Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +132 -0
- chat_template.jinja +154 -0
- config.json +648 -0
- generation_config.json +15 -0
- model.safetensors +3 -0
- model.safetensors.index.json +928 -0
- processor_config.json +63 -0
- quant_report.csv +201 -0
- tokenizer.json +3 -0
- tokenizer_config.json +32 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
base_model:
|
| 7 |
+
- Qwen/Qwen3.5-4B
|
| 8 |
+
---
|
| 9 |
+
# CoPaw-Flash-4B
|
| 10 |
+
**CoPaw-Flash** is a lightweight model deeply optimized for the CoPaw autonomous agent scenario. Since its training phase, the model has been specifically refined for CoPaw tasks, delivering enhanced agentic performance in tool invocation, command execution, memory management, and multi-step planning.
|
| 11 |
+
|
| 12 |
+
## Capability
|
| 13 |
+
The core strength of CoPaw-Flash stems from its native integration with the CoPaw ecosystem. We have constructed extensive, high-quality agent trajectory data sampled from real CoPaw environments, systematically enhancing the model's proficiency in high-frequency daily scenarios. Key features include:
|
| 14 |
+
|
| 15 |
+
+ **Active Memory Management:** Autonomously identifies, stores, and retrieves persistent user preferences and task states, ensuring high logical consistency across multi-turn interactions.
|
| 16 |
+
+ **Native File Parsing:** Optimized for terminal operations and file system orchestration. Excels at generating precise CLI commands and executing complex, multi-step file I/O tasks.
|
| 17 |
+
+ **Efficient Information Search:** Enhanced for web-search tool invocation. Features precise search intent recognition and multi-step web navigation to effectively identify and query online information.
|
| 18 |
+
+ **Intelligent Guidance:** Built-in awareness of the CoPaw feature map. Proactively suggests functional paths and troubleshooting based on real-time operational context.
|
| 19 |
+
|
| 20 |
+
## Model Overview
|
| 21 |
+
CoPaw-Flash-2B/4B/9B is fine-tuned from Qwen3.5-2B/4B/9B, sharing the same architectural parameters.
|
| 22 |
+
|
| 23 |
+
+ **Type:** Causal Language Model with Vision Encoder
|
| 24 |
+
+ **Training Stage:** Post-training
|
| 25 |
+
+ **Number of Parameters:** 2B/4B/9B
|
| 26 |
+
+ **Hidden Dimension:** 2048/2560/4096
|
| 27 |
+
+ **Token Embedding:** 248320 (Padded)
|
| 28 |
+
+ **Number of Layers:** 24/32/32
|
| 29 |
+
+ **Hidden Layout:** 6/8/8 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
|
| 30 |
+
+ **Gated DeltaNet:**
|
| 31 |
+
- **Number of Linear Attention Heads:** 16/32/32 for V and 16/16/16 for QK
|
| 32 |
+
- **Head Dimension:** 128
|
| 33 |
+
+ **Gated Attention:**
|
| 34 |
+
- **Number of Attention Heads:** 8/16/16 for Q and 2/4/4 for KV
|
| 35 |
+
- **Head Dimension:** 256
|
| 36 |
+
+ **Rotary Position Embedding Dimension:** 64
|
| 37 |
+
+ **Feed Forward Network:** Intermediate Dimension: 6144/9216/12288
|
| 38 |
+
+ **LM Output:** 248320 (Tied to token embedding)
|
| 39 |
+
+ **Context Length:** 262,144 tokens natively
|
| 40 |
+
|
| 41 |
+
## Benchmark Results
|
| 42 |
+
The complexity of CoPaw's context engineering and tool usage poses heightened challenges for model evaluation. To address this, we have developed a dedicated benchmark tailored to the CoPaw environment. This benchmark systematically evaluates model performance across five high-frequency usage scenarios, covering key operational dimensions.
|
| 43 |
+
|
| 44 |
+
Results indicate that CoPaw-Flash delivers substantial improvements across multiple task categories, achieving performance comparable to leading flagship models—all while maintaining significantly lower resource requirements.
|
| 45 |
+
|
| 46 |
+
<img src="https://img.alicdn.com/imgextra/i2/O1CN01uQsLX61XbwkjLtHuP_!!6000000002943-2-tps-1264-888.png" width="632" title="" crop="0,0,1,1" id="ufe625d3c" class="ne-image">
|
| 47 |
+
|
| 48 |
+
Figure 1: CoPaw-Flash-9B compared with other models.
|
| 49 |
+
|
| 50 |
+
<img src="https://img.alicdn.com/imgextra/i1/O1CN01OKDCHQ1yuic00Qmyu_!!6000000006639-2-tps-1984-975.png" width="628" title="" crop="0,0,1,1" id="u15257ae6" class="ne-image">
|
| 51 |
+
|
| 52 |
+
Figure 2: CoPaw-Flash-2B/4B/9B compared with their respective baseline models.
|
| 53 |
+
|
| 54 |
+
## Quickstart
|
| 55 |
+
### <font style="color:rgb(31, 35, 40);">Serving CoPaw-Flash</font>
|
| 56 |
+
CoPaw-Flash<font style="color:rgb(31, 35, 40);"> can be served via APIs using popular inference frameworks. Below are example commands to launch OpenAI-compatible API servers for CoPaw-Flash.</font>
|
| 57 |
+
|
| 58 |
+
#### <font style="color:rgb(31, 35, 40);">vLLM</font>
|
| 59 |
+
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Since CoPaw-Flash leverages the Qwen3.5 architecture, the latest vLLM version is required for optimal compatibility. You can install it in a fresh environment using:
|
| 60 |
+
|
| 61 |
+
```plain
|
| 62 |
+
uv pip install vllm --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly
|
| 63 |
+
```
|
| 64 |
+
|
| 65 |
+
**Note:** For more detailed usage guides and advanced configurations, please refer to the [vLLM Documentation](https://docs.vllm.ai/) and the [**Qwen3.5 Documentation**](https://qwen.readthedocs.io/).
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
The following command creates API endpoints at `http://localhost:8000/v1`. This example demonstrates launching the standard version with a maximum context length of 262,144 tokens using tensor parallelism across 8 GPUs.
|
| 70 |
+
|
| 71 |
+
Bash
|
| 72 |
+
|
| 73 |
+
```plain
|
| 74 |
+
vllm serve <your_model_path> \
|
| 75 |
+
--port 8000 \
|
| 76 |
+
--tensor-parallel-size 8 \
|
| 77 |
+
--max-model-len 262144 \
|
| 78 |
+
--reasoning-parser qwen3 \
|
| 79 |
+
--enable-auto-tool-choice \
|
| 80 |
+
--tool-call-parser qwen3_xml
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Using CoPaw-Flash via Chat Completions API
|
| 86 |
+
Once the server is running, you can access CoPaw-Flash via standard HTTP requests or OpenAI-compatible SDKs.
|
| 87 |
+
|
| 88 |
+
#### <font style="color:rgb(31, 35, 40);">Prerequisites</font>
|
| 89 |
+
Ensure the OpenAI Python SDK is installed and your environment variables are configured:
|
| 90 |
+
|
| 91 |
+
```plain
|
| 92 |
+
pip install -U openai
|
| 93 |
+
|
| 94 |
+
# Set the following accordingly
|
| 95 |
+
export OPENAI_BASE_URL="http://localhost:8000/v1"
|
| 96 |
+
export OPENAI_API_KEY="EMPTY"
|
| 97 |
+
```
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
#### Text-Only Input Example
|
| 102 |
+
The following Python script demonstrates how to interact with the model using the OpenAI SDK:
|
| 103 |
+
|
| 104 |
+
```plain
|
| 105 |
+
from openai import OpenAI
|
| 106 |
+
# Configured by environment variables
|
| 107 |
+
client = OpenAI()
|
| 108 |
+
|
| 109 |
+
messages = [
|
| 110 |
+
{"role": "user", "content": "Hello, Copaw!"},
|
| 111 |
+
]
|
| 112 |
+
|
| 113 |
+
chat_response = client.chat.completions.create(
|
| 114 |
+
model=<your_model_path>,
|
| 115 |
+
messages=messages,
|
| 116 |
+
max_tokens=81920,
|
| 117 |
+
temperature=1.0,
|
| 118 |
+
top_p=0.95,
|
| 119 |
+
presence_penalty=1.5,
|
| 120 |
+
extra_body={
|
| 121 |
+
"top_k": 20,
|
| 122 |
+
},
|
| 123 |
+
)
|
| 124 |
+
print("Chat response:", chat_response)
|
| 125 |
+
```
|
| 126 |
+
|
| 127 |
+
## Contact Us
|
| 128 |
+
CoPaw-Flash is developed by the AgentScope Team. If you would like to leave us a message, feel free to get in touch through the channels below.
|
| 129 |
+
|
| 130 |
+
| [Discord](https://discord.gg/eYMpfnkG8h) | [X (Twitter)](https://x.com/agentscope_ai) | [DingTalk](https://qr.dingtalk.com/action/joingroup?code=v1,k1,OmDlBXpjW+I2vWjKDsjvI9dhcXjGZi3bQiojOq3dlDw=&_dt_no_comment=1&origin=11) |
|
| 131 |
+
| ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
|
| 132 |
+
| [<img src="https://gw.alicdn.com/imgextra/i1/O1CN01hhD1mu1Dd3BWVUvxN_!!6000000000238-2-tps-400-400.png" width="80" height="80" alt="Discord">](https://discord.gg/eYMpfnkG8h) | [<img src="https://img.alicdn.com/imgextra/i4/O1CN01c0GOsa1UTkoxAGVvZ_!!6000000002519-2-tps-225-225.png" width="80" height="80" alt="X">](https://x.com/agentscope_ai) | [<img src="https://img.alicdn.com/imgextra/i2/O1CN01vCWI8a1skHtLGXEMQ_!!6000000005804-2-tps-458-460.png" width="80" height="80" alt="DingTalk">](https://qr.dingtalk.com/action/joingroup?code=v1,k1,OmDlBXpjW+I2vWjKDsjvI9dhcXjGZi3bQiojOq3dlDw=&_dt_no_comment=1&origin=11) |
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,648 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 248046,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 2560,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 9216,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"mlp_only_layers": [],
|
| 66 |
+
"model_type": "qwen3_5_text",
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_hidden_layers": 32,
|
| 71 |
+
"num_key_value_heads": 4,
|
| 72 |
+
"pad_token_id": null,
|
| 73 |
+
"partial_rotary_factor": 0.25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_parameters": {
|
| 76 |
+
"mrope_interleaved": true,
|
| 77 |
+
"mrope_section": [
|
| 78 |
+
11,
|
| 79 |
+
11,
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
"partial_rotary_factor": 0.25,
|
| 83 |
+
"rope_theta": 10000000,
|
| 84 |
+
"rope_type": "default"
|
| 85 |
+
},
|
| 86 |
+
"tie_word_embeddings": false,
|
| 87 |
+
"use_cache": true,
|
| 88 |
+
"vocab_size": 248320
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": false,
|
| 91 |
+
"transformers_version": "5.3.0",
|
| 92 |
+
"video_token_id": 248057,
|
| 93 |
+
"vision_config": {
|
| 94 |
+
"deepstack_visual_indexes": [],
|
| 95 |
+
"depth": 27,
|
| 96 |
+
"dtype": "bfloat16",
|
| 97 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 98 |
+
"hidden_size": 1024,
|
| 99 |
+
"in_channels": 3,
|
| 100 |
+
"initializer_range": 0.02,
|
| 101 |
+
"intermediate_size": 4096,
|
| 102 |
+
"model_type": "qwen3_5",
|
| 103 |
+
"num_heads": 16,
|
| 104 |
+
"num_position_embeddings": 2304,
|
| 105 |
+
"out_hidden_size": 2560,
|
| 106 |
+
"patch_size": 16,
|
| 107 |
+
"spatial_merge_size": 2,
|
| 108 |
+
"temporal_patch_size": 2
|
| 109 |
+
},
|
| 110 |
+
"vision_end_token_id": 248054,
|
| 111 |
+
"vision_start_token_id": 248053,
|
| 112 |
+
"quantization_config": {
|
| 113 |
+
"quant_method": "fp8",
|
| 114 |
+
"activation_scheme": "dynamic",
|
| 115 |
+
"weight_per_tensor": false,
|
| 116 |
+
"act_per_tensor": false,
|
| 117 |
+
"weight_block_size": [
|
| 118 |
+
128,
|
| 119 |
+
128
|
| 120 |
+
],
|
| 121 |
+
"modules_to_not_convert": [
|
| 122 |
+
"lm_head",
|
| 123 |
+
"model.language_model.embed_tokens",
|
| 124 |
+
"model.language_model.layers.0.input_layernorm",
|
| 125 |
+
"model.language_model.layers.0.linear_attn.A_log",
|
| 126 |
+
"model.language_model.layers.0.linear_attn.conv1d",
|
| 127 |
+
"model.language_model.layers.0.linear_attn.dt_bias",
|
| 128 |
+
"model.language_model.layers.0.linear_attn.in_proj_a",
|
| 129 |
+
"model.language_model.layers.0.linear_attn.in_proj_b",
|
| 130 |
+
"model.language_model.layers.0.linear_attn.norm",
|
| 131 |
+
"model.language_model.layers.0.post_attention_layernorm",
|
| 132 |
+
"model.language_model.layers.1.input_layernorm",
|
| 133 |
+
"model.language_model.layers.1.linear_attn.A_log",
|
| 134 |
+
"model.language_model.layers.1.linear_attn.conv1d",
|
| 135 |
+
"model.language_model.layers.1.linear_attn.dt_bias",
|
| 136 |
+
"model.language_model.layers.1.linear_attn.in_proj_a",
|
| 137 |
+
"model.language_model.layers.1.linear_attn.in_proj_b",
|
| 138 |
+
"model.language_model.layers.1.linear_attn.norm",
|
| 139 |
+
"model.language_model.layers.1.post_attention_layernorm",
|
| 140 |
+
"model.language_model.layers.10.input_layernorm",
|
| 141 |
+
"model.language_model.layers.10.linear_attn.A_log",
|
| 142 |
+
"model.language_model.layers.10.linear_attn.conv1d",
|
| 143 |
+
"model.language_model.layers.10.linear_attn.dt_bias",
|
| 144 |
+
"model.language_model.layers.10.linear_attn.in_proj_a",
|
| 145 |
+
"model.language_model.layers.10.linear_attn.in_proj_b",
|
| 146 |
+
"model.language_model.layers.10.linear_attn.norm",
|
| 147 |
+
"model.language_model.layers.10.post_attention_layernorm",
|
| 148 |
+
"model.language_model.layers.11.input_layernorm",
|
| 149 |
+
"model.language_model.layers.11.post_attention_layernorm",
|
| 150 |
+
"model.language_model.layers.11.self_attn.k_norm",
|
| 151 |
+
"model.language_model.layers.11.self_attn.q_norm",
|
| 152 |
+
"model.language_model.layers.12.input_layernorm",
|
| 153 |
+
"model.language_model.layers.12.linear_attn.A_log",
|
| 154 |
+
"model.language_model.layers.12.linear_attn.conv1d",
|
| 155 |
+
"model.language_model.layers.12.linear_attn.dt_bias",
|
| 156 |
+
"model.language_model.layers.12.linear_attn.in_proj_a",
|
| 157 |
+
"model.language_model.layers.12.linear_attn.in_proj_b",
|
| 158 |
+
"model.language_model.layers.12.linear_attn.norm",
|
| 159 |
+
"model.language_model.layers.12.post_attention_layernorm",
|
| 160 |
+
"model.language_model.layers.13.input_layernorm",
|
| 161 |
+
"model.language_model.layers.13.linear_attn.A_log",
|
| 162 |
+
"model.language_model.layers.13.linear_attn.conv1d",
|
| 163 |
+
"model.language_model.layers.13.linear_attn.dt_bias",
|
| 164 |
+
"model.language_model.layers.13.linear_attn.in_proj_a",
|
| 165 |
+
"model.language_model.layers.13.linear_attn.in_proj_b",
|
| 166 |
+
"model.language_model.layers.13.linear_attn.norm",
|
| 167 |
+
"model.language_model.layers.13.post_attention_layernorm",
|
| 168 |
+
"model.language_model.layers.14.input_layernorm",
|
| 169 |
+
"model.language_model.layers.14.linear_attn.A_log",
|
| 170 |
+
"model.language_model.layers.14.linear_attn.conv1d",
|
| 171 |
+
"model.language_model.layers.14.linear_attn.dt_bias",
|
| 172 |
+
"model.language_model.layers.14.linear_attn.in_proj_a",
|
| 173 |
+
"model.language_model.layers.14.linear_attn.in_proj_b",
|
| 174 |
+
"model.language_model.layers.14.linear_attn.norm",
|
| 175 |
+
"model.language_model.layers.14.post_attention_layernorm",
|
| 176 |
+
"model.language_model.layers.15.input_layernorm",
|
| 177 |
+
"model.language_model.layers.15.post_attention_layernorm",
|
| 178 |
+
"model.language_model.layers.15.self_attn.k_norm",
|
| 179 |
+
"model.language_model.layers.15.self_attn.q_norm",
|
| 180 |
+
"model.language_model.layers.16.input_layernorm",
|
| 181 |
+
"model.language_model.layers.16.linear_attn.A_log",
|
| 182 |
+
"model.language_model.layers.16.linear_attn.conv1d",
|
| 183 |
+
"model.language_model.layers.16.linear_attn.dt_bias",
|
| 184 |
+
"model.language_model.layers.16.linear_attn.in_proj_a",
|
| 185 |
+
"model.language_model.layers.16.linear_attn.in_proj_b",
|
| 186 |
+
"model.language_model.layers.16.linear_attn.norm",
|
| 187 |
+
"model.language_model.layers.16.post_attention_layernorm",
|
| 188 |
+
"model.language_model.layers.17.input_layernorm",
|
| 189 |
+
"model.language_model.layers.17.linear_attn.A_log",
|
| 190 |
+
"model.language_model.layers.17.linear_attn.conv1d",
|
| 191 |
+
"model.language_model.layers.17.linear_attn.dt_bias",
|
| 192 |
+
"model.language_model.layers.17.linear_attn.in_proj_a",
|
| 193 |
+
"model.language_model.layers.17.linear_attn.in_proj_b",
|
| 194 |
+
"model.language_model.layers.17.linear_attn.norm",
|
| 195 |
+
"model.language_model.layers.17.post_attention_layernorm",
|
| 196 |
+
"model.language_model.layers.18.input_layernorm",
|
| 197 |
+
"model.language_model.layers.18.linear_attn.A_log",
|
| 198 |
+
"model.language_model.layers.18.linear_attn.conv1d",
|
| 199 |
+
"model.language_model.layers.18.linear_attn.dt_bias",
|
| 200 |
+
"model.language_model.layers.18.linear_attn.in_proj_a",
|
| 201 |
+
"model.language_model.layers.18.linear_attn.in_proj_b",
|
| 202 |
+
"model.language_model.layers.18.linear_attn.norm",
|
| 203 |
+
"model.language_model.layers.18.post_attention_layernorm",
|
| 204 |
+
"model.language_model.layers.19.input_layernorm",
|
| 205 |
+
"model.language_model.layers.19.post_attention_layernorm",
|
| 206 |
+
"model.language_model.layers.19.self_attn.k_norm",
|
| 207 |
+
"model.language_model.layers.19.self_attn.q_norm",
|
| 208 |
+
"model.language_model.layers.2.input_layernorm",
|
| 209 |
+
"model.language_model.layers.2.linear_attn.A_log",
|
| 210 |
+
"model.language_model.layers.2.linear_attn.conv1d",
|
| 211 |
+
"model.language_model.layers.2.linear_attn.dt_bias",
|
| 212 |
+
"model.language_model.layers.2.linear_attn.in_proj_a",
|
| 213 |
+
"model.language_model.layers.2.linear_attn.in_proj_b",
|
| 214 |
+
"model.language_model.layers.2.linear_attn.norm",
|
| 215 |
+
"model.language_model.layers.2.post_attention_layernorm",
|
| 216 |
+
"model.language_model.layers.20.input_layernorm",
|
| 217 |
+
"model.language_model.layers.20.linear_attn.A_log",
|
| 218 |
+
"model.language_model.layers.20.linear_attn.conv1d",
|
| 219 |
+
"model.language_model.layers.20.linear_attn.dt_bias",
|
| 220 |
+
"model.language_model.layers.20.linear_attn.in_proj_a",
|
| 221 |
+
"model.language_model.layers.20.linear_attn.in_proj_b",
|
| 222 |
+
"model.language_model.layers.20.linear_attn.norm",
|
| 223 |
+
"model.language_model.layers.20.post_attention_layernorm",
|
| 224 |
+
"model.language_model.layers.21.input_layernorm",
|
| 225 |
+
"model.language_model.layers.21.linear_attn.A_log",
|
| 226 |
+
"model.language_model.layers.21.linear_attn.conv1d",
|
| 227 |
+
"model.language_model.layers.21.linear_attn.dt_bias",
|
| 228 |
+
"model.language_model.layers.21.linear_attn.in_proj_a",
|
| 229 |
+
"model.language_model.layers.21.linear_attn.in_proj_b",
|
| 230 |
+
"model.language_model.layers.21.linear_attn.norm",
|
| 231 |
+
"model.language_model.layers.21.post_attention_layernorm",
|
| 232 |
+
"model.language_model.layers.22.input_layernorm",
|
| 233 |
+
"model.language_model.layers.22.linear_attn.A_log",
|
| 234 |
+
"model.language_model.layers.22.linear_attn.conv1d",
|
| 235 |
+
"model.language_model.layers.22.linear_attn.dt_bias",
|
| 236 |
+
"model.language_model.layers.22.linear_attn.in_proj_a",
|
| 237 |
+
"model.language_model.layers.22.linear_attn.in_proj_b",
|
| 238 |
+
"model.language_model.layers.22.linear_attn.norm",
|
| 239 |
+
"model.language_model.layers.22.post_attention_layernorm",
|
| 240 |
+
"model.language_model.layers.23.input_layernorm",
|
| 241 |
+
"model.language_model.layers.23.post_attention_layernorm",
|
| 242 |
+
"model.language_model.layers.23.self_attn.k_norm",
|
| 243 |
+
"model.language_model.layers.23.self_attn.q_norm",
|
| 244 |
+
"model.language_model.layers.24.input_layernorm",
|
| 245 |
+
"model.language_model.layers.24.linear_attn.A_log",
|
| 246 |
+
"model.language_model.layers.24.linear_attn.conv1d",
|
| 247 |
+
"model.language_model.layers.24.linear_attn.dt_bias",
|
| 248 |
+
"model.language_model.layers.24.linear_attn.in_proj_a",
|
| 249 |
+
"model.language_model.layers.24.linear_attn.in_proj_b",
|
| 250 |
+
"model.language_model.layers.24.linear_attn.norm",
|
| 251 |
+
"model.language_model.layers.24.post_attention_layernorm",
|
| 252 |
+
"model.language_model.layers.25.input_layernorm",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.A_log",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.conv1d",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.dt_bias",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.in_proj_a",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.in_proj_b",
|
| 258 |
+
"model.language_model.layers.25.linear_attn.norm",
|
| 259 |
+
"model.language_model.layers.25.post_attention_layernorm",
|
| 260 |
+
"model.language_model.layers.26.input_layernorm",
|
| 261 |
+
"model.language_model.layers.26.linear_attn.A_log",
|
| 262 |
+
"model.language_model.layers.26.linear_attn.conv1d",
|
| 263 |
+
"model.language_model.layers.26.linear_attn.dt_bias",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.in_proj_a",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.in_proj_b",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.norm",
|
| 267 |
+
"model.language_model.layers.26.post_attention_layernorm",
|
| 268 |
+
"model.language_model.layers.27.input_layernorm",
|
| 269 |
+
"model.language_model.layers.27.post_attention_layernorm",
|
| 270 |
+
"model.language_model.layers.27.self_attn.k_norm",
|
| 271 |
+
"model.language_model.layers.27.self_attn.q_norm",
|
| 272 |
+
"model.language_model.layers.28.input_layernorm",
|
| 273 |
+
"model.language_model.layers.28.linear_attn.A_log",
|
| 274 |
+
"model.language_model.layers.28.linear_attn.conv1d",
|
| 275 |
+
"model.language_model.layers.28.linear_attn.dt_bias",
|
| 276 |
+
"model.language_model.layers.28.linear_attn.in_proj_a",
|
| 277 |
+
"model.language_model.layers.28.linear_attn.in_proj_b",
|
| 278 |
+
"model.language_model.layers.28.linear_attn.norm",
|
| 279 |
+
"model.language_model.layers.28.post_attention_layernorm",
|
| 280 |
+
"model.language_model.layers.29.input_layernorm",
|
| 281 |
+
"model.language_model.layers.29.linear_attn.A_log",
|
| 282 |
+
"model.language_model.layers.29.linear_attn.conv1d",
|
| 283 |
+
"model.language_model.layers.29.linear_attn.dt_bias",
|
| 284 |
+
"model.language_model.layers.29.linear_attn.in_proj_a",
|
| 285 |
+
"model.language_model.layers.29.linear_attn.in_proj_b",
|
| 286 |
+
"model.language_model.layers.29.linear_attn.norm",
|
| 287 |
+
"model.language_model.layers.29.post_attention_layernorm",
|
| 288 |
+
"model.language_model.layers.3.input_layernorm",
|
| 289 |
+
"model.language_model.layers.3.post_attention_layernorm",
|
| 290 |
+
"model.language_model.layers.3.self_attn.k_norm",
|
| 291 |
+
"model.language_model.layers.3.self_attn.q_norm",
|
| 292 |
+
"model.language_model.layers.30.input_layernorm",
|
| 293 |
+
"model.language_model.layers.30.linear_attn.A_log",
|
| 294 |
+
"model.language_model.layers.30.linear_attn.conv1d",
|
| 295 |
+
"model.language_model.layers.30.linear_attn.dt_bias",
|
| 296 |
+
"model.language_model.layers.30.linear_attn.in_proj_a",
|
| 297 |
+
"model.language_model.layers.30.linear_attn.in_proj_b",
|
| 298 |
+
"model.language_model.layers.30.linear_attn.norm",
|
| 299 |
+
"model.language_model.layers.30.post_attention_layernorm",
|
| 300 |
+
"model.language_model.layers.31.input_layernorm",
|
| 301 |
+
"model.language_model.layers.31.post_attention_layernorm",
|
| 302 |
+
"model.language_model.layers.31.self_attn.k_norm",
|
| 303 |
+
"model.language_model.layers.31.self_attn.q_norm",
|
| 304 |
+
"model.language_model.layers.4.input_layernorm",
|
| 305 |
+
"model.language_model.layers.4.linear_attn.A_log",
|
| 306 |
+
"model.language_model.layers.4.linear_attn.conv1d",
|
| 307 |
+
"model.language_model.layers.4.linear_attn.dt_bias",
|
| 308 |
+
"model.language_model.layers.4.linear_attn.in_proj_a",
|
| 309 |
+
"model.language_model.layers.4.linear_attn.in_proj_b",
|
| 310 |
+
"model.language_model.layers.4.linear_attn.norm",
|
| 311 |
+
"model.language_model.layers.4.post_attention_layernorm",
|
| 312 |
+
"model.language_model.layers.5.input_layernorm",
|
| 313 |
+
"model.language_model.layers.5.linear_attn.A_log",
|
| 314 |
+
"model.language_model.layers.5.linear_attn.conv1d",
|
| 315 |
+
"model.language_model.layers.5.linear_attn.dt_bias",
|
| 316 |
+
"model.language_model.layers.5.linear_attn.in_proj_a",
|
| 317 |
+
"model.language_model.layers.5.linear_attn.in_proj_b",
|
| 318 |
+
"model.language_model.layers.5.linear_attn.norm",
|
| 319 |
+
"model.language_model.layers.5.post_attention_layernorm",
|
| 320 |
+
"model.language_model.layers.6.input_layernorm",
|
| 321 |
+
"model.language_model.layers.6.linear_attn.A_log",
|
| 322 |
+
"model.language_model.layers.6.linear_attn.conv1d",
|
| 323 |
+
"model.language_model.layers.6.linear_attn.dt_bias",
|
| 324 |
+
"model.language_model.layers.6.linear_attn.in_proj_a",
|
| 325 |
+
"model.language_model.layers.6.linear_attn.in_proj_b",
|
| 326 |
+
"model.language_model.layers.6.linear_attn.norm",
|
| 327 |
+
"model.language_model.layers.6.post_attention_layernorm",
|
| 328 |
+
"model.language_model.layers.7.input_layernorm",
|
| 329 |
+
"model.language_model.layers.7.post_attention_layernorm",
|
| 330 |
+
"model.language_model.layers.7.self_attn.k_norm",
|
| 331 |
+
"model.language_model.layers.7.self_attn.q_norm",
|
| 332 |
+
"model.language_model.layers.8.input_layernorm",
|
| 333 |
+
"model.language_model.layers.8.linear_attn.A_log",
|
| 334 |
+
"model.language_model.layers.8.linear_attn.conv1d",
|
| 335 |
+
"model.language_model.layers.8.linear_attn.dt_bias",
|
| 336 |
+
"model.language_model.layers.8.linear_attn.in_proj_a",
|
| 337 |
+
"model.language_model.layers.8.linear_attn.in_proj_b",
|
| 338 |
+
"model.language_model.layers.8.linear_attn.norm",
|
| 339 |
+
"model.language_model.layers.8.post_attention_layernorm",
|
| 340 |
+
"model.language_model.layers.9.input_layernorm",
|
| 341 |
+
"model.language_model.layers.9.linear_attn.A_log",
|
| 342 |
+
"model.language_model.layers.9.linear_attn.conv1d",
|
| 343 |
+
"model.language_model.layers.9.linear_attn.dt_bias",
|
| 344 |
+
"model.language_model.layers.9.linear_attn.in_proj_a",
|
| 345 |
+
"model.language_model.layers.9.linear_attn.in_proj_b",
|
| 346 |
+
"model.language_model.layers.9.linear_attn.norm",
|
| 347 |
+
"model.language_model.layers.9.post_attention_layernorm",
|
| 348 |
+
"model.language_model.norm",
|
| 349 |
+
"model.visual.blocks.0.attn.proj",
|
| 350 |
+
"model.visual.blocks.0.attn.proj.bias",
|
| 351 |
+
"model.visual.blocks.0.attn.qkv",
|
| 352 |
+
"model.visual.blocks.0.attn.qkv.bias",
|
| 353 |
+
"model.visual.blocks.0.mlp.linear_fc1",
|
| 354 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias",
|
| 355 |
+
"model.visual.blocks.0.mlp.linear_fc2",
|
| 356 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias",
|
| 357 |
+
"model.visual.blocks.0.norm1",
|
| 358 |
+
"model.visual.blocks.0.norm1.bias",
|
| 359 |
+
"model.visual.blocks.0.norm2",
|
| 360 |
+
"model.visual.blocks.0.norm2.bias",
|
| 361 |
+
"model.visual.blocks.1.attn.proj",
|
| 362 |
+
"model.visual.blocks.1.attn.proj.bias",
|
| 363 |
+
"model.visual.blocks.1.attn.qkv",
|
| 364 |
+
"model.visual.blocks.1.attn.qkv.bias",
|
| 365 |
+
"model.visual.blocks.1.mlp.linear_fc1",
|
| 366 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias",
|
| 367 |
+
"model.visual.blocks.1.mlp.linear_fc2",
|
| 368 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias",
|
| 369 |
+
"model.visual.blocks.1.norm1",
|
| 370 |
+
"model.visual.blocks.1.norm1.bias",
|
| 371 |
+
"model.visual.blocks.1.norm2",
|
| 372 |
+
"model.visual.blocks.1.norm2.bias",
|
| 373 |
+
"model.visual.blocks.10.attn.proj",
|
| 374 |
+
"model.visual.blocks.10.attn.proj.bias",
|
| 375 |
+
"model.visual.blocks.10.attn.qkv",
|
| 376 |
+
"model.visual.blocks.10.attn.qkv.bias",
|
| 377 |
+
"model.visual.blocks.10.mlp.linear_fc1",
|
| 378 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias",
|
| 379 |
+
"model.visual.blocks.10.mlp.linear_fc2",
|
| 380 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias",
|
| 381 |
+
"model.visual.blocks.10.norm1",
|
| 382 |
+
"model.visual.blocks.10.norm1.bias",
|
| 383 |
+
"model.visual.blocks.10.norm2",
|
| 384 |
+
"model.visual.blocks.10.norm2.bias",
|
| 385 |
+
"model.visual.blocks.11.attn.proj",
|
| 386 |
+
"model.visual.blocks.11.attn.proj.bias",
|
| 387 |
+
"model.visual.blocks.11.attn.qkv",
|
| 388 |
+
"model.visual.blocks.11.attn.qkv.bias",
|
| 389 |
+
"model.visual.blocks.11.mlp.linear_fc1",
|
| 390 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias",
|
| 391 |
+
"model.visual.blocks.11.mlp.linear_fc2",
|
| 392 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias",
|
| 393 |
+
"model.visual.blocks.11.norm1",
|
| 394 |
+
"model.visual.blocks.11.norm1.bias",
|
| 395 |
+
"model.visual.blocks.11.norm2",
|
| 396 |
+
"model.visual.blocks.11.norm2.bias",
|
| 397 |
+
"model.visual.blocks.12.attn.proj",
|
| 398 |
+
"model.visual.blocks.12.attn.proj.bias",
|
| 399 |
+
"model.visual.blocks.12.attn.qkv",
|
| 400 |
+
"model.visual.blocks.12.attn.qkv.bias",
|
| 401 |
+
"model.visual.blocks.12.mlp.linear_fc1",
|
| 402 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias",
|
| 403 |
+
"model.visual.blocks.12.mlp.linear_fc2",
|
| 404 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias",
|
| 405 |
+
"model.visual.blocks.12.norm1",
|
| 406 |
+
"model.visual.blocks.12.norm1.bias",
|
| 407 |
+
"model.visual.blocks.12.norm2",
|
| 408 |
+
"model.visual.blocks.12.norm2.bias",
|
| 409 |
+
"model.visual.blocks.13.attn.proj",
|
| 410 |
+
"model.visual.blocks.13.attn.proj.bias",
|
| 411 |
+
"model.visual.blocks.13.attn.qkv",
|
| 412 |
+
"model.visual.blocks.13.attn.qkv.bias",
|
| 413 |
+
"model.visual.blocks.13.mlp.linear_fc1",
|
| 414 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias",
|
| 415 |
+
"model.visual.blocks.13.mlp.linear_fc2",
|
| 416 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias",
|
| 417 |
+
"model.visual.blocks.13.norm1",
|
| 418 |
+
"model.visual.blocks.13.norm1.bias",
|
| 419 |
+
"model.visual.blocks.13.norm2",
|
| 420 |
+
"model.visual.blocks.13.norm2.bias",
|
| 421 |
+
"model.visual.blocks.14.attn.proj",
|
| 422 |
+
"model.visual.blocks.14.attn.proj.bias",
|
| 423 |
+
"model.visual.blocks.14.attn.qkv",
|
| 424 |
+
"model.visual.blocks.14.attn.qkv.bias",
|
| 425 |
+
"model.visual.blocks.14.mlp.linear_fc1",
|
| 426 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias",
|
| 427 |
+
"model.visual.blocks.14.mlp.linear_fc2",
|
| 428 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias",
|
| 429 |
+
"model.visual.blocks.14.norm1",
|
| 430 |
+
"model.visual.blocks.14.norm1.bias",
|
| 431 |
+
"model.visual.blocks.14.norm2",
|
| 432 |
+
"model.visual.blocks.14.norm2.bias",
|
| 433 |
+
"model.visual.blocks.15.attn.proj",
|
| 434 |
+
"model.visual.blocks.15.attn.proj.bias",
|
| 435 |
+
"model.visual.blocks.15.attn.qkv",
|
| 436 |
+
"model.visual.blocks.15.attn.qkv.bias",
|
| 437 |
+
"model.visual.blocks.15.mlp.linear_fc1",
|
| 438 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias",
|
| 439 |
+
"model.visual.blocks.15.mlp.linear_fc2",
|
| 440 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias",
|
| 441 |
+
"model.visual.blocks.15.norm1",
|
| 442 |
+
"model.visual.blocks.15.norm1.bias",
|
| 443 |
+
"model.visual.blocks.15.norm2",
|
| 444 |
+
"model.visual.blocks.15.norm2.bias",
|
| 445 |
+
"model.visual.blocks.16.attn.proj",
|
| 446 |
+
"model.visual.blocks.16.attn.proj.bias",
|
| 447 |
+
"model.visual.blocks.16.attn.qkv",
|
| 448 |
+
"model.visual.blocks.16.attn.qkv.bias",
|
| 449 |
+
"model.visual.blocks.16.mlp.linear_fc1",
|
| 450 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias",
|
| 451 |
+
"model.visual.blocks.16.mlp.linear_fc2",
|
| 452 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias",
|
| 453 |
+
"model.visual.blocks.16.norm1",
|
| 454 |
+
"model.visual.blocks.16.norm1.bias",
|
| 455 |
+
"model.visual.blocks.16.norm2",
|
| 456 |
+
"model.visual.blocks.16.norm2.bias",
|
| 457 |
+
"model.visual.blocks.17.attn.proj",
|
| 458 |
+
"model.visual.blocks.17.attn.proj.bias",
|
| 459 |
+
"model.visual.blocks.17.attn.qkv",
|
| 460 |
+
"model.visual.blocks.17.attn.qkv.bias",
|
| 461 |
+
"model.visual.blocks.17.mlp.linear_fc1",
|
| 462 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias",
|
| 463 |
+
"model.visual.blocks.17.mlp.linear_fc2",
|
| 464 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias",
|
| 465 |
+
"model.visual.blocks.17.norm1",
|
| 466 |
+
"model.visual.blocks.17.norm1.bias",
|
| 467 |
+
"model.visual.blocks.17.norm2",
|
| 468 |
+
"model.visual.blocks.17.norm2.bias",
|
| 469 |
+
"model.visual.blocks.18.attn.proj",
|
| 470 |
+
"model.visual.blocks.18.attn.proj.bias",
|
| 471 |
+
"model.visual.blocks.18.attn.qkv",
|
| 472 |
+
"model.visual.blocks.18.attn.qkv.bias",
|
| 473 |
+
"model.visual.blocks.18.mlp.linear_fc1",
|
| 474 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias",
|
| 475 |
+
"model.visual.blocks.18.mlp.linear_fc2",
|
| 476 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias",
|
| 477 |
+
"model.visual.blocks.18.norm1",
|
| 478 |
+
"model.visual.blocks.18.norm1.bias",
|
| 479 |
+
"model.visual.blocks.18.norm2",
|
| 480 |
+
"model.visual.blocks.18.norm2.bias",
|
| 481 |
+
"model.visual.blocks.19.attn.proj",
|
| 482 |
+
"model.visual.blocks.19.attn.proj.bias",
|
| 483 |
+
"model.visual.blocks.19.attn.qkv",
|
| 484 |
+
"model.visual.blocks.19.attn.qkv.bias",
|
| 485 |
+
"model.visual.blocks.19.mlp.linear_fc1",
|
| 486 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias",
|
| 487 |
+
"model.visual.blocks.19.mlp.linear_fc2",
|
| 488 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias",
|
| 489 |
+
"model.visual.blocks.19.norm1",
|
| 490 |
+
"model.visual.blocks.19.norm1.bias",
|
| 491 |
+
"model.visual.blocks.19.norm2",
|
| 492 |
+
"model.visual.blocks.19.norm2.bias",
|
| 493 |
+
"model.visual.blocks.2.attn.proj",
|
| 494 |
+
"model.visual.blocks.2.attn.proj.bias",
|
| 495 |
+
"model.visual.blocks.2.attn.qkv",
|
| 496 |
+
"model.visual.blocks.2.attn.qkv.bias",
|
| 497 |
+
"model.visual.blocks.2.mlp.linear_fc1",
|
| 498 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias",
|
| 499 |
+
"model.visual.blocks.2.mlp.linear_fc2",
|
| 500 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias",
|
| 501 |
+
"model.visual.blocks.2.norm1",
|
| 502 |
+
"model.visual.blocks.2.norm1.bias",
|
| 503 |
+
"model.visual.blocks.2.norm2",
|
| 504 |
+
"model.visual.blocks.2.norm2.bias",
|
| 505 |
+
"model.visual.blocks.20.attn.proj",
|
| 506 |
+
"model.visual.blocks.20.attn.proj.bias",
|
| 507 |
+
"model.visual.blocks.20.attn.qkv",
|
| 508 |
+
"model.visual.blocks.20.attn.qkv.bias",
|
| 509 |
+
"model.visual.blocks.20.mlp.linear_fc1",
|
| 510 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias",
|
| 511 |
+
"model.visual.blocks.20.mlp.linear_fc2",
|
| 512 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias",
|
| 513 |
+
"model.visual.blocks.20.norm1",
|
| 514 |
+
"model.visual.blocks.20.norm1.bias",
|
| 515 |
+
"model.visual.blocks.20.norm2",
|
| 516 |
+
"model.visual.blocks.20.norm2.bias",
|
| 517 |
+
"model.visual.blocks.21.attn.proj",
|
| 518 |
+
"model.visual.blocks.21.attn.proj.bias",
|
| 519 |
+
"model.visual.blocks.21.attn.qkv",
|
| 520 |
+
"model.visual.blocks.21.attn.qkv.bias",
|
| 521 |
+
"model.visual.blocks.21.mlp.linear_fc1",
|
| 522 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias",
|
| 523 |
+
"model.visual.blocks.21.mlp.linear_fc2",
|
| 524 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias",
|
| 525 |
+
"model.visual.blocks.21.norm1",
|
| 526 |
+
"model.visual.blocks.21.norm1.bias",
|
| 527 |
+
"model.visual.blocks.21.norm2",
|
| 528 |
+
"model.visual.blocks.21.norm2.bias",
|
| 529 |
+
"model.visual.blocks.22.attn.proj",
|
| 530 |
+
"model.visual.blocks.22.attn.proj.bias",
|
| 531 |
+
"model.visual.blocks.22.attn.qkv",
|
| 532 |
+
"model.visual.blocks.22.attn.qkv.bias",
|
| 533 |
+
"model.visual.blocks.22.mlp.linear_fc1",
|
| 534 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias",
|
| 535 |
+
"model.visual.blocks.22.mlp.linear_fc2",
|
| 536 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias",
|
| 537 |
+
"model.visual.blocks.22.norm1",
|
| 538 |
+
"model.visual.blocks.22.norm1.bias",
|
| 539 |
+
"model.visual.blocks.22.norm2",
|
| 540 |
+
"model.visual.blocks.22.norm2.bias",
|
| 541 |
+
"model.visual.blocks.23.attn.proj",
|
| 542 |
+
"model.visual.blocks.23.attn.proj.bias",
|
| 543 |
+
"model.visual.blocks.23.attn.qkv",
|
| 544 |
+
"model.visual.blocks.23.attn.qkv.bias",
|
| 545 |
+
"model.visual.blocks.23.mlp.linear_fc1",
|
| 546 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias",
|
| 547 |
+
"model.visual.blocks.23.mlp.linear_fc2",
|
| 548 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias",
|
| 549 |
+
"model.visual.blocks.23.norm1",
|
| 550 |
+
"model.visual.blocks.23.norm1.bias",
|
| 551 |
+
"model.visual.blocks.23.norm2",
|
| 552 |
+
"model.visual.blocks.23.norm2.bias",
|
| 553 |
+
"model.visual.blocks.3.attn.proj",
|
| 554 |
+
"model.visual.blocks.3.attn.proj.bias",
|
| 555 |
+
"model.visual.blocks.3.attn.qkv",
|
| 556 |
+
"model.visual.blocks.3.attn.qkv.bias",
|
| 557 |
+
"model.visual.blocks.3.mlp.linear_fc1",
|
| 558 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias",
|
| 559 |
+
"model.visual.blocks.3.mlp.linear_fc2",
|
| 560 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias",
|
| 561 |
+
"model.visual.blocks.3.norm1",
|
| 562 |
+
"model.visual.blocks.3.norm1.bias",
|
| 563 |
+
"model.visual.blocks.3.norm2",
|
| 564 |
+
"model.visual.blocks.3.norm2.bias",
|
| 565 |
+
"model.visual.blocks.4.attn.proj",
|
| 566 |
+
"model.visual.blocks.4.attn.proj.bias",
|
| 567 |
+
"model.visual.blocks.4.attn.qkv",
|
| 568 |
+
"model.visual.blocks.4.attn.qkv.bias",
|
| 569 |
+
"model.visual.blocks.4.mlp.linear_fc1",
|
| 570 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias",
|
| 571 |
+
"model.visual.blocks.4.mlp.linear_fc2",
|
| 572 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias",
|
| 573 |
+
"model.visual.blocks.4.norm1",
|
| 574 |
+
"model.visual.blocks.4.norm1.bias",
|
| 575 |
+
"model.visual.blocks.4.norm2",
|
| 576 |
+
"model.visual.blocks.4.norm2.bias",
|
| 577 |
+
"model.visual.blocks.5.attn.proj",
|
| 578 |
+
"model.visual.blocks.5.attn.proj.bias",
|
| 579 |
+
"model.visual.blocks.5.attn.qkv",
|
| 580 |
+
"model.visual.blocks.5.attn.qkv.bias",
|
| 581 |
+
"model.visual.blocks.5.mlp.linear_fc1",
|
| 582 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias",
|
| 583 |
+
"model.visual.blocks.5.mlp.linear_fc2",
|
| 584 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias",
|
| 585 |
+
"model.visual.blocks.5.norm1",
|
| 586 |
+
"model.visual.blocks.5.norm1.bias",
|
| 587 |
+
"model.visual.blocks.5.norm2",
|
| 588 |
+
"model.visual.blocks.5.norm2.bias",
|
| 589 |
+
"model.visual.blocks.6.attn.proj",
|
| 590 |
+
"model.visual.blocks.6.attn.proj.bias",
|
| 591 |
+
"model.visual.blocks.6.attn.qkv",
|
| 592 |
+
"model.visual.blocks.6.attn.qkv.bias",
|
| 593 |
+
"model.visual.blocks.6.mlp.linear_fc1",
|
| 594 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias",
|
| 595 |
+
"model.visual.blocks.6.mlp.linear_fc2",
|
| 596 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias",
|
| 597 |
+
"model.visual.blocks.6.norm1",
|
| 598 |
+
"model.visual.blocks.6.norm1.bias",
|
| 599 |
+
"model.visual.blocks.6.norm2",
|
| 600 |
+
"model.visual.blocks.6.norm2.bias",
|
| 601 |
+
"model.visual.blocks.7.attn.proj",
|
| 602 |
+
"model.visual.blocks.7.attn.proj.bias",
|
| 603 |
+
"model.visual.blocks.7.attn.qkv",
|
| 604 |
+
"model.visual.blocks.7.attn.qkv.bias",
|
| 605 |
+
"model.visual.blocks.7.mlp.linear_fc1",
|
| 606 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias",
|
| 607 |
+
"model.visual.blocks.7.mlp.linear_fc2",
|
| 608 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias",
|
| 609 |
+
"model.visual.blocks.7.norm1",
|
| 610 |
+
"model.visual.blocks.7.norm1.bias",
|
| 611 |
+
"model.visual.blocks.7.norm2",
|
| 612 |
+
"model.visual.blocks.7.norm2.bias",
|
| 613 |
+
"model.visual.blocks.8.attn.proj",
|
| 614 |
+
"model.visual.blocks.8.attn.proj.bias",
|
| 615 |
+
"model.visual.blocks.8.attn.qkv",
|
| 616 |
+
"model.visual.blocks.8.attn.qkv.bias",
|
| 617 |
+
"model.visual.blocks.8.mlp.linear_fc1",
|
| 618 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias",
|
| 619 |
+
"model.visual.blocks.8.mlp.linear_fc2",
|
| 620 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias",
|
| 621 |
+
"model.visual.blocks.8.norm1",
|
| 622 |
+
"model.visual.blocks.8.norm1.bias",
|
| 623 |
+
"model.visual.blocks.8.norm2",
|
| 624 |
+
"model.visual.blocks.8.norm2.bias",
|
| 625 |
+
"model.visual.blocks.9.attn.proj",
|
| 626 |
+
"model.visual.blocks.9.attn.proj.bias",
|
| 627 |
+
"model.visual.blocks.9.attn.qkv",
|
| 628 |
+
"model.visual.blocks.9.attn.qkv.bias",
|
| 629 |
+
"model.visual.blocks.9.mlp.linear_fc1",
|
| 630 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias",
|
| 631 |
+
"model.visual.blocks.9.mlp.linear_fc2",
|
| 632 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias",
|
| 633 |
+
"model.visual.blocks.9.norm1",
|
| 634 |
+
"model.visual.blocks.9.norm1.bias",
|
| 635 |
+
"model.visual.blocks.9.norm2",
|
| 636 |
+
"model.visual.blocks.9.norm2.bias",
|
| 637 |
+
"model.visual.merger.linear_fc1",
|
| 638 |
+
"model.visual.merger.linear_fc1.bias",
|
| 639 |
+
"model.visual.merger.linear_fc2",
|
| 640 |
+
"model.visual.merger.linear_fc2.bias",
|
| 641 |
+
"model.visual.merger.norm",
|
| 642 |
+
"model.visual.merger.norm.bias",
|
| 643 |
+
"model.visual.patch_embed.proj",
|
| 644 |
+
"model.visual.patch_embed.proj.bias",
|
| 645 |
+
"model.visual.pos_embed"
|
| 646 |
+
]
|
| 647 |
+
}
|
| 648 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 248046,
|
| 4 |
+
"output_attentions": false,
|
| 5 |
+
"output_hidden_states": false,
|
| 6 |
+
"pad_token_id": 248044,
|
| 7 |
+
"transformers_version": "5.3.0",
|
| 8 |
+
"use_cache": true,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"min_p": 0.0,
|
| 13 |
+
"presence_penalty": 1.5,
|
| 14 |
+
"repetition_penalty": 1.0
|
| 15 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca8cdb7defa9c3237eae3355ca259ee6bb0038cd9cc682096f7b4bc4f029d495
|
| 3 |
+
size 6785324152
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,928 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"weight_map": {
|
| 3 |
+
"lm_head.weight": "model.safetensors",
|
| 4 |
+
"model.language_model.embed_tokens.weight": "model.safetensors",
|
| 5 |
+
"model.language_model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 6 |
+
"model.language_model.layers.0.linear_attn.A_log": "model.safetensors",
|
| 7 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model.safetensors",
|
| 8 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 15 |
+
"model.language_model.layers.0.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 16 |
+
"model.language_model.layers.0.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 17 |
+
"model.language_model.layers.0.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 18 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 19 |
+
"model.language_model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 20 |
+
"model.language_model.layers.1.linear_attn.A_log": "model.safetensors",
|
| 21 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model.safetensors",
|
| 22 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model.safetensors",
|
| 23 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 29 |
+
"model.language_model.layers.1.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 30 |
+
"model.language_model.layers.1.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 31 |
+
"model.language_model.layers.1.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 32 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 33 |
+
"model.language_model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 34 |
+
"model.language_model.layers.10.linear_attn.A_log": "model.safetensors",
|
| 35 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model.safetensors",
|
| 36 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model.safetensors",
|
| 37 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 43 |
+
"model.language_model.layers.10.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 44 |
+
"model.language_model.layers.10.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 45 |
+
"model.language_model.layers.10.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 46 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 47 |
+
"model.language_model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 48 |
+
"model.language_model.layers.11.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 49 |
+
"model.language_model.layers.11.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 50 |
+
"model.language_model.layers.11.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 51 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model.safetensors",
|
| 53 |
+
"model.language_model.layers.11.self_attn.k_proj.weight_scale_inv": "model.safetensors",
|
| 54 |
+
"model.language_model.layers.11.self_attn.o_proj.weight_scale_inv": "model.safetensors",
|
| 55 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.q_proj.weight_scale_inv": "model.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.v_proj.weight_scale_inv": "model.safetensors",
|
| 58 |
+
"model.language_model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 59 |
+
"model.language_model.layers.12.linear_attn.A_log": "model.safetensors",
|
| 60 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model.safetensors",
|
| 61 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model.safetensors",
|
| 62 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 68 |
+
"model.language_model.layers.12.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 69 |
+
"model.language_model.layers.12.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 70 |
+
"model.language_model.layers.12.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 71 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 72 |
+
"model.language_model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 73 |
+
"model.language_model.layers.13.linear_attn.A_log": "model.safetensors",
|
| 74 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model.safetensors",
|
| 75 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model.safetensors",
|
| 76 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 82 |
+
"model.language_model.layers.13.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 83 |
+
"model.language_model.layers.13.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 84 |
+
"model.language_model.layers.13.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 85 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 86 |
+
"model.language_model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 87 |
+
"model.language_model.layers.14.linear_attn.A_log": "model.safetensors",
|
| 88 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model.safetensors",
|
| 89 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model.safetensors",
|
| 90 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 96 |
+
"model.language_model.layers.14.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 97 |
+
"model.language_model.layers.14.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 98 |
+
"model.language_model.layers.14.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 99 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 100 |
+
"model.language_model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 101 |
+
"model.language_model.layers.15.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 102 |
+
"model.language_model.layers.15.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 103 |
+
"model.language_model.layers.15.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 104 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 105 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model.safetensors",
|
| 106 |
+
"model.language_model.layers.15.self_attn.k_proj.weight_scale_inv": "model.safetensors",
|
| 107 |
+
"model.language_model.layers.15.self_attn.o_proj.weight_scale_inv": "model.safetensors",
|
| 108 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.q_proj.weight_scale_inv": "model.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.v_proj.weight_scale_inv": "model.safetensors",
|
| 111 |
+
"model.language_model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 112 |
+
"model.language_model.layers.16.linear_attn.A_log": "model.safetensors",
|
| 113 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model.safetensors",
|
| 114 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model.safetensors",
|
| 115 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 121 |
+
"model.language_model.layers.16.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 122 |
+
"model.language_model.layers.16.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 123 |
+
"model.language_model.layers.16.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 124 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 125 |
+
"model.language_model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 126 |
+
"model.language_model.layers.17.linear_attn.A_log": "model.safetensors",
|
| 127 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model.safetensors",
|
| 128 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model.safetensors",
|
| 129 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 135 |
+
"model.language_model.layers.17.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 136 |
+
"model.language_model.layers.17.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 137 |
+
"model.language_model.layers.17.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 138 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 139 |
+
"model.language_model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 140 |
+
"model.language_model.layers.18.linear_attn.A_log": "model.safetensors",
|
| 141 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model.safetensors",
|
| 142 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model.safetensors",
|
| 143 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 149 |
+
"model.language_model.layers.18.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 150 |
+
"model.language_model.layers.18.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 151 |
+
"model.language_model.layers.18.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 152 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 153 |
+
"model.language_model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 154 |
+
"model.language_model.layers.19.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 155 |
+
"model.language_model.layers.19.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 156 |
+
"model.language_model.layers.19.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 157 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 158 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model.safetensors",
|
| 159 |
+
"model.language_model.layers.19.self_attn.k_proj.weight_scale_inv": "model.safetensors",
|
| 160 |
+
"model.language_model.layers.19.self_attn.o_proj.weight_scale_inv": "model.safetensors",
|
| 161 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.q_proj.weight_scale_inv": "model.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.v_proj.weight_scale_inv": "model.safetensors",
|
| 164 |
+
"model.language_model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 165 |
+
"model.language_model.layers.2.linear_attn.A_log": "model.safetensors",
|
| 166 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model.safetensors",
|
| 167 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model.safetensors",
|
| 168 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 174 |
+
"model.language_model.layers.2.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 175 |
+
"model.language_model.layers.2.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 176 |
+
"model.language_model.layers.2.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 177 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 178 |
+
"model.language_model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 179 |
+
"model.language_model.layers.20.linear_attn.A_log": "model.safetensors",
|
| 180 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model.safetensors",
|
| 181 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model.safetensors",
|
| 182 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 188 |
+
"model.language_model.layers.20.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 189 |
+
"model.language_model.layers.20.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 190 |
+
"model.language_model.layers.20.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 191 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 192 |
+
"model.language_model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 193 |
+
"model.language_model.layers.21.linear_attn.A_log": "model.safetensors",
|
| 194 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model.safetensors",
|
| 195 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model.safetensors",
|
| 196 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 202 |
+
"model.language_model.layers.21.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 203 |
+
"model.language_model.layers.21.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 204 |
+
"model.language_model.layers.21.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 205 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 206 |
+
"model.language_model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 207 |
+
"model.language_model.layers.22.linear_attn.A_log": "model.safetensors",
|
| 208 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model.safetensors",
|
| 209 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model.safetensors",
|
| 210 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 216 |
+
"model.language_model.layers.22.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 217 |
+
"model.language_model.layers.22.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 218 |
+
"model.language_model.layers.22.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 219 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 220 |
+
"model.language_model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 221 |
+
"model.language_model.layers.23.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 222 |
+
"model.language_model.layers.23.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 223 |
+
"model.language_model.layers.23.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 224 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 225 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model.safetensors",
|
| 226 |
+
"model.language_model.layers.23.self_attn.k_proj.weight_scale_inv": "model.safetensors",
|
| 227 |
+
"model.language_model.layers.23.self_attn.o_proj.weight_scale_inv": "model.safetensors",
|
| 228 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.q_proj.weight_scale_inv": "model.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.v_proj.weight_scale_inv": "model.safetensors",
|
| 231 |
+
"model.language_model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 232 |
+
"model.language_model.layers.24.linear_attn.A_log": "model.safetensors",
|
| 233 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model.safetensors",
|
| 234 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model.safetensors",
|
| 235 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 241 |
+
"model.language_model.layers.24.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 242 |
+
"model.language_model.layers.24.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 243 |
+
"model.language_model.layers.24.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 244 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 245 |
+
"model.language_model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 246 |
+
"model.language_model.layers.25.linear_attn.A_log": "model.safetensors",
|
| 247 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model.safetensors",
|
| 248 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model.safetensors",
|
| 249 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 255 |
+
"model.language_model.layers.25.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 256 |
+
"model.language_model.layers.25.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 257 |
+
"model.language_model.layers.25.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 258 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 259 |
+
"model.language_model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 260 |
+
"model.language_model.layers.26.linear_attn.A_log": "model.safetensors",
|
| 261 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model.safetensors",
|
| 262 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model.safetensors",
|
| 263 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 269 |
+
"model.language_model.layers.26.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 270 |
+
"model.language_model.layers.26.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 271 |
+
"model.language_model.layers.26.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 272 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 273 |
+
"model.language_model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 274 |
+
"model.language_model.layers.27.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 275 |
+
"model.language_model.layers.27.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 276 |
+
"model.language_model.layers.27.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 277 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 278 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model.safetensors",
|
| 279 |
+
"model.language_model.layers.27.self_attn.k_proj.weight_scale_inv": "model.safetensors",
|
| 280 |
+
"model.language_model.layers.27.self_attn.o_proj.weight_scale_inv": "model.safetensors",
|
| 281 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.q_proj.weight_scale_inv": "model.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.v_proj.weight_scale_inv": "model.safetensors",
|
| 284 |
+
"model.language_model.layers.28.input_layernorm.weight": "model.safetensors",
|
| 285 |
+
"model.language_model.layers.28.linear_attn.A_log": "model.safetensors",
|
| 286 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model.safetensors",
|
| 287 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model.safetensors",
|
| 288 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 294 |
+
"model.language_model.layers.28.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 295 |
+
"model.language_model.layers.28.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 296 |
+
"model.language_model.layers.28.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 297 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
| 298 |
+
"model.language_model.layers.29.input_layernorm.weight": "model.safetensors",
|
| 299 |
+
"model.language_model.layers.29.linear_attn.A_log": "model.safetensors",
|
| 300 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model.safetensors",
|
| 301 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model.safetensors",
|
| 302 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 308 |
+
"model.language_model.layers.29.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 309 |
+
"model.language_model.layers.29.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 310 |
+
"model.language_model.layers.29.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 311 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
| 312 |
+
"model.language_model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 313 |
+
"model.language_model.layers.3.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 314 |
+
"model.language_model.layers.3.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 315 |
+
"model.language_model.layers.3.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 316 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 317 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model.safetensors",
|
| 318 |
+
"model.language_model.layers.3.self_attn.k_proj.weight_scale_inv": "model.safetensors",
|
| 319 |
+
"model.language_model.layers.3.self_attn.o_proj.weight_scale_inv": "model.safetensors",
|
| 320 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.q_proj.weight_scale_inv": "model.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.v_proj.weight_scale_inv": "model.safetensors",
|
| 323 |
+
"model.language_model.layers.30.input_layernorm.weight": "model.safetensors",
|
| 324 |
+
"model.language_model.layers.30.linear_attn.A_log": "model.safetensors",
|
| 325 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model.safetensors",
|
| 326 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model.safetensors",
|
| 327 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 333 |
+
"model.language_model.layers.30.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 334 |
+
"model.language_model.layers.30.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 335 |
+
"model.language_model.layers.30.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 336 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
| 337 |
+
"model.language_model.layers.31.input_layernorm.weight": "model.safetensors",
|
| 338 |
+
"model.language_model.layers.31.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 339 |
+
"model.language_model.layers.31.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 340 |
+
"model.language_model.layers.31.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 341 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
| 342 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model.safetensors",
|
| 343 |
+
"model.language_model.layers.31.self_attn.k_proj.weight_scale_inv": "model.safetensors",
|
| 344 |
+
"model.language_model.layers.31.self_attn.o_proj.weight_scale_inv": "model.safetensors",
|
| 345 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.q_proj.weight_scale_inv": "model.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.v_proj.weight_scale_inv": "model.safetensors",
|
| 348 |
+
"model.language_model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 349 |
+
"model.language_model.layers.4.linear_attn.A_log": "model.safetensors",
|
| 350 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model.safetensors",
|
| 351 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model.safetensors",
|
| 352 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 358 |
+
"model.language_model.layers.4.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 359 |
+
"model.language_model.layers.4.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 360 |
+
"model.language_model.layers.4.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 361 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 362 |
+
"model.language_model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 363 |
+
"model.language_model.layers.5.linear_attn.A_log": "model.safetensors",
|
| 364 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model.safetensors",
|
| 365 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model.safetensors",
|
| 366 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 372 |
+
"model.language_model.layers.5.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 373 |
+
"model.language_model.layers.5.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 374 |
+
"model.language_model.layers.5.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 375 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 376 |
+
"model.language_model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 377 |
+
"model.language_model.layers.6.linear_attn.A_log": "model.safetensors",
|
| 378 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model.safetensors",
|
| 379 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model.safetensors",
|
| 380 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 386 |
+
"model.language_model.layers.6.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 387 |
+
"model.language_model.layers.6.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 388 |
+
"model.language_model.layers.6.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 389 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 390 |
+
"model.language_model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 391 |
+
"model.language_model.layers.7.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 392 |
+
"model.language_model.layers.7.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 393 |
+
"model.language_model.layers.7.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 394 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 395 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model.safetensors",
|
| 396 |
+
"model.language_model.layers.7.self_attn.k_proj.weight_scale_inv": "model.safetensors",
|
| 397 |
+
"model.language_model.layers.7.self_attn.o_proj.weight_scale_inv": "model.safetensors",
|
| 398 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.q_proj.weight_scale_inv": "model.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.v_proj.weight_scale_inv": "model.safetensors",
|
| 401 |
+
"model.language_model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 402 |
+
"model.language_model.layers.8.linear_attn.A_log": "model.safetensors",
|
| 403 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model.safetensors",
|
| 404 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model.safetensors",
|
| 405 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 411 |
+
"model.language_model.layers.8.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 412 |
+
"model.language_model.layers.8.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 413 |
+
"model.language_model.layers.8.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 414 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 415 |
+
"model.language_model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 416 |
+
"model.language_model.layers.9.linear_attn.A_log": "model.safetensors",
|
| 417 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model.safetensors",
|
| 418 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model.safetensors",
|
| 419 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight_scale_inv": "model.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight_scale_inv": "model.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight_scale_inv": "model.safetensors",
|
| 425 |
+
"model.language_model.layers.9.mlp.down_proj.weight_scale_inv": "model.safetensors",
|
| 426 |
+
"model.language_model.layers.9.mlp.gate_proj.weight_scale_inv": "model.safetensors",
|
| 427 |
+
"model.language_model.layers.9.mlp.up_proj.weight_scale_inv": "model.safetensors",
|
| 428 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 429 |
+
"model.language_model.norm.weight": "model.safetensors",
|
| 430 |
+
"model.visual.blocks.0.attn.proj.bias": "model.safetensors",
|
| 431 |
+
"model.visual.blocks.0.attn.proj.weight": "model.safetensors",
|
| 432 |
+
"model.visual.blocks.0.attn.qkv.bias": "model.safetensors",
|
| 433 |
+
"model.visual.blocks.0.attn.qkv.weight": "model.safetensors",
|
| 434 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors",
|
| 435 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors",
|
| 436 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors",
|
| 437 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors",
|
| 438 |
+
"model.visual.blocks.0.norm1.bias": "model.safetensors",
|
| 439 |
+
"model.visual.blocks.0.norm1.weight": "model.safetensors",
|
| 440 |
+
"model.visual.blocks.0.norm2.bias": "model.safetensors",
|
| 441 |
+
"model.visual.blocks.0.norm2.weight": "model.safetensors",
|
| 442 |
+
"model.visual.blocks.1.attn.proj.bias": "model.safetensors",
|
| 443 |
+
"model.visual.blocks.1.attn.proj.weight": "model.safetensors",
|
| 444 |
+
"model.visual.blocks.1.attn.qkv.bias": "model.safetensors",
|
| 445 |
+
"model.visual.blocks.1.attn.qkv.weight": "model.safetensors",
|
| 446 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors",
|
| 447 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors",
|
| 448 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors",
|
| 449 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors",
|
| 450 |
+
"model.visual.blocks.1.norm1.bias": "model.safetensors",
|
| 451 |
+
"model.visual.blocks.1.norm1.weight": "model.safetensors",
|
| 452 |
+
"model.visual.blocks.1.norm2.bias": "model.safetensors",
|
| 453 |
+
"model.visual.blocks.1.norm2.weight": "model.safetensors",
|
| 454 |
+
"model.visual.blocks.10.attn.proj.bias": "model.safetensors",
|
| 455 |
+
"model.visual.blocks.10.attn.proj.weight": "model.safetensors",
|
| 456 |
+
"model.visual.blocks.10.attn.qkv.bias": "model.safetensors",
|
| 457 |
+
"model.visual.blocks.10.attn.qkv.weight": "model.safetensors",
|
| 458 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors",
|
| 459 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors",
|
| 460 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors",
|
| 461 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors",
|
| 462 |
+
"model.visual.blocks.10.norm1.bias": "model.safetensors",
|
| 463 |
+
"model.visual.blocks.10.norm1.weight": "model.safetensors",
|
| 464 |
+
"model.visual.blocks.10.norm2.bias": "model.safetensors",
|
| 465 |
+
"model.visual.blocks.10.norm2.weight": "model.safetensors",
|
| 466 |
+
"model.visual.blocks.11.attn.proj.bias": "model.safetensors",
|
| 467 |
+
"model.visual.blocks.11.attn.proj.weight": "model.safetensors",
|
| 468 |
+
"model.visual.blocks.11.attn.qkv.bias": "model.safetensors",
|
| 469 |
+
"model.visual.blocks.11.attn.qkv.weight": "model.safetensors",
|
| 470 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors",
|
| 471 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors",
|
| 472 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors",
|
| 473 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors",
|
| 474 |
+
"model.visual.blocks.11.norm1.bias": "model.safetensors",
|
| 475 |
+
"model.visual.blocks.11.norm1.weight": "model.safetensors",
|
| 476 |
+
"model.visual.blocks.11.norm2.bias": "model.safetensors",
|
| 477 |
+
"model.visual.blocks.11.norm2.weight": "model.safetensors",
|
| 478 |
+
"model.visual.blocks.12.attn.proj.bias": "model.safetensors",
|
| 479 |
+
"model.visual.blocks.12.attn.proj.weight": "model.safetensors",
|
| 480 |
+
"model.visual.blocks.12.attn.qkv.bias": "model.safetensors",
|
| 481 |
+
"model.visual.blocks.12.attn.qkv.weight": "model.safetensors",
|
| 482 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model.safetensors",
|
| 483 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model.safetensors",
|
| 484 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model.safetensors",
|
| 485 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model.safetensors",
|
| 486 |
+
"model.visual.blocks.12.norm1.bias": "model.safetensors",
|
| 487 |
+
"model.visual.blocks.12.norm1.weight": "model.safetensors",
|
| 488 |
+
"model.visual.blocks.12.norm2.bias": "model.safetensors",
|
| 489 |
+
"model.visual.blocks.12.norm2.weight": "model.safetensors",
|
| 490 |
+
"model.visual.blocks.13.attn.proj.bias": "model.safetensors",
|
| 491 |
+
"model.visual.blocks.13.attn.proj.weight": "model.safetensors",
|
| 492 |
+
"model.visual.blocks.13.attn.qkv.bias": "model.safetensors",
|
| 493 |
+
"model.visual.blocks.13.attn.qkv.weight": "model.safetensors",
|
| 494 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model.safetensors",
|
| 495 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model.safetensors",
|
| 496 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model.safetensors",
|
| 497 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model.safetensors",
|
| 498 |
+
"model.visual.blocks.13.norm1.bias": "model.safetensors",
|
| 499 |
+
"model.visual.blocks.13.norm1.weight": "model.safetensors",
|
| 500 |
+
"model.visual.blocks.13.norm2.bias": "model.safetensors",
|
| 501 |
+
"model.visual.blocks.13.norm2.weight": "model.safetensors",
|
| 502 |
+
"model.visual.blocks.14.attn.proj.bias": "model.safetensors",
|
| 503 |
+
"model.visual.blocks.14.attn.proj.weight": "model.safetensors",
|
| 504 |
+
"model.visual.blocks.14.attn.qkv.bias": "model.safetensors",
|
| 505 |
+
"model.visual.blocks.14.attn.qkv.weight": "model.safetensors",
|
| 506 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model.safetensors",
|
| 507 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model.safetensors",
|
| 508 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model.safetensors",
|
| 509 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model.safetensors",
|
| 510 |
+
"model.visual.blocks.14.norm1.bias": "model.safetensors",
|
| 511 |
+
"model.visual.blocks.14.norm1.weight": "model.safetensors",
|
| 512 |
+
"model.visual.blocks.14.norm2.bias": "model.safetensors",
|
| 513 |
+
"model.visual.blocks.14.norm2.weight": "model.safetensors",
|
| 514 |
+
"model.visual.blocks.15.attn.proj.bias": "model.safetensors",
|
| 515 |
+
"model.visual.blocks.15.attn.proj.weight": "model.safetensors",
|
| 516 |
+
"model.visual.blocks.15.attn.qkv.bias": "model.safetensors",
|
| 517 |
+
"model.visual.blocks.15.attn.qkv.weight": "model.safetensors",
|
| 518 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model.safetensors",
|
| 519 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model.safetensors",
|
| 520 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model.safetensors",
|
| 521 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model.safetensors",
|
| 522 |
+
"model.visual.blocks.15.norm1.bias": "model.safetensors",
|
| 523 |
+
"model.visual.blocks.15.norm1.weight": "model.safetensors",
|
| 524 |
+
"model.visual.blocks.15.norm2.bias": "model.safetensors",
|
| 525 |
+
"model.visual.blocks.15.norm2.weight": "model.safetensors",
|
| 526 |
+
"model.visual.blocks.16.attn.proj.bias": "model.safetensors",
|
| 527 |
+
"model.visual.blocks.16.attn.proj.weight": "model.safetensors",
|
| 528 |
+
"model.visual.blocks.16.attn.qkv.bias": "model.safetensors",
|
| 529 |
+
"model.visual.blocks.16.attn.qkv.weight": "model.safetensors",
|
| 530 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model.safetensors",
|
| 531 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model.safetensors",
|
| 532 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model.safetensors",
|
| 533 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model.safetensors",
|
| 534 |
+
"model.visual.blocks.16.norm1.bias": "model.safetensors",
|
| 535 |
+
"model.visual.blocks.16.norm1.weight": "model.safetensors",
|
| 536 |
+
"model.visual.blocks.16.norm2.bias": "model.safetensors",
|
| 537 |
+
"model.visual.blocks.16.norm2.weight": "model.safetensors",
|
| 538 |
+
"model.visual.blocks.17.attn.proj.bias": "model.safetensors",
|
| 539 |
+
"model.visual.blocks.17.attn.proj.weight": "model.safetensors",
|
| 540 |
+
"model.visual.blocks.17.attn.qkv.bias": "model.safetensors",
|
| 541 |
+
"model.visual.blocks.17.attn.qkv.weight": "model.safetensors",
|
| 542 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model.safetensors",
|
| 543 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model.safetensors",
|
| 544 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model.safetensors",
|
| 545 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model.safetensors",
|
| 546 |
+
"model.visual.blocks.17.norm1.bias": "model.safetensors",
|
| 547 |
+
"model.visual.blocks.17.norm1.weight": "model.safetensors",
|
| 548 |
+
"model.visual.blocks.17.norm2.bias": "model.safetensors",
|
| 549 |
+
"model.visual.blocks.17.norm2.weight": "model.safetensors",
|
| 550 |
+
"model.visual.blocks.18.attn.proj.bias": "model.safetensors",
|
| 551 |
+
"model.visual.blocks.18.attn.proj.weight": "model.safetensors",
|
| 552 |
+
"model.visual.blocks.18.attn.qkv.bias": "model.safetensors",
|
| 553 |
+
"model.visual.blocks.18.attn.qkv.weight": "model.safetensors",
|
| 554 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model.safetensors",
|
| 555 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model.safetensors",
|
| 556 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model.safetensors",
|
| 557 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model.safetensors",
|
| 558 |
+
"model.visual.blocks.18.norm1.bias": "model.safetensors",
|
| 559 |
+
"model.visual.blocks.18.norm1.weight": "model.safetensors",
|
| 560 |
+
"model.visual.blocks.18.norm2.bias": "model.safetensors",
|
| 561 |
+
"model.visual.blocks.18.norm2.weight": "model.safetensors",
|
| 562 |
+
"model.visual.blocks.19.attn.proj.bias": "model.safetensors",
|
| 563 |
+
"model.visual.blocks.19.attn.proj.weight": "model.safetensors",
|
| 564 |
+
"model.visual.blocks.19.attn.qkv.bias": "model.safetensors",
|
| 565 |
+
"model.visual.blocks.19.attn.qkv.weight": "model.safetensors",
|
| 566 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model.safetensors",
|
| 567 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model.safetensors",
|
| 568 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model.safetensors",
|
| 569 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model.safetensors",
|
| 570 |
+
"model.visual.blocks.19.norm1.bias": "model.safetensors",
|
| 571 |
+
"model.visual.blocks.19.norm1.weight": "model.safetensors",
|
| 572 |
+
"model.visual.blocks.19.norm2.bias": "model.safetensors",
|
| 573 |
+
"model.visual.blocks.19.norm2.weight": "model.safetensors",
|
| 574 |
+
"model.visual.blocks.2.attn.proj.bias": "model.safetensors",
|
| 575 |
+
"model.visual.blocks.2.attn.proj.weight": "model.safetensors",
|
| 576 |
+
"model.visual.blocks.2.attn.qkv.bias": "model.safetensors",
|
| 577 |
+
"model.visual.blocks.2.attn.qkv.weight": "model.safetensors",
|
| 578 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors",
|
| 579 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors",
|
| 580 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors",
|
| 581 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors",
|
| 582 |
+
"model.visual.blocks.2.norm1.bias": "model.safetensors",
|
| 583 |
+
"model.visual.blocks.2.norm1.weight": "model.safetensors",
|
| 584 |
+
"model.visual.blocks.2.norm2.bias": "model.safetensors",
|
| 585 |
+
"model.visual.blocks.2.norm2.weight": "model.safetensors",
|
| 586 |
+
"model.visual.blocks.20.attn.proj.bias": "model.safetensors",
|
| 587 |
+
"model.visual.blocks.20.attn.proj.weight": "model.safetensors",
|
| 588 |
+
"model.visual.blocks.20.attn.qkv.bias": "model.safetensors",
|
| 589 |
+
"model.visual.blocks.20.attn.qkv.weight": "model.safetensors",
|
| 590 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model.safetensors",
|
| 591 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model.safetensors",
|
| 592 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model.safetensors",
|
| 593 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model.safetensors",
|
| 594 |
+
"model.visual.blocks.20.norm1.bias": "model.safetensors",
|
| 595 |
+
"model.visual.blocks.20.norm1.weight": "model.safetensors",
|
| 596 |
+
"model.visual.blocks.20.norm2.bias": "model.safetensors",
|
| 597 |
+
"model.visual.blocks.20.norm2.weight": "model.safetensors",
|
| 598 |
+
"model.visual.blocks.21.attn.proj.bias": "model.safetensors",
|
| 599 |
+
"model.visual.blocks.21.attn.proj.weight": "model.safetensors",
|
| 600 |
+
"model.visual.blocks.21.attn.qkv.bias": "model.safetensors",
|
| 601 |
+
"model.visual.blocks.21.attn.qkv.weight": "model.safetensors",
|
| 602 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model.safetensors",
|
| 603 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model.safetensors",
|
| 604 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model.safetensors",
|
| 605 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model.safetensors",
|
| 606 |
+
"model.visual.blocks.21.norm1.bias": "model.safetensors",
|
| 607 |
+
"model.visual.blocks.21.norm1.weight": "model.safetensors",
|
| 608 |
+
"model.visual.blocks.21.norm2.bias": "model.safetensors",
|
| 609 |
+
"model.visual.blocks.21.norm2.weight": "model.safetensors",
|
| 610 |
+
"model.visual.blocks.22.attn.proj.bias": "model.safetensors",
|
| 611 |
+
"model.visual.blocks.22.attn.proj.weight": "model.safetensors",
|
| 612 |
+
"model.visual.blocks.22.attn.qkv.bias": "model.safetensors",
|
| 613 |
+
"model.visual.blocks.22.attn.qkv.weight": "model.safetensors",
|
| 614 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model.safetensors",
|
| 615 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model.safetensors",
|
| 616 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model.safetensors",
|
| 617 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model.safetensors",
|
| 618 |
+
"model.visual.blocks.22.norm1.bias": "model.safetensors",
|
| 619 |
+
"model.visual.blocks.22.norm1.weight": "model.safetensors",
|
| 620 |
+
"model.visual.blocks.22.norm2.bias": "model.safetensors",
|
| 621 |
+
"model.visual.blocks.22.norm2.weight": "model.safetensors",
|
| 622 |
+
"model.visual.blocks.23.attn.proj.bias": "model.safetensors",
|
| 623 |
+
"model.visual.blocks.23.attn.proj.weight": "model.safetensors",
|
| 624 |
+
"model.visual.blocks.23.attn.qkv.bias": "model.safetensors",
|
| 625 |
+
"model.visual.blocks.23.attn.qkv.weight": "model.safetensors",
|
| 626 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model.safetensors",
|
| 627 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model.safetensors",
|
| 628 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model.safetensors",
|
| 629 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model.safetensors",
|
| 630 |
+
"model.visual.blocks.23.norm1.bias": "model.safetensors",
|
| 631 |
+
"model.visual.blocks.23.norm1.weight": "model.safetensors",
|
| 632 |
+
"model.visual.blocks.23.norm2.bias": "model.safetensors",
|
| 633 |
+
"model.visual.blocks.23.norm2.weight": "model.safetensors",
|
| 634 |
+
"model.visual.blocks.3.attn.proj.bias": "model.safetensors",
|
| 635 |
+
"model.visual.blocks.3.attn.proj.weight": "model.safetensors",
|
| 636 |
+
"model.visual.blocks.3.attn.qkv.bias": "model.safetensors",
|
| 637 |
+
"model.visual.blocks.3.attn.qkv.weight": "model.safetensors",
|
| 638 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors",
|
| 639 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors",
|
| 640 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors",
|
| 641 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors",
|
| 642 |
+
"model.visual.blocks.3.norm1.bias": "model.safetensors",
|
| 643 |
+
"model.visual.blocks.3.norm1.weight": "model.safetensors",
|
| 644 |
+
"model.visual.blocks.3.norm2.bias": "model.safetensors",
|
| 645 |
+
"model.visual.blocks.3.norm2.weight": "model.safetensors",
|
| 646 |
+
"model.visual.blocks.4.attn.proj.bias": "model.safetensors",
|
| 647 |
+
"model.visual.blocks.4.attn.proj.weight": "model.safetensors",
|
| 648 |
+
"model.visual.blocks.4.attn.qkv.bias": "model.safetensors",
|
| 649 |
+
"model.visual.blocks.4.attn.qkv.weight": "model.safetensors",
|
| 650 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors",
|
| 651 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors",
|
| 652 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors",
|
| 653 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors",
|
| 654 |
+
"model.visual.blocks.4.norm1.bias": "model.safetensors",
|
| 655 |
+
"model.visual.blocks.4.norm1.weight": "model.safetensors",
|
| 656 |
+
"model.visual.blocks.4.norm2.bias": "model.safetensors",
|
| 657 |
+
"model.visual.blocks.4.norm2.weight": "model.safetensors",
|
| 658 |
+
"model.visual.blocks.5.attn.proj.bias": "model.safetensors",
|
| 659 |
+
"model.visual.blocks.5.attn.proj.weight": "model.safetensors",
|
| 660 |
+
"model.visual.blocks.5.attn.qkv.bias": "model.safetensors",
|
| 661 |
+
"model.visual.blocks.5.attn.qkv.weight": "model.safetensors",
|
| 662 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors",
|
| 663 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors",
|
| 664 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors",
|
| 665 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors",
|
| 666 |
+
"model.visual.blocks.5.norm1.bias": "model.safetensors",
|
| 667 |
+
"model.visual.blocks.5.norm1.weight": "model.safetensors",
|
| 668 |
+
"model.visual.blocks.5.norm2.bias": "model.safetensors",
|
| 669 |
+
"model.visual.blocks.5.norm2.weight": "model.safetensors",
|
| 670 |
+
"model.visual.blocks.6.attn.proj.bias": "model.safetensors",
|
| 671 |
+
"model.visual.blocks.6.attn.proj.weight": "model.safetensors",
|
| 672 |
+
"model.visual.blocks.6.attn.qkv.bias": "model.safetensors",
|
| 673 |
+
"model.visual.blocks.6.attn.qkv.weight": "model.safetensors",
|
| 674 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors",
|
| 675 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors",
|
| 676 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors",
|
| 677 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors",
|
| 678 |
+
"model.visual.blocks.6.norm1.bias": "model.safetensors",
|
| 679 |
+
"model.visual.blocks.6.norm1.weight": "model.safetensors",
|
| 680 |
+
"model.visual.blocks.6.norm2.bias": "model.safetensors",
|
| 681 |
+
"model.visual.blocks.6.norm2.weight": "model.safetensors",
|
| 682 |
+
"model.visual.blocks.7.attn.proj.bias": "model.safetensors",
|
| 683 |
+
"model.visual.blocks.7.attn.proj.weight": "model.safetensors",
|
| 684 |
+
"model.visual.blocks.7.attn.qkv.bias": "model.safetensors",
|
| 685 |
+
"model.visual.blocks.7.attn.qkv.weight": "model.safetensors",
|
| 686 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors",
|
| 687 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors",
|
| 688 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors",
|
| 689 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors",
|
| 690 |
+
"model.visual.blocks.7.norm1.bias": "model.safetensors",
|
| 691 |
+
"model.visual.blocks.7.norm1.weight": "model.safetensors",
|
| 692 |
+
"model.visual.blocks.7.norm2.bias": "model.safetensors",
|
| 693 |
+
"model.visual.blocks.7.norm2.weight": "model.safetensors",
|
| 694 |
+
"model.visual.blocks.8.attn.proj.bias": "model.safetensors",
|
| 695 |
+
"model.visual.blocks.8.attn.proj.weight": "model.safetensors",
|
| 696 |
+
"model.visual.blocks.8.attn.qkv.bias": "model.safetensors",
|
| 697 |
+
"model.visual.blocks.8.attn.qkv.weight": "model.safetensors",
|
| 698 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors",
|
| 699 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors",
|
| 700 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors",
|
| 701 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors",
|
| 702 |
+
"model.visual.blocks.8.norm1.bias": "model.safetensors",
|
| 703 |
+
"model.visual.blocks.8.norm1.weight": "model.safetensors",
|
| 704 |
+
"model.visual.blocks.8.norm2.bias": "model.safetensors",
|
| 705 |
+
"model.visual.blocks.8.norm2.weight": "model.safetensors",
|
| 706 |
+
"model.visual.blocks.9.attn.proj.bias": "model.safetensors",
|
| 707 |
+
"model.visual.blocks.9.attn.proj.weight": "model.safetensors",
|
| 708 |
+
"model.visual.blocks.9.attn.qkv.bias": "model.safetensors",
|
| 709 |
+
"model.visual.blocks.9.attn.qkv.weight": "model.safetensors",
|
| 710 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors",
|
| 711 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors",
|
| 712 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors",
|
| 713 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors",
|
| 714 |
+
"model.visual.blocks.9.norm1.bias": "model.safetensors",
|
| 715 |
+
"model.visual.blocks.9.norm1.weight": "model.safetensors",
|
| 716 |
+
"model.visual.blocks.9.norm2.bias": "model.safetensors",
|
| 717 |
+
"model.visual.blocks.9.norm2.weight": "model.safetensors",
|
| 718 |
+
"model.visual.merger.linear_fc1.bias": "model.safetensors",
|
| 719 |
+
"model.visual.merger.linear_fc1.weight": "model.safetensors",
|
| 720 |
+
"model.visual.merger.linear_fc2.bias": "model.safetensors",
|
| 721 |
+
"model.visual.merger.linear_fc2.weight": "model.safetensors",
|
| 722 |
+
"model.visual.merger.norm.bias": "model.safetensors",
|
| 723 |
+
"model.visual.merger.norm.weight": "model.safetensors",
|
| 724 |
+
"model.visual.patch_embed.proj.bias": "model.safetensors",
|
| 725 |
+
"model.visual.patch_embed.proj.weight": "model.safetensors",
|
| 726 |
+
"model.visual.pos_embed.weight": "model.safetensors",
|
| 727 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 728 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 729 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model.safetensors",
|
| 730 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 731 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 732 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 733 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 734 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 735 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model.safetensors",
|
| 736 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 737 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 738 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 739 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 740 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 741 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model.safetensors",
|
| 742 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 743 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 744 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 745 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 746 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 747 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 748 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 749 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 750 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 751 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 752 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 753 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 754 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors",
|
| 755 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 756 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 757 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 758 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 759 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 760 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model.safetensors",
|
| 761 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 762 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 763 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 764 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 765 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 766 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model.safetensors",
|
| 767 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 768 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 769 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 770 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 771 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 772 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 773 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 774 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 775 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 776 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 777 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 778 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 779 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model.safetensors",
|
| 780 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 781 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 782 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 783 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 784 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 785 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model.safetensors",
|
| 786 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 787 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 788 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 789 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 790 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 791 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model.safetensors",
|
| 792 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 793 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 794 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 795 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 796 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 797 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 798 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 799 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 800 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 801 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 802 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 803 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 804 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model.safetensors",
|
| 805 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 806 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 807 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 808 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 809 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 810 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model.safetensors",
|
| 811 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 812 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 813 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 814 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 815 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 816 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model.safetensors",
|
| 817 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 818 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 819 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 820 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 821 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 822 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model.safetensors",
|
| 823 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 824 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 825 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 826 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 827 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 828 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 829 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 830 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 831 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 832 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 833 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 834 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 835 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model.safetensors",
|
| 836 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 837 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 838 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 839 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 840 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 841 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model.safetensors",
|
| 842 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 843 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 844 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 845 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 846 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 847 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model.safetensors",
|
| 848 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 849 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 850 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 851 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 852 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 853 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 854 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 855 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 856 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 857 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 858 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 859 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 860 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model.safetensors",
|
| 861 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
| 862 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
| 863 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
| 864 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 865 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 866 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model.safetensors",
|
| 867 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
| 868 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
| 869 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
| 870 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 871 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 872 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 873 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 874 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 875 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 876 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 877 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 878 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 879 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model.safetensors",
|
| 880 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
| 881 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
| 882 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
| 883 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
| 884 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
| 885 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
| 886 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
| 887 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
| 888 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
| 889 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
| 890 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 891 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 892 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model.safetensors",
|
| 893 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 894 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 895 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 896 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 897 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 898 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model.safetensors",
|
| 899 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 900 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 901 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 902 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 903 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 904 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model.safetensors",
|
| 905 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 906 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 907 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 908 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 909 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 910 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 911 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 912 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 913 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 914 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 915 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 916 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 917 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model.safetensors",
|
| 918 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 919 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 920 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 921 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
| 922 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors",
|
| 923 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model.safetensors",
|
| 924 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 925 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 926 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model.safetensors"
|
| 927 |
+
}
|
| 928 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 16777216,
|
| 25 |
+
"shortest_edge": 65536
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "Qwen3VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": true,
|
| 38 |
+
"fps": 2,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.5,
|
| 41 |
+
0.5,
|
| 42 |
+
0.5
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.5,
|
| 46 |
+
0.5,
|
| 47 |
+
0.5
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 16,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 25165824,
|
| 58 |
+
"shortest_edge": 4096
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
quant_report.csv
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
tensor,abs_error,rel_error,max_abs_error,max_rel_error
|
| 2 |
+
model.language_model.layers.0.linear_attn.in_proj_qkv.weight,0.0002288644900545478,0.022573521360754967,0.010009765625,1.0
|
| 3 |
+
model.language_model.layers.0.linear_attn.in_proj_z.weight,0.0002496865054126829,0.022577408701181412,0.0103759765625,1.0
|
| 4 |
+
model.language_model.layers.0.linear_attn.out_proj.weight,0.00020850235887337476,0.022551698610186577,0.0111083984375,1.0
|
| 5 |
+
model.language_model.layers.0.mlp.down_proj.weight,0.00015209217963274568,0.02255294658243656,0.012451171875,1.0
|
| 6 |
+
model.language_model.layers.0.mlp.gate_proj.weight,0.00016169399896170944,0.022551609203219414,0.0068359375,1.0
|
| 7 |
+
model.language_model.layers.0.mlp.up_proj.weight,0.00015117781003937125,0.02255258522927761,0.0029296875,1.0
|
| 8 |
+
model.language_model.layers.1.linear_attn.in_proj_qkv.weight,0.0002292687277076766,0.02255474030971527,0.0062255859375,1.0
|
| 9 |
+
model.language_model.layers.1.linear_attn.in_proj_z.weight,0.0002291145792696625,0.0225661788135767,0.00531005859375,1.0
|
| 10 |
+
model.language_model.layers.1.linear_attn.out_proj.weight,0.00021559526794590056,0.022549403831362724,0.017578125,1.0
|
| 11 |
+
model.language_model.layers.1.mlp.down_proj.weight,0.00014902905968483537,0.02256031706929207,0.008544921875,1.0
|
| 12 |
+
model.language_model.layers.1.mlp.gate_proj.weight,0.0001620517869014293,0.02254900522530079,0.0054931640625,1.0
|
| 13 |
+
model.language_model.layers.1.mlp.up_proj.weight,0.00015020165301393718,0.02255512960255146,0.00439453125,1.0
|
| 14 |
+
model.language_model.layers.10.linear_attn.in_proj_qkv.weight,0.00023624692403245717,0.022560078650712967,0.00830078125,1.0
|
| 15 |
+
model.language_model.layers.10.linear_attn.in_proj_z.weight,0.00021974637638777494,0.022571643814444542,0.00543212890625,1.0
|
| 16 |
+
model.language_model.layers.10.linear_attn.out_proj.weight,0.00020931093604303896,0.022552598267793655,0.0081787109375,1.0
|
| 17 |
+
model.language_model.layers.10.mlp.down_proj.weight,0.00015145482029765844,0.02255522459745407,0.0078125,1.0
|
| 18 |
+
model.language_model.layers.10.mlp.gate_proj.weight,0.00016400637105107307,0.02255416475236416,0.0054931640625,1.0
|
| 19 |
+
model.language_model.layers.10.mlp.up_proj.weight,0.00015613566210959107,0.022557711228728294,0.00531005859375,1.0
|
| 20 |
+
model.language_model.layers.11.mlp.down_proj.weight,0.00015151314437389374,0.022559013217687607,0.00830078125,1.0
|
| 21 |
+
model.language_model.layers.11.mlp.gate_proj.weight,0.00016201252583414316,0.022556183859705925,0.00567626953125,1.0
|
| 22 |
+
model.language_model.layers.11.mlp.up_proj.weight,0.00015703569806646556,0.022554609924554825,0.00372314453125,1.0
|
| 23 |
+
model.language_model.layers.11.self_attn.k_proj.weight,0.00019734246598090976,0.02255634032189846,0.00469970703125,1.0
|
| 24 |
+
model.language_model.layers.11.self_attn.o_proj.weight,0.00020126943127252162,0.02255907654762268,0.0076904296875,1.0
|
| 25 |
+
model.language_model.layers.11.self_attn.q_proj.weight,0.000220531175727956,0.02257588319480419,0.0078125,1.0
|
| 26 |
+
model.language_model.layers.11.self_attn.v_proj.weight,0.0002084169100271538,0.022565411403775215,0.00531005859375,1.0
|
| 27 |
+
model.language_model.layers.12.linear_attn.in_proj_qkv.weight,0.00024008475884329528,0.022564297541975975,0.00830078125,1.0
|
| 28 |
+
model.language_model.layers.12.linear_attn.in_proj_z.weight,0.0002092733484460041,0.022567342966794968,0.00634765625,1.0
|
| 29 |
+
model.language_model.layers.12.linear_attn.out_proj.weight,0.00020556699018925428,0.022563446313142776,0.00830078125,1.0
|
| 30 |
+
model.language_model.layers.12.mlp.down_proj.weight,0.00015053026436362416,0.022555958479642868,0.0078125,1.0
|
| 31 |
+
model.language_model.layers.12.mlp.gate_proj.weight,0.00015943571634124964,0.022559259086847305,0.005126953125,1.0
|
| 32 |
+
model.language_model.layers.12.mlp.up_proj.weight,0.00015643140068277717,0.022554917261004448,0.002838134765625,1.0
|
| 33 |
+
model.language_model.layers.13.linear_attn.in_proj_qkv.weight,0.00023956158838700503,0.022552726790308952,0.00640869140625,1.0
|
| 34 |
+
model.language_model.layers.13.linear_attn.in_proj_z.weight,0.0002191012754337862,0.022564377635717392,0.00421142578125,1.0
|
| 35 |
+
model.language_model.layers.13.linear_attn.out_proj.weight,0.00020733346173074096,0.022560277953743935,0.01220703125,1.0
|
| 36 |
+
model.language_model.layers.13.mlp.down_proj.weight,0.00014872576866764575,0.022557660937309265,0.00665283203125,1.0
|
| 37 |
+
model.language_model.layers.13.mlp.gate_proj.weight,0.00015896494733169675,0.022560637444257736,0.00390625,1.0
|
| 38 |
+
model.language_model.layers.13.mlp.up_proj.weight,0.0001551884488435462,0.022555695846676826,0.00390625,1.0
|
| 39 |
+
model.language_model.layers.14.linear_attn.in_proj_qkv.weight,0.00023701110330875963,0.022563043981790543,0.0072021484375,1.0
|
| 40 |
+
model.language_model.layers.14.linear_attn.in_proj_z.weight,0.0002117482799803838,0.022562233731150627,0.00555419921875,1.0
|
| 41 |
+
model.language_model.layers.14.linear_attn.out_proj.weight,0.0002027892041951418,0.022570254281163216,0.0098876953125,1.0
|
| 42 |
+
model.language_model.layers.14.mlp.down_proj.weight,0.0001492516603320837,0.022562861442565918,0.005126953125,1.0
|
| 43 |
+
model.language_model.layers.14.mlp.gate_proj.weight,0.00015417249232996255,0.022556787356734276,0.0045166015625,1.0
|
| 44 |
+
model.language_model.layers.14.mlp.up_proj.weight,0.0001553886686451733,0.022559629753232002,0.00323486328125,1.0
|
| 45 |
+
model.language_model.layers.15.mlp.down_proj.weight,0.0001499698992120102,0.022554052993655205,0.007568359375,1.0
|
| 46 |
+
model.language_model.layers.15.mlp.gate_proj.weight,0.00015498952416237444,0.022560331970453262,0.0054931640625,1.0
|
| 47 |
+
model.language_model.layers.15.mlp.up_proj.weight,0.000156383088324219,0.022548511624336243,0.003662109375,1.0
|
| 48 |
+
model.language_model.layers.15.self_attn.k_proj.weight,0.00019300809071864933,0.022578809410333633,0.006591796875,1.0
|
| 49 |
+
model.language_model.layers.15.self_attn.o_proj.weight,0.00020355328160803765,0.02256242372095585,0.0072021484375,1.0
|
| 50 |
+
model.language_model.layers.15.self_attn.q_proj.weight,0.0002095298405038193,0.022566786035895348,0.0079345703125,1.0
|
| 51 |
+
model.language_model.layers.15.self_attn.v_proj.weight,0.00023315798898693174,0.02257569134235382,0.004150390625,1.0
|
| 52 |
+
model.language_model.layers.16.linear_attn.in_proj_qkv.weight,0.00023208880156744272,0.022561149671673775,0.0078125,1.0
|
| 53 |
+
model.language_model.layers.16.linear_attn.in_proj_z.weight,0.00021182936325203627,0.02256929688155651,0.0054931640625,1.0
|
| 54 |
+
model.language_model.layers.16.linear_attn.out_proj.weight,0.0002010040043387562,0.022555965930223465,0.00762939453125,1.0
|
| 55 |
+
model.language_model.layers.16.mlp.down_proj.weight,0.0001498008205089718,0.02255294658243656,0.008056640625,1.0
|
| 56 |
+
model.language_model.layers.16.mlp.gate_proj.weight,0.00015609548427164555,0.02256045863032341,0.0069580078125,1.0
|
| 57 |
+
model.language_model.layers.16.mlp.up_proj.weight,0.0001555332710267976,0.022555029019713402,0.002685546875,1.0
|
| 58 |
+
model.language_model.layers.17.linear_attn.in_proj_qkv.weight,0.00024388996826019138,0.022566376253962517,0.0078125,1.0
|
| 59 |
+
model.language_model.layers.17.linear_attn.in_proj_z.weight,0.00020695969578810036,0.022559700533747673,0.00433349609375,1.0
|
| 60 |
+
model.language_model.layers.17.linear_attn.out_proj.weight,0.00020460608357097954,0.022568626329302788,0.00634765625,1.0
|
| 61 |
+
model.language_model.layers.17.mlp.down_proj.weight,0.00015177398745436221,0.022552764043211937,0.0107421875,1.0
|
| 62 |
+
model.language_model.layers.17.mlp.gate_proj.weight,0.00015490452642552555,0.022561974823474884,0.007080078125,1.0
|
| 63 |
+
model.language_model.layers.17.mlp.up_proj.weight,0.00015714728215243667,0.022551696747541428,0.00347900390625,1.0
|
| 64 |
+
model.language_model.layers.18.linear_attn.in_proj_qkv.weight,0.00023818621411919594,0.022560784593224525,0.005859375,1.0
|
| 65 |
+
model.language_model.layers.18.linear_attn.in_proj_z.weight,0.0002139952703146264,0.02256784401834011,0.0069580078125,1.0
|
| 66 |
+
model.language_model.layers.18.linear_attn.out_proj.weight,0.0002012260229093954,0.022554166615009308,0.0067138671875,1.0
|
| 67 |
+
model.language_model.layers.18.mlp.down_proj.weight,0.00015193356375675648,0.02256336249411106,0.00634765625,1.0
|
| 68 |
+
model.language_model.layers.18.mlp.gate_proj.weight,0.00015890877693891525,0.022568708285689354,0.00714111328125,1.0
|
| 69 |
+
model.language_model.layers.18.mlp.up_proj.weight,0.0001587076112627983,0.02255690097808838,0.00567626953125,1.0
|
| 70 |
+
model.language_model.layers.19.mlp.down_proj.weight,0.00015821700799278915,0.022555017843842506,0.008056640625,1.0
|
| 71 |
+
model.language_model.layers.19.mlp.gate_proj.weight,0.00016658515960443765,0.0225626640021801,0.0068359375,1.0
|
| 72 |
+
model.language_model.layers.19.mlp.up_proj.weight,0.00016422961198259145,0.022555558010935783,0.0042724609375,1.0
|
| 73 |
+
model.language_model.layers.19.self_attn.k_proj.weight,0.00019199248345103115,0.022561004385352135,0.00634765625,1.0
|
| 74 |
+
model.language_model.layers.19.self_attn.o_proj.weight,0.00022973395243752748,0.022571546956896782,0.0087890625,1.0
|
| 75 |
+
model.language_model.layers.19.self_attn.q_proj.weight,0.0002120744902640581,0.022563133388757706,0.006103515625,1.0
|
| 76 |
+
model.language_model.layers.19.self_attn.v_proj.weight,0.0002541026333346963,0.022564219310879707,0.0072021484375,1.0
|
| 77 |
+
model.language_model.layers.2.linear_attn.in_proj_qkv.weight,0.0002306597598362714,0.022556453943252563,0.0050048828125,1.0
|
| 78 |
+
model.language_model.layers.2.linear_attn.in_proj_z.weight,0.00023098285601008683,0.022551102563738823,0.00634765625,1.0
|
| 79 |
+
model.language_model.layers.2.linear_attn.out_proj.weight,0.00021688091510441154,0.02255122736096382,0.013671875,1.0
|
| 80 |
+
model.language_model.layers.2.mlp.down_proj.weight,0.00014778433251194656,0.02256494201719761,0.0098876953125,1.0
|
| 81 |
+
model.language_model.layers.2.mlp.gate_proj.weight,0.00017037913494277745,0.022547587752342224,0.0047607421875,1.0
|
| 82 |
+
model.language_model.layers.2.mlp.up_proj.weight,0.0001469121198169887,0.022557457908988,0.00347900390625,1.0
|
| 83 |
+
model.language_model.layers.20.linear_attn.in_proj_qkv.weight,0.0002640320162754506,0.022562270984053612,0.009033203125,1.0
|
| 84 |
+
model.language_model.layers.20.linear_attn.in_proj_z.weight,0.00024061118892859668,0.02256954275071621,0.0064697265625,1.0
|
| 85 |
+
model.language_model.layers.20.linear_attn.out_proj.weight,0.00020089803729206324,0.022557325661182404,0.0068359375,1.0
|
| 86 |
+
model.language_model.layers.20.mlp.down_proj.weight,0.00015524946502409875,0.022556712850928307,0.00531005859375,1.0
|
| 87 |
+
model.language_model.layers.20.mlp.gate_proj.weight,0.0001860234042396769,0.022562365978956223,0.007080078125,1.0
|
| 88 |
+
model.language_model.layers.20.mlp.up_proj.weight,0.00015993081615306437,0.022555122151970863,0.00360107421875,1.0
|
| 89 |
+
model.language_model.layers.21.linear_attn.in_proj_qkv.weight,0.00026452215388417244,0.02256227470934391,0.0093994140625,1.0
|
| 90 |
+
model.language_model.layers.21.linear_attn.in_proj_z.weight,0.00024837040109559894,0.022568469867110252,0.0057373046875,1.0
|
| 91 |
+
model.language_model.layers.21.linear_attn.out_proj.weight,0.00020265734929125756,0.022569268941879272,0.009765625,1.0
|
| 92 |
+
model.language_model.layers.21.mlp.down_proj.weight,0.000155414774781093,0.02255360782146454,0.00732421875,1.0
|
| 93 |
+
model.language_model.layers.21.mlp.gate_proj.weight,0.00019156474445480853,0.02256862074136734,0.005859375,1.0
|
| 94 |
+
model.language_model.layers.21.mlp.up_proj.weight,0.00016012504056561738,0.022551272064447403,0.0057373046875,1.0
|
| 95 |
+
model.language_model.layers.22.linear_attn.in_proj_qkv.weight,0.0002546037721913308,0.02256367914378643,0.006591796875,1.0
|
| 96 |
+
model.language_model.layers.22.linear_attn.in_proj_z.weight,0.00026494762278161943,0.022555097937583923,0.0069580078125,1.0
|
| 97 |
+
model.language_model.layers.22.linear_attn.out_proj.weight,0.00021045612811576575,0.022553199902176857,0.008056640625,1.0
|
| 98 |
+
model.language_model.layers.22.mlp.down_proj.weight,0.00015479394642170519,0.022549038752913475,0.007568359375,1.0
|
| 99 |
+
model.language_model.layers.22.mlp.gate_proj.weight,0.00020498104277066886,0.02256789058446884,0.0068359375,1.0
|
| 100 |
+
model.language_model.layers.22.mlp.up_proj.weight,0.00016118204803206027,0.022550931200385094,0.00421142578125,1.0
|
| 101 |
+
model.language_model.layers.23.mlp.down_proj.weight,0.00015864675515331328,0.022555802017450333,0.0069580078125,1.0
|
| 102 |
+
model.language_model.layers.23.mlp.gate_proj.weight,0.00020092309569008648,0.02256515808403492,0.010009765625,1.0
|
| 103 |
+
model.language_model.layers.23.mlp.up_proj.weight,0.0001637433742871508,0.02255050465464592,0.00421142578125,1.0
|
| 104 |
+
model.language_model.layers.23.self_attn.k_proj.weight,0.00018098278087563813,0.022567136213183403,0.00634765625,1.0
|
| 105 |
+
model.language_model.layers.23.self_attn.o_proj.weight,0.00023816707835067064,0.022569818422198296,0.0078125,1.0
|
| 106 |
+
model.language_model.layers.23.self_attn.q_proj.weight,0.000227713244385086,0.02256455458700657,0.0062255859375,1.0
|
| 107 |
+
model.language_model.layers.23.self_attn.v_proj.weight,0.00026653488748706877,0.02256249450147152,0.00677490234375,1.0
|
| 108 |
+
model.language_model.layers.24.linear_attn.in_proj_qkv.weight,0.0002693170390557498,0.022567344829440117,0.0084228515625,1.0
|
| 109 |
+
model.language_model.layers.24.linear_attn.in_proj_z.weight,0.0002538460830692202,0.02256719581782818,0.00567626953125,1.0
|
| 110 |
+
model.language_model.layers.24.linear_attn.out_proj.weight,0.00020330306142568588,0.022570529952645302,0.0084228515625,1.0
|
| 111 |
+
model.language_model.layers.24.mlp.down_proj.weight,0.00015885118045844138,0.022550610825419426,0.00494384765625,1.0
|
| 112 |
+
model.language_model.layers.24.mlp.gate_proj.weight,0.00021010820637457073,0.022560426965355873,0.00714111328125,1.0
|
| 113 |
+
model.language_model.layers.24.mlp.up_proj.weight,0.00016317309928126633,0.02255329117178917,0.003021240234375,1.0
|
| 114 |
+
model.language_model.layers.25.linear_attn.in_proj_qkv.weight,0.00026717805303633213,0.022563327103853226,0.009765625,1.0
|
| 115 |
+
model.language_model.layers.25.linear_attn.in_proj_z.weight,0.0002628267393447459,0.02256210520863533,0.00634765625,1.0
|
| 116 |
+
model.language_model.layers.25.linear_attn.out_proj.weight,0.00020916573703289032,0.022562330588698387,0.0126953125,1.0
|
| 117 |
+
model.language_model.layers.25.mlp.down_proj.weight,0.00016039941692724824,0.02255595289170742,0.0032958984375,1.0
|
| 118 |
+
model.language_model.layers.25.mlp.gate_proj.weight,0.00022006654762662947,0.02256022021174431,0.0078125,1.0
|
| 119 |
+
model.language_model.layers.25.mlp.up_proj.weight,0.0001643435243749991,0.022548459470272064,0.002960205078125,1.0
|
| 120 |
+
model.language_model.layers.26.linear_attn.in_proj_qkv.weight,0.0002581943408586085,0.02256830967962742,0.0087890625,1.0
|
| 121 |
+
model.language_model.layers.26.linear_attn.in_proj_z.weight,0.0002761335053946823,0.022558968514204025,0.0068359375,1.0
|
| 122 |
+
model.language_model.layers.26.linear_attn.out_proj.weight,0.00021359766833484173,0.02255198173224926,0.0062255859375,1.0
|
| 123 |
+
model.language_model.layers.26.mlp.down_proj.weight,0.0001638468966120854,0.02255149558186531,0.00732421875,1.0
|
| 124 |
+
model.language_model.layers.26.mlp.gate_proj.weight,0.00022841512691229582,0.022563379257917404,0.009033203125,1.0
|
| 125 |
+
model.language_model.layers.26.mlp.up_proj.weight,0.0001677913824096322,0.022554265335202217,0.00421142578125,1.0
|
| 126 |
+
model.language_model.layers.27.mlp.down_proj.weight,0.00016469335241708905,0.02255808562040329,0.0166015625,1.0
|
| 127 |
+
model.language_model.layers.27.mlp.gate_proj.weight,0.00022574790637008846,0.022563595324754715,0.009765625,1.0
|
| 128 |
+
model.language_model.layers.27.mlp.up_proj.weight,0.00016890818369574845,0.022550472989678383,0.0072021484375,1.0
|
| 129 |
+
model.language_model.layers.27.self_attn.k_proj.weight,0.0001709440111881122,0.022578848525881767,0.0052490234375,1.0
|
| 130 |
+
model.language_model.layers.27.self_attn.o_proj.weight,0.00027648929972201586,0.02256343699991703,0.01953125,1.0
|
| 131 |
+
model.language_model.layers.27.self_attn.q_proj.weight,0.00021184247452765703,0.02256433665752411,0.00616455078125,1.0
|
| 132 |
+
model.language_model.layers.27.self_attn.v_proj.weight,0.00034176354529336095,0.022553836926817894,0.017578125,1.0
|
| 133 |
+
model.language_model.layers.28.linear_attn.in_proj_qkv.weight,0.00027356192003935575,0.022564401850104332,0.0113525390625,1.0
|
| 134 |
+
model.language_model.layers.28.linear_attn.in_proj_z.weight,0.0002593788376543671,0.022565582767128944,0.0107421875,1.0
|
| 135 |
+
model.language_model.layers.28.linear_attn.out_proj.weight,0.00021418403775896877,0.022561682388186455,0.009033203125,1.0
|
| 136 |
+
model.language_model.layers.28.mlp.down_proj.weight,0.0001660223351791501,0.022554855793714523,0.0062255859375,1.0
|
| 137 |
+
model.language_model.layers.28.mlp.gate_proj.weight,0.0002249829558422789,0.022565433755517006,0.010498046875,1.0
|
| 138 |
+
model.language_model.layers.28.mlp.up_proj.weight,0.00017198786372318864,0.02255391515791416,0.004150390625,1.0
|
| 139 |
+
model.language_model.layers.29.linear_attn.in_proj_qkv.weight,0.0002539691631682217,0.022562459111213684,0.0106201171875,1.0
|
| 140 |
+
model.language_model.layers.29.linear_attn.in_proj_z.weight,0.0002693347632884979,0.022561227902770042,0.008544921875,1.0
|
| 141 |
+
model.language_model.layers.29.linear_attn.out_proj.weight,0.0002213741245213896,0.022565854713320732,0.012939453125,1.0
|
| 142 |
+
model.language_model.layers.29.mlp.down_proj.weight,0.00016899735783226788,0.022552814334630966,0.00732421875,1.0
|
| 143 |
+
model.language_model.layers.29.mlp.gate_proj.weight,0.00022756408725399524,0.022566981613636017,0.009033203125,1.0
|
| 144 |
+
model.language_model.layers.29.mlp.up_proj.weight,0.00017649562505539507,0.02254878543317318,0.005126953125,1.0
|
| 145 |
+
model.language_model.layers.3.mlp.down_proj.weight,0.00015041806909721345,0.022556740790605545,0.011474609375,1.0
|
| 146 |
+
model.language_model.layers.3.mlp.gate_proj.weight,0.00016486125241499394,0.0225497018545866,0.00634765625,1.0
|
| 147 |
+
model.language_model.layers.3.mlp.up_proj.weight,0.00015113413974177092,0.022561943158507347,0.002899169921875,1.0
|
| 148 |
+
model.language_model.layers.3.self_attn.k_proj.weight,0.00021339447994250804,0.022566577419638634,0.0050048828125,1.0
|
| 149 |
+
model.language_model.layers.3.self_attn.o_proj.weight,0.00021263804228510708,0.022559845820069313,0.0087890625,1.0
|
| 150 |
+
model.language_model.layers.3.self_attn.q_proj.weight,0.0002583638415671885,0.02255704626441002,0.0096435546875,1.0
|
| 151 |
+
model.language_model.layers.3.self_attn.v_proj.weight,0.0002259030006825924,0.022552011534571648,0.0054931640625,1.0
|
| 152 |
+
model.language_model.layers.30.linear_attn.in_proj_qkv.weight,0.00025830656522884965,0.022561054676771164,0.0107421875,1.0
|
| 153 |
+
model.language_model.layers.30.linear_attn.in_proj_z.weight,0.00024973336257971823,0.02255878783762455,0.009033203125,1.0
|
| 154 |
+
model.language_model.layers.30.linear_attn.out_proj.weight,0.00021969841327518225,0.02256990596652031,0.01171875,1.0
|
| 155 |
+
model.language_model.layers.30.mlp.down_proj.weight,0.00016666158626321703,0.02255326882004738,0.015869140625,1.0
|
| 156 |
+
model.language_model.layers.30.mlp.gate_proj.weight,0.00022040129988454282,0.022564705461263657,0.00830078125,1.0
|
| 157 |
+
model.language_model.layers.30.mlp.up_proj.weight,0.00017789911362342536,0.02255379967391491,0.0069580078125,1.0
|
| 158 |
+
model.language_model.layers.31.mlp.down_proj.weight,0.00015326951688621193,0.022561663761734962,0.010986328125,1.0
|
| 159 |
+
model.language_model.layers.31.mlp.gate_proj.weight,0.00022906243975739926,0.0225653238594532,0.0113525390625,1.0
|
| 160 |
+
model.language_model.layers.31.mlp.up_proj.weight,0.0001891985157271847,0.022557884454727173,0.00634765625,1.0
|
| 161 |
+
model.language_model.layers.31.self_attn.k_proj.weight,0.00017114308138843626,0.022555235773324966,0.0054931640625,1.0
|
| 162 |
+
model.language_model.layers.31.self_attn.o_proj.weight,0.00023986246378626674,0.02256777323782444,0.0107421875,1.0
|
| 163 |
+
model.language_model.layers.31.self_attn.q_proj.weight,0.00021660039783455431,0.022563865408301353,0.00927734375,1.0
|
| 164 |
+
model.language_model.layers.31.self_attn.v_proj.weight,0.0003289662708994001,0.022566666826605797,0.013916015625,1.0
|
| 165 |
+
model.language_model.layers.4.linear_attn.in_proj_qkv.weight,0.00023586097813677043,0.02256236970424652,0.0069580078125,1.0
|
| 166 |
+
model.language_model.layers.4.linear_attn.in_proj_z.weight,0.00024199117615353316,0.02256041206419468,0.00653076171875,1.0
|
| 167 |
+
model.language_model.layers.4.linear_attn.out_proj.weight,0.00021725031547248363,0.022552549839019775,0.012939453125,1.0
|
| 168 |
+
model.language_model.layers.4.mlp.down_proj.weight,0.00015003871521912515,0.02256321907043457,0.0069580078125,1.0
|
| 169 |
+
model.language_model.layers.4.mlp.gate_proj.weight,0.0001657613756833598,0.022553298622369766,0.00537109375,1.0
|
| 170 |
+
model.language_model.layers.4.mlp.up_proj.weight,0.00015156803419813514,0.022557910531759262,0.003204345703125,1.0
|
| 171 |
+
model.language_model.layers.5.linear_attn.in_proj_qkv.weight,0.00023324321955442429,0.022557981312274933,0.0057373046875,1.0
|
| 172 |
+
model.language_model.layers.5.linear_attn.in_proj_z.weight,0.00023876572959125042,0.022574609145522118,0.00518798828125,1.0
|
| 173 |
+
model.language_model.layers.5.linear_attn.out_proj.weight,0.00021442548313643783,0.022549694404006004,0.017578125,1.0
|
| 174 |
+
model.language_model.layers.5.mlp.down_proj.weight,0.0001483637315686792,0.022555651143193245,0.0103759765625,1.0
|
| 175 |
+
model.language_model.layers.5.mlp.gate_proj.weight,0.00017122196732088923,0.022553417831659317,0.005126953125,1.0
|
| 176 |
+
model.language_model.layers.5.mlp.up_proj.weight,0.00014983104483690113,0.02255517989397049,0.00299072265625,1.0
|
| 177 |
+
model.language_model.layers.6.linear_attn.in_proj_qkv.weight,0.00023652194067835808,0.02256416156888008,0.005859375,1.0
|
| 178 |
+
model.language_model.layers.6.linear_attn.in_proj_z.weight,0.00021688667766284198,0.022565511986613274,0.005859375,1.0
|
| 179 |
+
model.language_model.layers.6.linear_attn.out_proj.weight,0.0002121904253726825,0.02256208471953869,0.010009765625,1.0
|
| 180 |
+
model.language_model.layers.6.mlp.down_proj.weight,0.0001445349771529436,0.022562075406312943,0.008544921875,1.0
|
| 181 |
+
model.language_model.layers.6.mlp.gate_proj.weight,0.00017411279259249568,0.022549359127879143,0.0048828125,1.0
|
| 182 |
+
model.language_model.layers.6.mlp.up_proj.weight,0.00014768079563509673,0.022557439282536507,0.00439453125,1.0
|
| 183 |
+
model.language_model.layers.7.mlp.down_proj.weight,0.0001457672187825665,0.022557830438017845,0.01171875,1.0
|
| 184 |
+
model.language_model.layers.7.mlp.gate_proj.weight,0.00018216179159935564,0.022556543350219727,0.00628662109375,1.0
|
| 185 |
+
model.language_model.layers.7.mlp.up_proj.weight,0.00014817075862083584,0.02255597524344921,0.00274658203125,1.0
|
| 186 |
+
model.language_model.layers.7.self_attn.k_proj.weight,0.00020004417456220835,0.0225676279515028,0.0052490234375,1.0
|
| 187 |
+
model.language_model.layers.7.self_attn.o_proj.weight,0.00020404263341333717,0.022564029321074486,0.00689697265625,1.0
|
| 188 |
+
model.language_model.layers.7.self_attn.q_proj.weight,0.00023088876332622021,0.02255987375974655,0.00732421875,1.0
|
| 189 |
+
model.language_model.layers.7.self_attn.v_proj.weight,0.00020786412642337382,0.022550610825419426,0.004638671875,1.0
|
| 190 |
+
model.language_model.layers.8.linear_attn.in_proj_qkv.weight,0.00023769451945554465,0.022566089406609535,0.00634765625,1.0
|
| 191 |
+
model.language_model.layers.8.linear_attn.in_proj_z.weight,0.00022673913917969912,0.022562745958566666,0.0054931640625,1.0
|
| 192 |
+
model.language_model.layers.8.linear_attn.out_proj.weight,0.0002099133562296629,0.02255435660481453,0.00830078125,1.0
|
| 193 |
+
model.language_model.layers.8.mlp.down_proj.weight,0.00014871569874230772,0.022556334733963013,0.007080078125,1.0
|
| 194 |
+
model.language_model.layers.8.mlp.gate_proj.weight,0.00017881690291687846,0.02255040779709816,0.0045166015625,1.0
|
| 195 |
+
model.language_model.layers.8.mlp.up_proj.weight,0.00015113098197616637,0.022553378716111183,0.003204345703125,1.0
|
| 196 |
+
model.language_model.layers.9.linear_attn.in_proj_qkv.weight,0.00024076682166196406,0.022562865167856216,0.0068359375,1.0
|
| 197 |
+
model.language_model.layers.9.linear_attn.in_proj_z.weight,0.0002264067152282223,0.022568045184016228,0.0050048828125,1.0
|
| 198 |
+
model.language_model.layers.9.linear_attn.out_proj.weight,0.00021181227930355817,0.022558098658919334,0.0087890625,1.0
|
| 199 |
+
model.language_model.layers.9.mlp.down_proj.weight,0.0001507206616224721,0.02255772054195404,0.0098876953125,1.0
|
| 200 |
+
model.language_model.layers.9.mlp.gate_proj.weight,0.00017373391892760992,0.02255294844508171,0.0054931640625,1.0
|
| 201 |
+
model.language_model.layers.9.mlp.up_proj.weight,0.0001545706472825259,0.022554507479071617,0.00360107421875,1.0
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"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+",
|
| 25 |
+
"processor_class": "Qwen3VLProcessor",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "TokenizersBackend",
|
| 28 |
+
"unk_token": null,
|
| 29 |
+
"video_token": "<|video_pad|>",
|
| 30 |
+
"vision_bos_token": "<|vision_start|>",
|
| 31 |
+
"vision_eos_token": "<|vision_end|>"
|
| 32 |
+
}
|