Instructions to use Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF")
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 AutoModel
model = AutoModel.from_pretrained("Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF

SGLang

How to use Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF 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 "Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF" \
    --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": "Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF" \
        --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": "Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF 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 Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF 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 Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF",
    max_seq_length=2048,
)

Docker Model Runner
How to use Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF
```

failed to parse grammar with llama.cpp on master

by nervousapps - opened Jun 25

Discussion

nervousapps

Jun 25

When running llama-server with these args :

./build/bin/llama-server -m ../models/Qwopus3.6-27B-Coder-Compat-MTP-Q8_0.gguf --host 0.0.0.0 --port 11435 --mlock --cache-type-k q8_0 --cache-type-v q8_0 --flash-attn on -b 4096 -ub 2048 --no-webui --offline -c 262144 --ctx-checkpoints 32 --keep -1 --split-mode tensor -np 1 --log-verbosity 4 --jinja --no-mmap --kv-unified --spec-type draft-mtp --spec-draft-type-v q8_0 --spec-draft-type-k q8_0 --spec-draft-n-max 4 --mmproj ../models/mmproj-F32-QW36compat.gguf

I got this error :

2.44.107.624 I srv get_availabl: prompt cache update took 1.00 ms
parse: error parsing grammar: unknown escape at \w-]+) """
tool-RemoteTrigger-schema-trigger-id-kv ::= ""trigger_id"" space ":" space tool-RemoteTrigger-schema-trigger-id
.
.
.
tool-memory-update-schema-memory-id-kv ::= ""memory_id"" space ":" space string
tool-memory-update-schema-new-content-kv ::= ""new_content"" space ":" space string
tool-memory-update-schema-reason-kv ::= ""reason"" space ":" space string
value ::= object | array | string | number | boolean | null

2.43.628.098 E failed to parse grammar
2.43.628.603 E srv send_error: task id = 11, error: Failed to initialize samplers: failed to parse grammar
2.43.628.618 E srv process_sing: failed to launch slot with task, id_task = 11
2.43.628.768 W srv stop: cancel task, id_task = 11

Any thoughts about what is happening? Template needs to be defined?

Linukso1D

Jun 27

Hello @nervousapps , I had the same error with the sampler initializing, but I've found this chat template version: https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates, then I put it in the launch command like that:

./build/bin/llama-server \
     --model /home/linukso1d/LLM/models/MTP/Qwopus3.6-27B-Coder-Compat-MTP-Q5_K_M.gguf \
     --jinja --chat-template-file /home/linukso1d/LLM/models/MTP/chat_template.jinja \
...

So the connected Claude code doesn't crash anymore, tool call is working, try it out, maybe it will help

ptitza

Jul 7

•

edited Jul 7

I had the same error with the sampler initializing, but I've found this chat template version: https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates, then I put it in the launch command like that:
@Linukso1D

without this template pi tool call also not work

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment