Instructions to use bzouiri/B3G_ABP.IO_Coder_thinking_max with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bzouiri/B3G_ABP.IO_Coder_thinking_max with Transformers:

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

pipe = pipeline("text-generation", model="bzouiri/B3G_ABP.IO_Coder_thinking_max")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bzouiri/B3G_ABP.IO_Coder_thinking_max", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bzouiri/B3G_ABP.IO_Coder_thinking_max with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bzouiri/B3G_ABP.IO_Coder_thinking_max"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bzouiri/B3G_ABP.IO_Coder_thinking_max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bzouiri/B3G_ABP.IO_Coder_thinking_max

SGLang

How to use bzouiri/B3G_ABP.IO_Coder_thinking_max 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 "bzouiri/B3G_ABP.IO_Coder_thinking_max" \
    --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": "bzouiri/B3G_ABP.IO_Coder_thinking_max",
		"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 "bzouiri/B3G_ABP.IO_Coder_thinking_max" \
        --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": "bzouiri/B3G_ABP.IO_Coder_thinking_max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use bzouiri/B3G_ABP.IO_Coder_thinking_max 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 bzouiri/B3G_ABP.IO_Coder_thinking_max 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 bzouiri/B3G_ABP.IO_Coder_thinking_max to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bzouiri/B3G_ABP.IO_Coder_thinking_max to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="bzouiri/B3G_ABP.IO_Coder_thinking_max",
    max_seq_length=2048,
)

Docker Model Runner
How to use bzouiri/B3G_ABP.IO_Coder_thinking_max with Docker Model Runner:
```
docker model run hf.co/bzouiri/B3G_ABP.IO_Coder_thinking_max
```

bzouiri commited on Jul 16, 2025

Commit

5fec1e5

verified ·

1 Parent(s): d642bb6

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +3 -3
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "k_proj",
     "q_proj",
-    "v_proj",
     "gate_proj",
     "o_proj",
-    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
     "q_proj",
+    "down_proj",
     "gate_proj",
     "o_proj",
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09657d033ceb1826dbab882303b307d9cdb976d80eb724240845921abd834ed
 size 513877864

 version https://git-lfs.github.com/spec/v1
+oid sha256:051f0b722ba11316902a5ba5116105ec41def966d134f4880e00831aa3b7d60e
 size 513877864