Text Generation
Transformers
Safetensors
MLX
qwen3_5
image-text-to-text
text-generation-inference
unsloth
qwen3_6
reasoning
chain-of-thought
lora
sft
agent
tool-use
function-calling
coder
mlx-my-repo
conversational
5-bit
Instructions to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="analogbox/Qwopus3.6-27B-Coder-mlx-5Bit") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("analogbox/Qwopus3.6-27B-Coder-mlx-5Bit") model = AutoModelForMultimodalLM.from_pretrained("analogbox/Qwopus3.6-27B-Coder-mlx-5Bit") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - MLX
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("analogbox/Qwopus3.6-27B-Coder-mlx-5Bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- vLLM
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/analogbox/Qwopus3.6-27B-Coder-mlx-5Bit
- SGLang
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for analogbox/Qwopus3.6-27B-Coder-mlx-5Bit to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for analogbox/Qwopus3.6-27B-Coder-mlx-5Bit to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for analogbox/Qwopus3.6-27B-Coder-mlx-5Bit to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="analogbox/Qwopus3.6-27B-Coder-mlx-5Bit", max_seq_length=2048, ) - Pi
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default analogbox/Qwopus3.6-27B-Coder-mlx-5Bit
Run Hermes
hermes
- OpenClaw new
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- MLX LM
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "analogbox/Qwopus3.6-27B-Coder-mlx-5Bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Docker Model Runner
How to use analogbox/Qwopus3.6-27B-Coder-mlx-5Bit with Docker Model Runner:
docker model run hf.co/analogbox/Qwopus3.6-27B-Coder-mlx-5Bit
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +56 -0
- chat_template.jinja +144 -0
- config.json +143 -0
- generation_config.json +13 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- tokenizer.json +3 -0
- tokenizer_config.json +34 -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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Jackrong/Qwopus3.6-27B-Coder
|
| 3 |
+
tags:
|
| 4 |
+
- text-generation-inference
|
| 5 |
+
- transformers
|
| 6 |
+
- unsloth
|
| 7 |
+
- qwen3_6
|
| 8 |
+
- reasoning
|
| 9 |
+
- chain-of-thought
|
| 10 |
+
- lora
|
| 11 |
+
- sft
|
| 12 |
+
- agent
|
| 13 |
+
- tool-use
|
| 14 |
+
- function-calling
|
| 15 |
+
- coder
|
| 16 |
+
- mlx
|
| 17 |
+
- mlx-my-repo
|
| 18 |
+
license: apache-2.0
|
| 19 |
+
language:
|
| 20 |
+
- en
|
| 21 |
+
- zh
|
| 22 |
+
- es
|
| 23 |
+
- ru
|
| 24 |
+
- ja
|
| 25 |
+
pipeline_tag: text-generation
|
| 26 |
+
datasets:
|
| 27 |
+
- Jackrong/Claude-opus-4.6-TraceInversion-9000x
|
| 28 |
+
- Jackrong/Claude-opus-4.7-TraceInversion-5000x
|
| 29 |
+
- lambda/hermes-agent-reasoning-traces
|
| 30 |
+
---
|
| 31 |
+
|
| 32 |
+
# analogbox/Qwopus3.6-27B-Coder-mlx-5Bit
|
| 33 |
+
|
| 34 |
+
The Model [analogbox/Qwopus3.6-27B-Coder-mlx-5Bit](https://huggingface.co/analogbox/Qwopus3.6-27B-Coder-mlx-5Bit) was converted to MLX format from [Jackrong/Qwopus3.6-27B-Coder](https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder) using mlx-lm version **0.31.2**.
|
| 35 |
+
|
| 36 |
+
## Use with mlx
|
| 37 |
+
|
| 38 |
+
```bash
|
| 39 |
+
pip install mlx-lm
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
```python
|
| 43 |
+
from mlx_lm import load, generate
|
| 44 |
+
|
| 45 |
+
model, tokenizer = load("analogbox/Qwopus3.6-27B-Coder-mlx-5Bit")
|
| 46 |
+
|
| 47 |
+
prompt="hello"
|
| 48 |
+
|
| 49 |
+
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
|
| 50 |
+
messages = [{"role": "user", "content": prompt}]
|
| 51 |
+
prompt = tokenizer.apply_chat_template(
|
| 52 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 53 |
+
)
|
| 54 |
+
|
| 55 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 56 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
{%- if tools %}
|
| 3 |
+
{{- '<|im_start|>system
|
| 4 |
+
' }}
|
| 5 |
+
{%- if messages[0].role == 'system' %}
|
| 6 |
+
{{- messages[0].content + '
|
| 7 |
+
|
| 8 |
+
' }}
|
| 9 |
+
{%- endif %}
|
| 10 |
+
{{- "# Tools
|
| 11 |
+
|
| 12 |
+
You may call one or more functions to assist with the user query.
|
| 13 |
+
|
| 14 |
+
You are provided with function signatures within <tools></tools> XML tags:
|
| 15 |
+
<tools>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "
|
| 18 |
+
" }}
|
| 19 |
+
{{- tool | tojson }}
|
| 20 |
+
{%- endfor %}
|
| 21 |
+
{{- "
|
| 22 |
+
</tools>
|
| 23 |
+
|
| 24 |
+
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
| 25 |
+
<tool_call>
|
| 26 |
+
{\"name\": <function-name>, \"arguments\": <args-json-object>}
|
| 27 |
+
</tool_call><|im_end|>
|
| 28 |
+
" }}
|
| 29 |
+
{%- else %}
|
| 30 |
+
{%- if messages[0].role == 'system' %}
|
| 31 |
+
{{- '<|im_start|>system
|
| 32 |
+
' + messages[0].content + '<|im_end|>
|
| 33 |
+
' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 37 |
+
{%- for forward_message in messages %}
|
| 38 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 39 |
+
{%- set message = messages[index] %}
|
| 40 |
+
{%- set current_content = message.content if message.content is not none else '' %}
|
| 41 |
+
{%- set tool_start = '<tool_response>' %}
|
| 42 |
+
{%- set tool_start_length = tool_start|length %}
|
| 43 |
+
{%- set start_of_message = current_content[:tool_start_length] %}
|
| 44 |
+
{%- set tool_end = '</tool_response>' %}
|
| 45 |
+
{%- set tool_end_length = tool_end|length %}
|
| 46 |
+
{%- set start_pos = (current_content|length) - tool_end_length %}
|
| 47 |
+
{%- if start_pos < 0 %}
|
| 48 |
+
{%- set start_pos = 0 %}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- set end_of_message = current_content[start_pos:] %}
|
| 51 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
|
| 52 |
+
{%- set ns.multi_step_tool = false %}
|
| 53 |
+
{%- set ns.last_query_index = index %}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{%- endfor %}
|
| 56 |
+
{%- for message in messages %}
|
| 57 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 58 |
+
{{- '<|im_start|>' + message.role + '
|
| 59 |
+
' + message.content + '<|im_end|>' + '
|
| 60 |
+
' }}
|
| 61 |
+
{%- elif message.role == "assistant" %}
|
| 62 |
+
{%- set content = message.content %}
|
| 63 |
+
{%- set reasoning_content = '' %}
|
| 64 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 65 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 66 |
+
{%- else %}
|
| 67 |
+
{%- if '</think>' in message.content %}
|
| 68 |
+
{%- set content = (message.content.split('</think>')|last).lstrip('
|
| 69 |
+
') %}
|
| 70 |
+
{%- set reasoning_content = (message.content.split('</think>')|first).rstrip('
|
| 71 |
+
') %}
|
| 72 |
+
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('
|
| 73 |
+
') %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 77 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 78 |
+
{{- '<|im_start|>' + message.role + '
|
| 79 |
+
<think>
|
| 80 |
+
' + reasoning_content.strip('
|
| 81 |
+
') + '
|
| 82 |
+
</think>
|
| 83 |
+
|
| 84 |
+
' + content.lstrip('
|
| 85 |
+
') }}
|
| 86 |
+
{%- else %}
|
| 87 |
+
{{- '<|im_start|>' + message.role + '
|
| 88 |
+
' + content }}
|
| 89 |
+
{%- endif %}
|
| 90 |
+
{%- else %}
|
| 91 |
+
{{- '<|im_start|>' + message.role + '
|
| 92 |
+
' + content }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{%- if message.tool_calls %}
|
| 95 |
+
{%- for tool_call in message.tool_calls %}
|
| 96 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 97 |
+
{{- '
|
| 98 |
+
' }}
|
| 99 |
+
{%- endif %}
|
| 100 |
+
{%- if tool_call.function %}
|
| 101 |
+
{%- set tool_call = tool_call.function %}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
{{- '<tool_call>
|
| 104 |
+
{"name": "' }}
|
| 105 |
+
{{- tool_call.name }}
|
| 106 |
+
{{- '", "arguments": ' }}
|
| 107 |
+
{%- if tool_call.arguments is string %}
|
| 108 |
+
{{- tool_call.arguments }}
|
| 109 |
+
{%- else %}
|
| 110 |
+
{{- tool_call.arguments | tojson }}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '}
|
| 113 |
+
</tool_call>' }}
|
| 114 |
+
{%- endfor %}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{{- '<|im_end|>
|
| 117 |
+
' }}
|
| 118 |
+
{%- elif message.role == "tool" %}
|
| 119 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 120 |
+
{{- '<|im_start|>user' }}
|
| 121 |
+
{%- endif %}
|
| 122 |
+
{{- '
|
| 123 |
+
<tool_response>
|
| 124 |
+
' }}
|
| 125 |
+
{{- message.content }}
|
| 126 |
+
{{- '
|
| 127 |
+
</tool_response>' }}
|
| 128 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 129 |
+
{{- '<|im_end|>
|
| 130 |
+
' }}
|
| 131 |
+
{%- endif %}
|
| 132 |
+
{%- endif %}
|
| 133 |
+
{%- endfor %}
|
| 134 |
+
{%- if add_generation_prompt %}
|
| 135 |
+
{{- '<|im_start|>assistant
|
| 136 |
+
' }}
|
| 137 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 138 |
+
{{- '<think>
|
| 139 |
+
|
| 140 |
+
</think>
|
| 141 |
+
|
| 142 |
+
' }}
|
| 143 |
+
{%- endif %}
|
| 144 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
248046,
|
| 7 |
+
248044
|
| 8 |
+
],
|
| 9 |
+
"image_token_id": 248056,
|
| 10 |
+
"language_model_only": false,
|
| 11 |
+
"model_name": "Unsloth/qwen3.6-27B",
|
| 12 |
+
"model_type": "qwen3_5",
|
| 13 |
+
"mtp_num_hidden_layers": 1,
|
| 14 |
+
"pad_token_id": 248055,
|
| 15 |
+
"quantization": {
|
| 16 |
+
"group_size": 64,
|
| 17 |
+
"bits": 5,
|
| 18 |
+
"mode": "affine"
|
| 19 |
+
},
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"group_size": 64,
|
| 22 |
+
"bits": 5,
|
| 23 |
+
"mode": "affine"
|
| 24 |
+
},
|
| 25 |
+
"text_config": {
|
| 26 |
+
"attention_bias": false,
|
| 27 |
+
"attention_dropout": 0.0,
|
| 28 |
+
"attn_output_gate": true,
|
| 29 |
+
"bos_token_id": 248044,
|
| 30 |
+
"torch_dtype": "bfloat16",
|
| 31 |
+
"eos_token_id": 248044,
|
| 32 |
+
"full_attention_interval": 4,
|
| 33 |
+
"head_dim": 256,
|
| 34 |
+
"hidden_act": "silu",
|
| 35 |
+
"hidden_size": 5120,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 17408,
|
| 38 |
+
"layer_types": [
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"linear_attention",
|
| 65 |
+
"linear_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"linear_attention",
|
| 68 |
+
"linear_attention",
|
| 69 |
+
"linear_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"linear_attention",
|
| 72 |
+
"linear_attention",
|
| 73 |
+
"linear_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"linear_attention",
|
| 76 |
+
"linear_attention",
|
| 77 |
+
"linear_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"linear_attention",
|
| 82 |
+
"full_attention",
|
| 83 |
+
"linear_attention",
|
| 84 |
+
"linear_attention",
|
| 85 |
+
"linear_attention",
|
| 86 |
+
"full_attention",
|
| 87 |
+
"linear_attention",
|
| 88 |
+
"linear_attention",
|
| 89 |
+
"linear_attention",
|
| 90 |
+
"full_attention",
|
| 91 |
+
"linear_attention",
|
| 92 |
+
"linear_attention",
|
| 93 |
+
"linear_attention",
|
| 94 |
+
"full_attention",
|
| 95 |
+
"linear_attention",
|
| 96 |
+
"linear_attention",
|
| 97 |
+
"linear_attention",
|
| 98 |
+
"full_attention",
|
| 99 |
+
"linear_attention",
|
| 100 |
+
"linear_attention",
|
| 101 |
+
"linear_attention",
|
| 102 |
+
"full_attention"
|
| 103 |
+
],
|
| 104 |
+
"linear_conv_kernel_dim": 4,
|
| 105 |
+
"linear_key_head_dim": 128,
|
| 106 |
+
"linear_num_key_heads": 16,
|
| 107 |
+
"linear_num_value_heads": 48,
|
| 108 |
+
"linear_value_head_dim": 128,
|
| 109 |
+
"mamba_ssm_dtype": "float32",
|
| 110 |
+
"max_position_embeddings": 262144,
|
| 111 |
+
"model_type": "qwen3_5_text",
|
| 112 |
+
"mtp_num_hidden_layers": 1,
|
| 113 |
+
"mtp_use_dedicated_embeddings": false,
|
| 114 |
+
"num_attention_heads": 24,
|
| 115 |
+
"num_hidden_layers": 64,
|
| 116 |
+
"num_key_value_heads": 4,
|
| 117 |
+
"output_gate_type": "swish",
|
| 118 |
+
"pad_token_id": null,
|
| 119 |
+
"partial_rotary_factor": 0.25,
|
| 120 |
+
"rms_norm_eps": 1e-06,
|
| 121 |
+
"rope_parameters": {
|
| 122 |
+
"mrope_interleaved": true,
|
| 123 |
+
"mrope_section": [
|
| 124 |
+
11,
|
| 125 |
+
11,
|
| 126 |
+
10
|
| 127 |
+
],
|
| 128 |
+
"partial_rotary_factor": 0.25,
|
| 129 |
+
"rope_theta": 10000000,
|
| 130 |
+
"type": "default"
|
| 131 |
+
},
|
| 132 |
+
"tie_word_embeddings": false,
|
| 133 |
+
"use_cache": true,
|
| 134 |
+
"vocab_size": 248320
|
| 135 |
+
},
|
| 136 |
+
"tie_word_embeddings": false,
|
| 137 |
+
"torch_dtype": "bfloat16",
|
| 138 |
+
"unsloth_fixed_mtp": true,
|
| 139 |
+
"unsloth_version": "2026.5.9",
|
| 140 |
+
"video_token_id": 248057,
|
| 141 |
+
"vision_end_token_id": 248054,
|
| 142 |
+
"vision_start_token_id": 248053
|
| 143 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248055,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.3.0"
|
| 13 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9743bd5ce498cd970e05a8038213345e01b1e55c0044c4a815a5aeb2c75811
|
| 3 |
+
size 5360417859
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab0c013e604617a253d7ee7ff358f72e5d3afe8134d744f9321744e3f6589762
|
| 3 |
+
size 5338181777
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:522a6202c1edb5c9fb83873b3d39c0d36dd85550c6e277f91174a020eb15cab0
|
| 3 |
+
size 5355925620
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d66859d80cc4fd33dfafb8288e1e647219c620ca5043c8dcafc41edc1a0d69a
|
| 3 |
+
size 2440187747
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|vision_pad|>",
|
| 24 |
+
"padding_side": "left",
|
| 25 |
+
"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+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"tool_parser_type": "json_tools",
|
| 30 |
+
"unk_token": null,
|
| 31 |
+
"video_token": "<|video_pad|>",
|
| 32 |
+
"vision_bos_token": "<|vision_start|>",
|
| 33 |
+
"vision_eos_token": "<|vision_end|>"
|
| 34 |
+
}
|