- endfor %}
126
- {%- endif %}
127
- {{- '</function>\n</tool_call>' }}
128
- {%- endfor %}
129
- {%- endif %}
130
- {{- '<|im_end|>\n' }}
131
- {%- elif message.role == "tool" %}
132
- {%- if loop.previtem and loop.previtem.role != "tool" %}
133
- {{- '<|im_start|>user' }}
134
- {%- endif %}
135
- {{- '\n<tool_response>\n' }}
136
- {{- content }}
137
- {{- '\n</tool_response>' }}
138
- {%- if not loop.last and loop.nextitem.role != "tool" %}
139
- {{- '<|im_end|>\n' }}
140
- {%- elif loop.last %}
141
- {{- '<|im_end|>\n' }}
142
- {%- endif %}
143
- {%- else %}
144
- {{- raise_exception('Unexpected message role.') }}
145
- {%- endif %}
146
- {%- endfor %}
147
- {%- if add_generation_prompt %}
148
- {{- '<|im_start|>assistant\n' }}
149
- {%- if enable_thinking is defined and enable_thinking is true %}
150
- {{- '<think>\n' }}
151
- {%- else %}
152
- {{- '<think>\n\n</think>\n\n' }}
153
- {%- endif %}
154
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,96 +1,27 @@
1
  {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
- ],
5
- "image_token_id": 248056,
6
- "model_type": "qwen3_5",
7
- "text_config": {
8
- "attention_bias": false,
9
- "attention_dropout": 0.0,
10
- "attn_output_gate": true,
11
- "dtype": "bfloat16",
12
- "eos_token_id": 248044,
13
- "full_attention_interval": 4,
14
- "head_dim": 256,
15
- "hidden_act": "silu",
16
- "hidden_size": 2048,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 6144,
19
- "layer_types": [
20
- "linear_attention",
21
- "linear_attention",
22
- "linear_attention",
23
- "full_attention",
24
- "linear_attention",
25
- "linear_attention",
26
- "linear_attention",
27
- "full_attention",
28
- "linear_attention",
29
- "linear_attention",
30
- "linear_attention",
31
- "full_attention",
32
- "linear_attention",
33
- "linear_attention",
34
- "linear_attention",
35
- "full_attention",
36
- "linear_attention",
37
- "linear_attention",
38
- "linear_attention",
39
- "full_attention",
40
- "linear_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "full_attention"
44
- ],
45
- "linear_conv_kernel_dim": 4,
46
- "linear_key_head_dim": 128,
47
- "linear_num_key_heads": 16,
48
- "linear_num_value_heads": 16,
49
- "linear_value_head_dim": 128,
50
- "max_position_embeddings": 262144,
51
- "mlp_only_layers": [],
52
- "model_type": "qwen3_5_text",
53
- "mtp_num_hidden_layers": 1,
54
- "mtp_use_dedicated_embeddings": false,
55
- "num_attention_heads": 8,
56
- "num_hidden_layers": 24,
57
- "num_key_value_heads": 2,
58
- "rms_norm_eps": 1e-06,
59
- "tie_word_embeddings": true,
60
- "use_cache": true,
61
- "vocab_size": 248320,
62
- "mamba_ssm_dtype": "float32",
63
- "rope_parameters": {
64
- "mrope_interleaved": true,
65
- "mrope_section": [
66
- 11,
67
- 11,
68
- 10
69
- ],
70
- "rope_type": "default",
71
- "rope_theta": 10000000,
72
- "partial_rotary_factor": 0.25
73
- }
74
- },
75
- "tie_word_embeddings": true,
76
- "transformers_version": "4.57.0.dev0",
77
- "video_token_id": 248057,
78
- "vision_config": {
79
- "deepstack_visual_indexes": [],
80
- "depth": 24,
81
- "hidden_act": "gelu_pytorch_tanh",
82
- "hidden_size": 1024,
83
- "in_channels": 3,
84
- "initializer_range": 0.02,
85
- "intermediate_size": 4096,
86
- "model_type": "qwen3_5",
87
- "num_heads": 16,
88
- "num_position_embeddings": 2304,
89
- "out_hidden_size": 2048,
90
- "patch_size": 16,
91
- "spatial_merge_size": 2,
92
- "temporal_patch_size": 2
93
- },
94
- "vision_end_token_id": 248054,
95
- "vision_start_token_id": 248053
96
- }
 
1
  {
2
+ "_name_or_path": "rax-3.5-chat",
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": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 5632,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 22,
17
+ "num_key_value_heads": 4,
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": "bfloat16",
24
+ "transformers_version": "4.35.0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -2.707406759262085,
4
+ "eval_logits/rejected": -2.656524419784546,
5
+ "eval_logps/chosen": -370.1297607421875,
6
+ "eval_logps/rejected": -296.0738525390625,
7
+ "eval_loss": 0.513750433921814,
8
+ "eval_rewards/accuracies": 0.738095223903656,
9
+ "eval_rewards/chosen": -0.02744222804903984,
10
+ "eval_rewards/margins": 1.0087225437164307,
11
+ "eval_rewards/rejected": -1.03616464138031,
12
+ "eval_runtime": 93.5908,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 21.37,
15
+ "eval_steps_per_second": 0.673
16
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 2048,
6
+ "pad_token_id": 2,
7
+ "transformers_version": "4.35.0"
8
+ }
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
model.safetensors-00001-of-00001.safetensors → model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa33250c4fc64891ddfaba3a314fd9542ea371843c387178b425fbcc5ed680b1
3
- size 4548221488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e6001da2106d4757498752a021df6c2bdc332c650aae4bae6b0c004dcf14933
3
+ size 2200119864
model.safetensors.index.json DELETED
@@ -1,639 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 4548144832
4
- },
5
- "weight_map": {
6
- "model.language_model.embed_tokens.weight": "model.safetensors-00001-of-00001.safetensors",
7
- "model.visual.merger.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
8
- "model.language_model.layers.22.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
9
- "model.language_model.layers.22.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
10
- "model.language_model.layers.22.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
11
- "model.language_model.layers.23.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
12
- "model.language_model.layers.23.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
13
- "model.language_model.layers.23.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
14
- "model.language_model.layers.3.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
15
- "model.language_model.layers.3.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
16
- "model.language_model.layers.3.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
17
- "model.language_model.layers.6.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
18
- "model.language_model.layers.6.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
19
- "model.language_model.layers.6.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
20
- "model.language_model.layers.7.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
21
- "model.language_model.layers.7.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
22
- "model.language_model.layers.7.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
23
- "model.language_model.layers.9.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
24
- "model.language_model.layers.9.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
25
- "model.language_model.layers.9.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
26
- "mtp.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
27
- "mtp.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
28
- "mtp.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
29
- "model.language_model.layers.10.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
30
- "model.language_model.layers.11.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
31
- "model.language_model.layers.11.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
32
- "model.language_model.layers.11.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
33
- "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
34
- "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
35
- "model.language_model.layers.4.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
36
- "model.language_model.layers.4.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
37
- "model.language_model.layers.4.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
38
- "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
39
- "model.language_model.layers.14.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
40
- "model.language_model.layers.14.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
41
- "model.language_model.layers.14.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
42
- "model.language_model.layers.15.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
43
- "model.language_model.layers.15.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
44
- "model.language_model.layers.15.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
45
- "model.language_model.layers.2.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
46
- "model.language_model.layers.2.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
47
- "model.language_model.layers.2.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
48
- "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
49
- "model.language_model.layers.20.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
50
- "model.language_model.layers.20.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
51
- "model.language_model.layers.20.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
52
- "model.language_model.layers.17.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
53
- "model.language_model.layers.17.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
54
- "model.language_model.layers.17.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
55
- "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
56
- "model.language_model.layers.18.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
57
- "model.language_model.layers.18.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
58
- "model.language_model.layers.18.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
59
- "model.language_model.layers.12.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
60
- "model.language_model.layers.12.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
61
- "model.language_model.layers.12.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
62
- "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
63
- "model.language_model.layers.13.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
64
- "model.language_model.layers.13.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
65
- "model.language_model.layers.13.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
66
- "model.language_model.layers.19.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
67
- "model.language_model.layers.19.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
68
- "model.language_model.layers.19.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
69
- "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
70
- "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
71
- "model.language_model.layers.1.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
72
- "model.language_model.layers.1.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
73
- "model.language_model.layers.1.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
74
- "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
75
- "model.language_model.layers.10.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
76
- "model.language_model.layers.10.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
77
- "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
78
- "model.language_model.layers.16.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
79
- "model.language_model.layers.16.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
80
- "model.language_model.layers.16.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
81
- "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
82
- "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
83
- "model.language_model.layers.5.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
84
- "model.language_model.layers.5.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
85
- "model.language_model.layers.5.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
86
- "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
87
- "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
88
- "model.language_model.layers.21.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
89
- "model.language_model.layers.21.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
90
- "model.language_model.layers.21.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
91
- "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
92
- "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
93
- "model.language_model.layers.8.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
94
- "model.language_model.layers.8.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
95
- "model.language_model.layers.8.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
96
- "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
97
- "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
98
- "model.language_model.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
99
- "model.language_model.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
100
- "model.language_model.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
101
- "model.language_model.layers.23.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
102
- "model.language_model.layers.7.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
103
- "mtp.fc.weight": "model.safetensors-00001-of-00001.safetensors",
104
- "mtp.layers.0.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
105
- "model.language_model.layers.11.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
106
- "model.language_model.layers.3.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
107
- "model.language_model.layers.15.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
108
- "model.language_model.layers.19.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
109
- "model.visual.merger.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
110
- "model.language_model.layers.23.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
111
- "model.language_model.layers.3.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
112
- "model.language_model.layers.6.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
113
- "model.language_model.layers.7.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
114
- "mtp.layers.0.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
115
- "model.language_model.layers.11.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
116
- "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
117
- "model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
118
- "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
119
- "model.language_model.layers.4.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
120
- "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
121
- "model.language_model.layers.14.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
122
- "model.language_model.layers.15.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
123
- "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
124
- "model.language_model.layers.20.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
125
- "model.language_model.layers.17.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
126
- "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
127
- "model.language_model.layers.18.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
128
- "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
129
- "model.language_model.layers.13.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
130
- "model.language_model.layers.19.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
131
- "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
132
- "model.language_model.layers.2.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
133
- "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
134
- "model.language_model.layers.1.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
135
- "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
136
- "model.language_model.layers.10.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
137
- "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
138
- "model.language_model.layers.16.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
139
- "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
140
- "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
141
- "model.language_model.layers.5.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
142
- "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
143
- "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
144
- "model.language_model.layers.21.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
145
- "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
146
- "model.language_model.layers.22.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
147
- "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
148
- "model.language_model.layers.8.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
149
- "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
150
- "model.language_model.layers.9.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
151
- "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
152
- "model.language_model.layers.0.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
153
- "model.visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
154
- "model.visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
155
- "model.visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
156
- "model.visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
157
- "model.visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
158
- "model.visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
159
- "model.visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
160
- "model.visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
161
- "model.visual.blocks.12.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
162
- "model.visual.blocks.12.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
163
- "model.visual.blocks.13.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
164
- "model.visual.blocks.13.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
165
- "model.visual.blocks.14.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
166
- "model.visual.blocks.14.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
167
- "model.visual.blocks.15.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
168
- "model.visual.blocks.15.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
169
- "model.visual.blocks.16.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
170
- "model.visual.blocks.16.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
171
- "model.visual.blocks.17.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
172
- "model.visual.blocks.17.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
173
- "model.visual.blocks.18.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
174
- "model.visual.blocks.18.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
175
- "model.visual.blocks.19.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
176
- "model.visual.blocks.19.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
177
- "model.visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
178
- "model.visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
179
- "model.visual.blocks.20.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
180
- "model.visual.blocks.20.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
181
- "model.visual.blocks.21.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
182
- "model.visual.blocks.21.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
183
- "model.visual.blocks.22.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
184
- "model.visual.blocks.22.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
185
- "model.visual.blocks.23.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
186
- "model.visual.blocks.23.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
187
- "model.visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
188
- "model.visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
189
- "model.visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
190
- "model.visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
191
- "model.visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
192
- "model.visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
193
- "model.visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
194
- "model.visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
195
- "model.visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
196
- "model.visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
197
- "model.visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
198
- "model.visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
199
- "model.visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
200
- "model.visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
201
- "model.visual.blocks.0.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
202
- "model.visual.blocks.1.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
203
- "model.visual.blocks.10.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
204
- "model.visual.blocks.11.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
205
- "model.visual.blocks.12.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
206
- "model.visual.blocks.13.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
207
- "model.visual.blocks.14.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
208
- "model.visual.blocks.15.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
209
- "model.visual.blocks.16.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
210
- "model.visual.blocks.17.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
211
- "model.visual.blocks.18.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
212
- "model.visual.blocks.19.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
213
- "model.visual.blocks.2.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
214
- "model.visual.blocks.20.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
215
- "model.visual.blocks.21.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
216
- "model.visual.blocks.22.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
217
- "model.visual.blocks.23.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
218
- "model.visual.blocks.3.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
219
- "model.visual.blocks.4.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
220
- "model.visual.blocks.5.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
221
- "model.visual.blocks.6.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
222
- "model.visual.blocks.7.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
223
- "model.visual.blocks.8.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
224
- "model.visual.blocks.9.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
225
- "model.visual.pos_embed.weight": "model.safetensors-00001-of-00001.safetensors",
226
- "model.visual.patch_embed.proj.weight": "model.safetensors-00001-of-00001.safetensors",
227
- "model.language_model.layers.23.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
228
- "model.language_model.layers.23.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
229
- "model.language_model.layers.7.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
230
- "model.language_model.layers.7.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
231
- "mtp.layers.0.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
232
- "mtp.layers.0.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
233
- "model.language_model.layers.11.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
234
- "model.language_model.layers.11.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
235
- "model.language_model.layers.3.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
236
- "model.language_model.layers.3.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
237
- "model.language_model.layers.15.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
238
- "model.language_model.layers.15.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
239
- "model.language_model.layers.19.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
240
- "model.language_model.layers.19.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
241
- "model.visual.blocks.0.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
242
- "model.visual.blocks.1.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
243
- "model.visual.blocks.10.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
244
- "model.visual.blocks.11.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
245
- "model.visual.blocks.12.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
246
- "model.visual.blocks.13.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
247
- "model.visual.blocks.14.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
248
- "model.visual.blocks.15.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
249
- "model.visual.blocks.16.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
250
- "model.visual.blocks.17.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
251
- "model.visual.blocks.18.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
252
- "model.visual.blocks.19.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
253
- "model.visual.blocks.2.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
254
- "model.visual.blocks.20.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
255
- "model.visual.blocks.21.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
256
- "model.visual.blocks.22.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
257
- "model.visual.blocks.23.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
258
- "model.visual.blocks.3.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
259
- "model.visual.blocks.4.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
260
- "model.visual.blocks.5.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
261
- "model.visual.blocks.6.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
262
- "model.visual.blocks.7.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
263
- "model.visual.blocks.8.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
264
- "model.visual.blocks.9.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
265
- "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
266
- "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
267
- "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
268
- "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
269
- "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
270
- "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
271
- "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
272
- "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
273
- "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
274
- "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
275
- "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
276
- "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
277
- "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
278
- "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
279
- "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
280
- "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
281
- "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
282
- "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
283
- "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
284
- "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
285
- "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
286
- "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
287
- "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
288
- "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
289
- "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
290
- "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
291
- "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
292
- "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
293
- "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
294
- "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
295
- "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
296
- "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
297
- "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
298
- "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
299
- "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
300
- "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
301
- "model.language_model.layers.8.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
302
- "model.language_model.layers.12.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
303
- "model.language_model.layers.4.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
304
- "model.language_model.layers.5.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
305
- "model.language_model.layers.20.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
306
- "model.language_model.layers.21.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
307
- "model.language_model.layers.18.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
308
- "model.language_model.layers.13.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
309
- "model.language_model.layers.14.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
310
- "model.language_model.layers.2.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
311
- "model.language_model.layers.10.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
312
- "model.language_model.layers.16.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
313
- "model.language_model.layers.17.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
314
- "model.language_model.layers.6.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
315
- "model.language_model.layers.22.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
316
- "model.language_model.layers.9.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
317
- "model.language_model.layers.0.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
318
- "model.language_model.layers.1.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
319
- "model.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
320
- "model.visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
321
- "model.visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
322
- "model.visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
323
- "model.visual.blocks.12.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
324
- "model.visual.blocks.13.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
325
- "model.visual.blocks.14.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
326
- "model.visual.blocks.15.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
327
- "model.visual.blocks.16.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
328
- "model.visual.blocks.17.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
329
- "model.visual.blocks.18.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
330
- "model.visual.blocks.19.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
331
- "model.visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
332
- "model.visual.blocks.20.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
333
- "model.visual.blocks.21.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
334
- "model.visual.blocks.22.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
335
- "model.visual.blocks.23.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
336
- "model.visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
337
- "model.visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
338
- "model.visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
339
- "model.visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
340
- "model.visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
341
- "model.visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
342
- "model.visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
343
- "model.visual.merger.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
344
- "model.visual.blocks.0.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
345
- "model.visual.blocks.1.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
346
- "model.visual.blocks.10.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
347
- "model.visual.blocks.11.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
348
- "model.visual.blocks.12.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
349
- "model.visual.blocks.13.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
350
- "model.visual.blocks.14.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
351
- "model.visual.blocks.15.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
352
- "model.visual.blocks.16.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
353
- "model.visual.blocks.17.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
354
- "model.visual.blocks.18.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
355
- "model.visual.blocks.19.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
356
- "model.visual.blocks.2.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
357
- "model.visual.blocks.20.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
358
- "model.visual.blocks.21.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
359
- "model.visual.blocks.22.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
360
- "model.visual.blocks.23.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
361
- "model.visual.blocks.3.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
362
- "model.visual.blocks.4.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
363
- "model.visual.blocks.5.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
364
- "model.visual.blocks.6.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
365
- "model.visual.blocks.7.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
366
- "model.visual.blocks.8.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
367
- "model.visual.blocks.9.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
368
- "model.language_model.layers.22.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
369
- "model.language_model.layers.23.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
370
- "model.language_model.layers.23.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
371
- "model.language_model.layers.3.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
372
- "model.language_model.layers.6.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
373
- "model.language_model.layers.7.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
374
- "model.language_model.layers.7.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
375
- "model.language_model.layers.8.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
376
- "mtp.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
377
- "mtp.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
378
- "mtp.norm.weight": "model.safetensors-00001-of-00001.safetensors",
379
- "mtp.pre_fc_norm_embedding.weight": "model.safetensors-00001-of-00001.safetensors",
380
- "mtp.pre_fc_norm_hidden.weight": "model.safetensors-00001-of-00001.safetensors",
381
- "model.language_model.layers.11.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
382
- "model.language_model.layers.11.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
383
- "model.language_model.layers.12.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
384
- "model.language_model.layers.3.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
385
- "model.language_model.layers.4.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
386
- "model.language_model.layers.4.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
387
- "model.language_model.layers.14.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
388
- "model.language_model.layers.14.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
389
- "model.language_model.layers.15.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
390
- "model.language_model.layers.15.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
391
- "model.language_model.layers.20.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
392
- "model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
393
- "model.language_model.layers.17.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
394
- "model.language_model.layers.18.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
395
- "model.language_model.layers.18.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
396
- "model.language_model.layers.19.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
397
- "model.language_model.layers.12.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
398
- "model.language_model.layers.13.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
399
- "model.language_model.layers.13.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
400
- "model.language_model.layers.19.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
401
- "model.language_model.layers.2.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
402
- "model.language_model.layers.2.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
403
- "model.language_model.layers.1.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
404
- "model.language_model.layers.10.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
405
- "model.language_model.layers.10.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
406
- "model.language_model.layers.16.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
407
- "model.language_model.layers.16.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
408
- "model.language_model.layers.17.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
409
- "model.language_model.layers.5.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
410
- "model.language_model.layers.5.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
411
- "model.language_model.layers.6.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
412
- "model.language_model.layers.21.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
413
- "model.language_model.layers.21.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
414
- "model.language_model.layers.22.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
415
- "model.language_model.layers.8.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
416
- "model.language_model.layers.9.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
417
- "model.language_model.layers.9.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
418
- "model.language_model.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
419
- "model.language_model.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
420
- "model.language_model.layers.1.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
421
- "model.language_model.norm.weight": "model.safetensors-00001-of-00001.safetensors",
422
- "model.visual.merger.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
423
- "model.visual.blocks.0.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
424
- "model.visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
425
- "model.visual.blocks.0.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
426
- "model.visual.blocks.0.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
427
- "model.visual.blocks.0.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
428
- "model.visual.blocks.0.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
429
- "model.visual.blocks.1.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
430
- "model.visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
431
- "model.visual.blocks.1.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
432
- "model.visual.blocks.1.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
433
- "model.visual.blocks.1.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
434
- "model.visual.blocks.1.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
435
- "model.visual.blocks.10.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
436
- "model.visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
437
- "model.visual.blocks.10.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
438
- "model.visual.blocks.10.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
439
- "model.visual.blocks.10.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
440
- "model.visual.blocks.10.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
441
- "model.visual.blocks.11.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
442
- "model.visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
443
- "model.visual.blocks.11.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
444
- "model.visual.blocks.11.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
445
- "model.visual.blocks.11.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
446
- "model.visual.blocks.11.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
447
- "model.visual.blocks.12.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
448
- "model.visual.blocks.12.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
449
- "model.visual.blocks.12.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
450
- "model.visual.blocks.12.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
451
- "model.visual.blocks.12.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
452
- "model.visual.blocks.12.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
453
- "model.visual.blocks.13.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
454
- "model.visual.blocks.13.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
455
- "model.visual.blocks.13.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
456
- "model.visual.blocks.13.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
457
- "model.visual.blocks.13.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
458
- "model.visual.blocks.13.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
459
- "model.visual.blocks.14.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
460
- "model.visual.blocks.14.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
461
- "model.visual.blocks.14.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
462
- "model.visual.blocks.14.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
463
- "model.visual.blocks.14.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
464
- "model.visual.blocks.14.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
465
- "model.visual.blocks.15.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
466
- "model.visual.blocks.15.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
467
- "model.visual.blocks.15.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
468
- "model.visual.blocks.15.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
469
- "model.visual.blocks.15.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
470
- "model.visual.blocks.15.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
471
- "model.visual.blocks.16.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
472
- "model.visual.blocks.16.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
473
- "model.visual.blocks.16.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
474
- "model.visual.blocks.16.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
475
- "model.visual.blocks.16.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
476
- "model.visual.blocks.16.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
477
- "model.visual.blocks.17.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
478
- "model.visual.blocks.17.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
479
- "model.visual.blocks.17.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
480
- "model.visual.blocks.17.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
481
- "model.visual.blocks.17.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
482
- "model.visual.blocks.17.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
483
- "model.visual.blocks.18.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
484
- "model.visual.blocks.18.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
485
- "model.visual.blocks.18.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
486
- "model.visual.blocks.18.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
487
- "model.visual.blocks.18.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
488
- "model.visual.blocks.18.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
489
- "model.visual.blocks.19.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
490
- "model.visual.blocks.19.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
491
- "model.visual.blocks.19.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
492
- "model.visual.blocks.19.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
493
- "model.visual.blocks.19.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
494
- "model.visual.blocks.19.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
495
- "model.visual.blocks.2.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
496
- "model.visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
497
- "model.visual.blocks.2.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
498
- "model.visual.blocks.2.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
499
- "model.visual.blocks.2.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
500
- "model.visual.blocks.2.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
501
- "model.visual.blocks.20.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
502
- "model.visual.blocks.20.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
503
- "model.visual.blocks.20.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
504
- "model.visual.blocks.20.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
505
- "model.visual.blocks.20.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
506
- "model.visual.blocks.20.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
507
- "model.visual.blocks.21.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
508
- "model.visual.blocks.21.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
509
- "model.visual.blocks.21.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
510
- "model.visual.blocks.21.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
511
- "model.visual.blocks.21.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
512
- "model.visual.blocks.21.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
513
- "model.visual.blocks.22.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
514
- "model.visual.blocks.22.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
515
- "model.visual.blocks.22.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
516
- "model.visual.blocks.22.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
517
- "model.visual.blocks.22.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
518
- "model.visual.blocks.22.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
519
- "model.visual.blocks.23.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
520
- "model.visual.blocks.23.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
521
- "model.visual.blocks.23.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
522
- "model.visual.blocks.23.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
523
- "model.visual.blocks.23.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
524
- "model.visual.blocks.23.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
525
- "model.visual.blocks.3.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
526
- "model.visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
527
- "model.visual.blocks.3.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
528
- "model.visual.blocks.3.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
529
- "model.visual.blocks.3.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
530
- "model.visual.blocks.3.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
531
- "model.visual.blocks.4.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
532
- "model.visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
533
- "model.visual.blocks.4.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
534
- "model.visual.blocks.4.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
535
- "model.visual.blocks.4.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
536
- "model.visual.blocks.4.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
537
- "model.visual.blocks.5.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
538
- "model.visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
539
- "model.visual.blocks.5.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
540
- "model.visual.blocks.5.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
541
- "model.visual.blocks.5.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
542
- "model.visual.blocks.5.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
543
- "model.visual.blocks.6.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
544
- "model.visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
545
- "model.visual.blocks.6.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
546
- "model.visual.blocks.6.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
547
- "model.visual.blocks.6.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
548
- "model.visual.blocks.6.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
549
- "model.visual.blocks.7.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
550
- "model.visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
551
- "model.visual.blocks.7.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
552
- "model.visual.blocks.7.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
553
- "model.visual.blocks.7.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
554
- "model.visual.blocks.7.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
555
- "model.visual.blocks.8.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
556
- "model.visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
557
- "model.visual.blocks.8.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
558
- "model.visual.blocks.8.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
559
- "model.visual.blocks.8.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
560
- "model.visual.blocks.8.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
561
- "model.visual.blocks.9.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
562
- "model.visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
563
- "model.visual.blocks.9.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
564
- "model.visual.blocks.9.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
565
- "model.visual.blocks.9.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
566
- "model.visual.blocks.9.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
567
- "model.visual.merger.norm.bias": "model.safetensors-00001-of-00001.safetensors",
568
- "model.visual.merger.norm.weight": "model.safetensors-00001-of-00001.safetensors",
569
- "model.visual.patch_embed.proj.bias": "model.safetensors-00001-of-00001.safetensors",
570
- "model.language_model.layers.23.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
571
- "model.language_model.layers.23.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
572
- "model.language_model.layers.3.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
573
- "model.language_model.layers.7.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
574
- "model.language_model.layers.7.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
575
- "mtp.layers.0.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
576
- "mtp.layers.0.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
577
- "model.language_model.layers.11.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
578
- "model.language_model.layers.11.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
579
- "model.language_model.layers.12.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
580
- "model.language_model.layers.3.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
581
- "model.language_model.layers.4.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
582
- "model.language_model.layers.14.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
583
- "model.language_model.layers.15.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
584
- "model.language_model.layers.15.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
585
- "model.language_model.layers.20.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
586
- "model.language_model.layers.18.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
587
- "model.language_model.layers.13.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
588
- "model.language_model.layers.19.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
589
- "model.language_model.layers.19.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
590
- "model.language_model.layers.2.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
591
- "model.language_model.layers.1.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
592
- "model.language_model.layers.10.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
593
- "model.language_model.layers.16.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
594
- "model.language_model.layers.17.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
595
- "model.language_model.layers.5.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
596
- "model.language_model.layers.6.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
597
- "model.language_model.layers.21.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
598
- "model.language_model.layers.22.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
599
- "model.language_model.layers.8.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
600
- "model.language_model.layers.9.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
601
- "model.language_model.layers.0.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
602
- "model.language_model.layers.8.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
603
- "model.language_model.layers.12.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
604
- "model.language_model.layers.4.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
605
- "model.language_model.layers.5.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
606
- "model.language_model.layers.16.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
607
- "model.language_model.layers.20.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
608
- "model.language_model.layers.21.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
609
- "model.language_model.layers.18.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
610
- "model.language_model.layers.13.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
611
- "model.language_model.layers.14.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
612
- "model.language_model.layers.2.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
613
- "model.language_model.layers.10.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
614
- "model.language_model.layers.17.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
615
- "model.language_model.layers.6.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
616
- "model.language_model.layers.22.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
617
- "model.language_model.layers.9.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
618
- "model.language_model.layers.0.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
619
- "model.language_model.layers.1.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
620
- "model.language_model.layers.8.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
621
- "model.language_model.layers.12.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
622
- "model.language_model.layers.4.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
623
- "model.language_model.layers.20.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
624
- "model.language_model.layers.21.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
625
- "model.language_model.layers.18.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
626
- "model.language_model.layers.13.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
627
- "model.language_model.layers.14.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
628
- "model.language_model.layers.2.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
629
- "model.language_model.layers.10.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
630
- "model.language_model.layers.16.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
631
- "model.language_model.layers.17.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
632
- "model.language_model.layers.5.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
633
- "model.language_model.layers.6.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
634
- "model.language_model.layers.22.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
635
- "model.language_model.layers.9.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
636
- "model.language_model.layers.0.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
637
- "model.language_model.layers.1.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors"
638
- }
639
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_card.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - chat
8
+ - conversational
9
+ - llama
10
+ - fine-tuned
11
+ - rax
12
+ - raxcore
13
+ model_type: llama
14
+ ---
15
+
16
+ # Rax 3.5 Chat
17
+
18
+ **Developed by RaxCore - A leading developer company in Africa and beyond**
19
+
20
+ ## Model Description
21
+
22
+ Rax 3.5 Chat is an extensively enhanced conversational AI model featuring breakthrough improvements developed by RaxCore. Built upon the Llama architecture with TinyLlama as foundation, this model incorporates proprietary optimization techniques, advanced training methodologies, and cultural context awareness that significantly exceed baseline performance.
23
+
24
+ ## Quick Start
25
+
26
+ ```python
27
+ from transformers import AutoTokenizer, AutoModelForCausalLM
28
+
29
+ tokenizer = AutoTokenizer.from_pretrained("rax-3.5-chat")
30
+ model = AutoModelForCausalLM.from_pretrained("rax-3.5-chat")
31
+
32
+ messages = [
33
+ {"role": "system", "content": "You are Rax, a helpful AI assistant."},
34
+ {"role": "user", "content": "Hello!"}
35
+ ]
36
+
37
+ input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
38
+ inputs = tokenizer(input_text, return_tensors="pt")
39
+ outputs = model.generate(**inputs, max_new_tokens=256)
40
+ ```
41
+
42
+ ## Model Details
43
+
44
+ - **Architecture**: Enhanced Llama (1.1B parameters with RaxCore optimizations)
45
+ - **Context Length**: 2048 tokens
46
+ - **Development**: Extensively enhanced by RaxCore with proprietary improvements
47
+ - **Base**: TinyLlama foundation with significant RaxCore upgrades
48
+ - **License**: Apache 2.0
49
+
50
+ ## Intended Use
51
+
52
+ - Conversational AI applications
53
+ - Research and educational purposes
54
+ - Creative writing assistance
55
+ - Chatbot development
56
+
57
+ ## Limitations
58
+
59
+ - 2048 token context limit
60
+ - May generate biased or incorrect information
61
+ - Requires responsible deployment practices
62
+
63
+ ## Links
64
+
65
+ - **RaxCore Website**: [www.raxcore.dev](https://www.raxcore.dev/)
66
+ - **Hugging Face Profile**: [raxcore-dev](https://huggingface.co/raxcore-dev)
preprocessor_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "size": {
3
- "longest_edge": 16777216,
4
- "shortest_edge": 65536
5
- },
6
- "patch_size": 16,
7
- "temporal_patch_size": 2,
8
- "merge_size": 2,
9
- "image_mean": [
10
- 0.5,
11
- 0.5,
12
- 0.5
13
- ],
14
- "image_std": [
15
- 0.5,
16
- 0.5,
17
- 0.5
18
- ],
19
- "processor_class": "Qwen3VLProcessor",
20
- "image_processor_type": "Qwen2VLImageProcessorFast"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
test_rax.py ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ """
3
+ Test script for Rax 3.5 Chat model
4
+ """
5
+
6
+ from transformers import AutoTokenizer, AutoModelForCausalLM
7
+ import torch
8
+
9
+ def test_rax_chat():
10
+ print("Loading Rax 3.5 Chat model...")
11
+
12
+ # Load model and tokenizer
13
+ tokenizer = AutoTokenizer.from_pretrained(".")
14
+ model = AutoModelForCausalLM.from_pretrained(
15
+ ".",
16
+ torch_dtype=torch.bfloat16,
17
+ device_map="auto"
18
+ )
19
+
20
+ print("Model loaded successfully!")
21
+
22
+ # Test conversation
23
+ messages = [
24
+ {"role": "system", "content": "You are Rax, a helpful AI assistant."},
25
+ {"role": "user", "content": "Hello! Can you tell me about yourself?"}
26
+ ]
27
+
28
+ # Apply chat template
29
+ input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
30
+ print(f"Input: {input_text}")
31
+
32
+ inputs = tokenizer(input_text, return_tensors="pt")
33
+
34
+ # Generate response
35
+ with torch.no_grad():
36
+ outputs = model.generate(
37
+ **inputs,
38
+ max_new_tokens=128,
39
+ temperature=0.7,
40
+ do_sample=True,
41
+ pad_token_id=tokenizer.eos_token_id
42
+ )
43
+
44
+ response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
45
+ print(f"Rax: {response}")
46
+
47
+ if __name__ == "__main__":
48
+ test_rax_chat()
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,305 +1,41 @@
1
  {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "248044": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "248045": {
13
- "content": "<|im_start|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "248046": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "248047": {
29
- "content": "<|object_ref_start|>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "248048": {
37
- "content": "<|object_ref_end|>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "248049": {
45
- "content": "<|box_start|>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "248050": {
53
- "content": "<|box_end|>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "248051": {
61
- "content": "<|quad_start|>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "248052": {
69
- "content": "<|quad_end|>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "248053": {
77
- "content": "<|vision_start|>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "248054": {
85
- "content": "<|vision_end|>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "248055": {
93
- "content": "<|vision_pad|>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "248056": {
101
- "content": "<|image_pad|>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "248057": {
109
- "content": "<|video_pad|>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "248058": {
117
- "content": "<tool_call>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "248059": {
125
- "content": "</tool_call>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "248060": {
133
- "content": "<|fim_prefix|>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "248061": {
141
- "content": "<|fim_middle|>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "248062": {
149
- "content": "<|fim_suffix|>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "248063": {
157
- "content": "<|fim_pad|>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "248064": {
165
- "content": "<|repo_name|>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "248065": {
173
- "content": "<|file_sep|>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "248066": {
181
- "content": "<tool_response>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "248067": {
189
- "content": "</tool_response>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "248068": {
197
- "content": "<think>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "248069": {
205
- "content": "</think>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "248070": {
213
- "content": "<|audio_start|>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "248071": {
221
- "content": "<|audio_end|>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "248072": {
229
- "content": "<tts_pad>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "248073": {
237
- "content": "<tts_text_bos>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "248074": {
245
- "content": "<tts_text_eod>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "248075": {
253
- "content": "<tts_text_bos_single>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "248076": {
261
- "content": "<|audio_pad|>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": true
267
- }
268
  },
269
- "additional_special_tokens": [
270
- "<|im_start|>",
271
- "<|im_end|>",
272
- "<|object_ref_start|>",
273
- "<|object_ref_end|>",
274
- "<|box_start|>",
275
- "<|box_end|>",
276
- "<|quad_start|>",
277
- "<|quad_end|>",
278
- "<|vision_start|>",
279
- "<|vision_end|>",
280
- "<|vision_pad|>",
281
- "<|image_pad|>",
282
- "<|video_pad|>"
283
- ],
284
- "bos_token": null,
285
- "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is true %}\n {{- '<think>\\n' }}\n {%- else %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
286
- "clean_up_tokenization_spaces": false,
287
- "eos_token": "<|im_end|>",
288
- "errors": "replace",
289
- "model_max_length": 262144,
290
- "pad_token": "<|endoftext|>",
291
- "split_special_tokens": false,
292
- "tokenizer_class": "Qwen2Tokenizer",
293
- "unk_token": null,
294
- "add_bos_token": false,
295
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
296
- "extra_special_tokens": {
297
- "audio_bos_token": "<|audio_start|>",
298
- "audio_eos_token": "<|audio_end|>",
299
- "audio_token": "<|audio_pad|>",
300
- "image_token": "<|image_pad|>",
301
- "video_token": "<|video_pad|>",
302
- "vision_bos_token": "<|vision_start|>",
303
- "vision_eos_token": "<|vision_end|>"
304
  }
305
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
27
+ },
28
+ "bos_token": "<s>",
29
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 2048,
34
+ "name_or_path": "rax-3.5-chat",
35
+ "pad_token": "</s>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
video_preprocessor_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "size": {
3
- "longest_edge": 25165824,
4
- "shortest_edge": 4096
5
- },
6
- "patch_size": 16,
7
- "temporal_patch_size": 2,
8
- "merge_size": 2,
9
- "image_mean": [
10
- 0.5,
11
- 0.5,
12
- 0.5
13
- ],
14
- "image_std": [
15
- 0.5,
16
- 0.5,
17
- 0.5
18
- ],
19
- "processor_class": "Qwen3VLProcessor",
20
- "video_processor_type": "Qwen3VLVideoProcessor"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vocab.json DELETED
The diff for this file is too large to render. See raw diff