Instructions to use bjk110/Qwen3.5-122B-A10B-abliterated-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bjk110/Qwen3.5-122B-A10B-abliterated-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="bjk110/Qwen3.5-122B-A10B-abliterated-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("bjk110/Qwen3.5-122B-A10B-abliterated-FP8")
model = AutoModelForCausalLM.from_pretrained("bjk110/Qwen3.5-122B-A10B-abliterated-FP8", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bjk110/Qwen3.5-122B-A10B-abliterated-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bjk110/Qwen3.5-122B-A10B-abliterated-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bjk110/Qwen3.5-122B-A10B-abliterated-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bjk110/Qwen3.5-122B-A10B-abliterated-FP8

SGLang

How to use bjk110/Qwen3.5-122B-A10B-abliterated-FP8 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 "bjk110/Qwen3.5-122B-A10B-abliterated-FP8" \
    --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": "bjk110/Qwen3.5-122B-A10B-abliterated-FP8",
		"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 "bjk110/Qwen3.5-122B-A10B-abliterated-FP8" \
        --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": "bjk110/Qwen3.5-122B-A10B-abliterated-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bjk110/Qwen3.5-122B-A10B-abliterated-FP8 with Docker Model Runner:
```
docker model run hf.co/bjk110/Qwen3.5-122B-A10B-abliterated-FP8
```

Qwen3.5-122B-A10B-abliterated-FP8 / config.json

Ban

Upload FP8 block-wise quantized model (128x128, weight_scale_inv)

ee139d3 verified 5 months ago

Raw

History Blame

17.4 kB

	{
	"architectures": [
	"Qwen3_5MoeForCausalLM"
	],
	"model_type": "qwen3_5_moe",
	"text_config": {
	"architectures": [
	"Qwen3_5MoeForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 64,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"mlp_only_layers": [],
	"model_type": "qwen3_5_moe_text",
	"moe_intermediate_size": 1024,
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 32,
	"num_experts": 256,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 48,
	"num_key_value_heads": 2,
	"output_router_logits": false,
	"pad_token_id": null,
	"partial_rotary_factor": 0.25,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	11,
	11,
	10
	],
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"router_aux_loss_coef": 0.001,
	"shared_expert_intermediate_size": 1024,
	"tie_word_embeddings": false,
	"transformers_version": "5.3.0.dev0",
	"use_cache": true,
	"vocab_size": 248320
	},
	"quantization_config": {
	"quant_method": "fp8",
	"activation_scheme": "dynamic",
	"act_per_tensor": false,
	"modules_to_not_convert": [
	"lm_head",
	"model.language_model.embed_tokens",
	"model.language_model.layers.0.linear_attn.conv1d",
	"model.language_model.layers.0.linear_attn.in_proj_a",
	"model.language_model.layers.0.linear_attn.in_proj_b",
	"model.language_model.layers.0.mlp.gate",
	"model.language_model.layers.0.mlp.shared_expert_gate",
	"model.language_model.layers.1.linear_attn.conv1d",
	"model.language_model.layers.1.linear_attn.in_proj_a",
	"model.language_model.layers.1.linear_attn.in_proj_b",
	"model.language_model.layers.1.mlp.gate",
	"model.language_model.layers.1.mlp.shared_expert_gate",
	"model.language_model.layers.10.linear_attn.conv1d",
	"model.language_model.layers.10.linear_attn.in_proj_a",
	"model.language_model.layers.10.linear_attn.in_proj_b",
	"model.language_model.layers.10.mlp.gate",
	"model.language_model.layers.10.mlp.shared_expert_gate",
	"model.language_model.layers.11.linear_attn.conv1d",
	"model.language_model.layers.11.linear_attn.in_proj_a",
	"model.language_model.layers.11.linear_attn.in_proj_b",
	"model.language_model.layers.11.mlp.gate",
	"model.language_model.layers.11.mlp.shared_expert_gate",
	"model.language_model.layers.12.linear_attn.conv1d",
	"model.language_model.layers.12.linear_attn.in_proj_a",
	"model.language_model.layers.12.linear_attn.in_proj_b",
	"model.language_model.layers.12.mlp.gate",
	"model.language_model.layers.12.mlp.shared_expert_gate",
	"model.language_model.layers.13.linear_attn.conv1d",
	"model.language_model.layers.13.linear_attn.in_proj_a",
	"model.language_model.layers.13.linear_attn.in_proj_b",
	"model.language_model.layers.13.mlp.gate",
	"model.language_model.layers.13.mlp.shared_expert_gate",
	"model.language_model.layers.14.linear_attn.conv1d",
	"model.language_model.layers.14.linear_attn.in_proj_a",
	"model.language_model.layers.14.linear_attn.in_proj_b",
	"model.language_model.layers.14.mlp.gate",
	"model.language_model.layers.14.mlp.shared_expert_gate",
	"model.language_model.layers.15.linear_attn.conv1d",
	"model.language_model.layers.15.linear_attn.in_proj_a",
	"model.language_model.layers.15.linear_attn.in_proj_b",
	"model.language_model.layers.15.mlp.gate",
	"model.language_model.layers.15.mlp.shared_expert_gate",
	"model.language_model.layers.16.linear_attn.conv1d",
	"model.language_model.layers.16.linear_attn.in_proj_a",
	"model.language_model.layers.16.linear_attn.in_proj_b",
	"model.language_model.layers.16.mlp.gate",
	"model.language_model.layers.16.mlp.shared_expert_gate",
	"model.language_model.layers.17.linear_attn.conv1d",
	"model.language_model.layers.17.linear_attn.in_proj_a",
	"model.language_model.layers.17.linear_attn.in_proj_b",
	"model.language_model.layers.17.mlp.gate",
	"model.language_model.layers.17.mlp.shared_expert_gate",
	"model.language_model.layers.18.linear_attn.conv1d",
	"model.language_model.layers.18.linear_attn.in_proj_a",
	"model.language_model.layers.18.linear_attn.in_proj_b",
	"model.language_model.layers.18.mlp.gate",
	"model.language_model.layers.18.mlp.shared_expert_gate",
	"model.language_model.layers.19.linear_attn.conv1d",
	"model.language_model.layers.19.linear_attn.in_proj_a",
	"model.language_model.layers.19.linear_attn.in_proj_b",
	"model.language_model.layers.19.mlp.gate",
	"model.language_model.layers.19.mlp.shared_expert_gate",
	"model.language_model.layers.2.linear_attn.conv1d",
	"model.language_model.layers.2.linear_attn.in_proj_a",
	"model.language_model.layers.2.linear_attn.in_proj_b",
	"model.language_model.layers.2.mlp.gate",
	"model.language_model.layers.2.mlp.shared_expert_gate",
	"model.language_model.layers.20.linear_attn.conv1d",
	"model.language_model.layers.20.linear_attn.in_proj_a",
	"model.language_model.layers.20.linear_attn.in_proj_b",
	"model.language_model.layers.20.mlp.gate",
	"model.language_model.layers.20.mlp.shared_expert_gate",
	"model.language_model.layers.21.linear_attn.conv1d",
	"model.language_model.layers.21.linear_attn.in_proj_a",
	"model.language_model.layers.21.linear_attn.in_proj_b",
	"model.language_model.layers.21.mlp.gate",
	"model.language_model.layers.21.mlp.shared_expert_gate",
	"model.language_model.layers.22.linear_attn.conv1d",
	"model.language_model.layers.22.linear_attn.in_proj_a",
	"model.language_model.layers.22.linear_attn.in_proj_b",
	"model.language_model.layers.22.mlp.gate",
	"model.language_model.layers.22.mlp.shared_expert_gate",
	"model.language_model.layers.23.linear_attn.conv1d",
	"model.language_model.layers.23.linear_attn.in_proj_a",
	"model.language_model.layers.23.linear_attn.in_proj_b",
	"model.language_model.layers.23.mlp.gate",
	"model.language_model.layers.23.mlp.shared_expert_gate",
	"model.language_model.layers.24.linear_attn.conv1d",
	"model.language_model.layers.24.linear_attn.in_proj_a",
	"model.language_model.layers.24.linear_attn.in_proj_b",
	"model.language_model.layers.24.mlp.gate",
	"model.language_model.layers.24.mlp.shared_expert_gate",
	"model.language_model.layers.25.linear_attn.conv1d",
	"model.language_model.layers.25.linear_attn.in_proj_a",
	"model.language_model.layers.25.linear_attn.in_proj_b",
	"model.language_model.layers.25.mlp.gate",
	"model.language_model.layers.25.mlp.shared_expert_gate",
	"model.language_model.layers.26.linear_attn.conv1d",
	"model.language_model.layers.26.linear_attn.in_proj_a",
	"model.language_model.layers.26.linear_attn.in_proj_b",
	"model.language_model.layers.26.mlp.gate",
	"model.language_model.layers.26.mlp.shared_expert_gate",
	"model.language_model.layers.27.linear_attn.conv1d",
	"model.language_model.layers.27.linear_attn.in_proj_a",
	"model.language_model.layers.27.linear_attn.in_proj_b",
	"model.language_model.layers.27.mlp.gate",
	"model.language_model.layers.27.mlp.shared_expert_gate",
	"model.language_model.layers.28.linear_attn.conv1d",
	"model.language_model.layers.28.linear_attn.in_proj_a",
	"model.language_model.layers.28.linear_attn.in_proj_b",
	"model.language_model.layers.28.mlp.gate",
	"model.language_model.layers.28.mlp.shared_expert_gate",
	"model.language_model.layers.29.linear_attn.conv1d",
	"model.language_model.layers.29.linear_attn.in_proj_a",
	"model.language_model.layers.29.linear_attn.in_proj_b",
	"model.language_model.layers.29.mlp.gate",
	"model.language_model.layers.29.mlp.shared_expert_gate",
	"model.language_model.layers.3.linear_attn.conv1d",
	"model.language_model.layers.3.linear_attn.in_proj_a",
	"model.language_model.layers.3.linear_attn.in_proj_b",
	"model.language_model.layers.3.mlp.gate",
	"model.language_model.layers.3.mlp.shared_expert_gate",
	"model.language_model.layers.30.linear_attn.conv1d",
	"model.language_model.layers.30.linear_attn.in_proj_a",
	"model.language_model.layers.30.linear_attn.in_proj_b",
	"model.language_model.layers.30.mlp.gate",
	"model.language_model.layers.30.mlp.shared_expert_gate",
	"model.language_model.layers.31.linear_attn.conv1d",
	"model.language_model.layers.31.linear_attn.in_proj_a",
	"model.language_model.layers.31.linear_attn.in_proj_b",
	"model.language_model.layers.31.mlp.gate",
	"model.language_model.layers.31.mlp.shared_expert_gate",
	"model.language_model.layers.32.linear_attn.conv1d",
	"model.language_model.layers.32.linear_attn.in_proj_a",
	"model.language_model.layers.32.linear_attn.in_proj_b",
	"model.language_model.layers.32.mlp.gate",
	"model.language_model.layers.32.mlp.shared_expert_gate",
	"model.language_model.layers.33.linear_attn.conv1d",
	"model.language_model.layers.33.linear_attn.in_proj_a",
	"model.language_model.layers.33.linear_attn.in_proj_b",
	"model.language_model.layers.33.mlp.gate",
	"model.language_model.layers.33.mlp.shared_expert_gate",
	"model.language_model.layers.34.linear_attn.conv1d",
	"model.language_model.layers.34.linear_attn.in_proj_a",
	"model.language_model.layers.34.linear_attn.in_proj_b",
	"model.language_model.layers.34.mlp.gate",
	"model.language_model.layers.34.mlp.shared_expert_gate",
	"model.language_model.layers.35.linear_attn.conv1d",
	"model.language_model.layers.35.linear_attn.in_proj_a",
	"model.language_model.layers.35.linear_attn.in_proj_b",
	"model.language_model.layers.35.mlp.gate",
	"model.language_model.layers.35.mlp.shared_expert_gate",
	"model.language_model.layers.36.linear_attn.conv1d",
	"model.language_model.layers.36.linear_attn.in_proj_a",
	"model.language_model.layers.36.linear_attn.in_proj_b",
	"model.language_model.layers.36.mlp.gate",
	"model.language_model.layers.36.mlp.shared_expert_gate",
	"model.language_model.layers.37.linear_attn.conv1d",
	"model.language_model.layers.37.linear_attn.in_proj_a",
	"model.language_model.layers.37.linear_attn.in_proj_b",
	"model.language_model.layers.37.mlp.gate",
	"model.language_model.layers.37.mlp.shared_expert_gate",
	"model.language_model.layers.38.linear_attn.conv1d",
	"model.language_model.layers.38.linear_attn.in_proj_a",
	"model.language_model.layers.38.linear_attn.in_proj_b",
	"model.language_model.layers.38.mlp.gate",
	"model.language_model.layers.38.mlp.shared_expert_gate",
	"model.language_model.layers.39.linear_attn.conv1d",
	"model.language_model.layers.39.linear_attn.in_proj_a",
	"model.language_model.layers.39.linear_attn.in_proj_b",
	"model.language_model.layers.39.mlp.gate",
	"model.language_model.layers.39.mlp.shared_expert_gate",
	"model.language_model.layers.4.linear_attn.conv1d",
	"model.language_model.layers.4.linear_attn.in_proj_a",
	"model.language_model.layers.4.linear_attn.in_proj_b",
	"model.language_model.layers.4.mlp.gate",
	"model.language_model.layers.4.mlp.shared_expert_gate",
	"model.language_model.layers.40.linear_attn.conv1d",
	"model.language_model.layers.40.linear_attn.in_proj_a",
	"model.language_model.layers.40.linear_attn.in_proj_b",
	"model.language_model.layers.40.mlp.gate",
	"model.language_model.layers.40.mlp.shared_expert_gate",
	"model.language_model.layers.41.linear_attn.conv1d",
	"model.language_model.layers.41.linear_attn.in_proj_a",
	"model.language_model.layers.41.linear_attn.in_proj_b",
	"model.language_model.layers.41.mlp.gate",
	"model.language_model.layers.41.mlp.shared_expert_gate",
	"model.language_model.layers.42.linear_attn.conv1d",
	"model.language_model.layers.42.linear_attn.in_proj_a",
	"model.language_model.layers.42.linear_attn.in_proj_b",
	"model.language_model.layers.42.mlp.gate",
	"model.language_model.layers.42.mlp.shared_expert_gate",
	"model.language_model.layers.43.linear_attn.conv1d",
	"model.language_model.layers.43.linear_attn.in_proj_a",
	"model.language_model.layers.43.linear_attn.in_proj_b",
	"model.language_model.layers.43.mlp.gate",
	"model.language_model.layers.43.mlp.shared_expert_gate",
	"model.language_model.layers.44.linear_attn.conv1d",
	"model.language_model.layers.44.linear_attn.in_proj_a",
	"model.language_model.layers.44.linear_attn.in_proj_b",
	"model.language_model.layers.44.mlp.gate",
	"model.language_model.layers.44.mlp.shared_expert_gate",
	"model.language_model.layers.45.linear_attn.conv1d",
	"model.language_model.layers.45.linear_attn.in_proj_a",
	"model.language_model.layers.45.linear_attn.in_proj_b",
	"model.language_model.layers.45.mlp.gate",
	"model.language_model.layers.45.mlp.shared_expert_gate",
	"model.language_model.layers.46.linear_attn.conv1d",
	"model.language_model.layers.46.linear_attn.in_proj_a",
	"model.language_model.layers.46.linear_attn.in_proj_b",
	"model.language_model.layers.46.mlp.gate",
	"model.language_model.layers.46.mlp.shared_expert_gate",
	"model.language_model.layers.47.linear_attn.conv1d",
	"model.language_model.layers.47.linear_attn.in_proj_a",
	"model.language_model.layers.47.linear_attn.in_proj_b",
	"model.language_model.layers.47.mlp.gate",
	"model.language_model.layers.47.mlp.shared_expert_gate",
	"model.language_model.layers.5.linear_attn.conv1d",
	"model.language_model.layers.5.linear_attn.in_proj_a",
	"model.language_model.layers.5.linear_attn.in_proj_b",
	"model.language_model.layers.5.mlp.gate",
	"model.language_model.layers.5.mlp.shared_expert_gate",
	"model.language_model.layers.6.linear_attn.conv1d",
	"model.language_model.layers.6.linear_attn.in_proj_a",
	"model.language_model.layers.6.linear_attn.in_proj_b",
	"model.language_model.layers.6.mlp.gate",
	"model.language_model.layers.6.mlp.shared_expert_gate",
	"model.language_model.layers.7.linear_attn.conv1d",
	"model.language_model.layers.7.linear_attn.in_proj_a",
	"model.language_model.layers.7.linear_attn.in_proj_b",
	"model.language_model.layers.7.mlp.gate",
	"model.language_model.layers.7.mlp.shared_expert_gate",
	"model.language_model.layers.8.linear_attn.conv1d",
	"model.language_model.layers.8.linear_attn.in_proj_a",
	"model.language_model.layers.8.linear_attn.in_proj_b",
	"model.language_model.layers.8.mlp.gate",
	"model.language_model.layers.8.mlp.shared_expert_gate",
	"model.language_model.layers.9.linear_attn.conv1d",
	"model.language_model.layers.9.linear_attn.in_proj_a",
	"model.language_model.layers.9.linear_attn.in_proj_b",
	"model.language_model.layers.9.mlp.gate",
	"model.language_model.layers.9.mlp.shared_expert_gate"
	],
	"weight_block_size": [
	128,
	128
	],
	"weight_per_tensor": false
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.3.0.dev0",
	"vision_config": null
	}