Instructions to use Kaleto/Fallen-Command-111B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kaleto/Fallen-Command-111B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="Kaleto/Fallen-Command-111B-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kaleto/Fallen-Command-111B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("Kaleto/Fallen-Command-111B-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kaleto/Fallen-Command-111B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kaleto/Fallen-Command-111B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kaleto/Fallen-Command-111B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kaleto/Fallen-Command-111B-NVFP4

SGLang

How to use Kaleto/Fallen-Command-111B-NVFP4 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 "Kaleto/Fallen-Command-111B-NVFP4" \
    --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": "Kaleto/Fallen-Command-111B-NVFP4",
		"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 "Kaleto/Fallen-Command-111B-NVFP4" \
        --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": "Kaleto/Fallen-Command-111B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kaleto/Fallen-Command-111B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Kaleto/Fallen-Command-111B-NVFP4
```

Fallen-Command-111B-NVFP4 / config.json

Kaleto

Upload config.json with huggingface_hub

767e22d verified 5 days ago

raw

history blame contribute delete

3.26 kB

	{
	"_sliding_window_pattern": 4,
	"architectures": [
	"Cohere2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 5,
	"cache_implementation": "hybrid",
	"dtype": "bfloat16",
	"eos_token_id": 255001,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 12288,
	"initializer_range": 0.02,
	"intermediate_size": 36864,
	"layer_norm_eps": 1e-05,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"logit_scale": 0.25,
	"max_position_embeddings": 262144,
	"model_type": "cohere2",
	"num_attention_heads": 96,
	"num_hidden_layers": 64,
	"num_key_value_heads": 8,
	"order_of_interleaved_layers": "local_attn_first",
	"pad_token_id": 0,
	"position_embedding_type": "rope_gptj",
	"rope_scaling": null,
	"rope_theta": 50000,
	"rotary_pct": 1.0,
	"sliding_window": 4096,
	"sliding_window_pattern": 4,
	"transformers_version": "4.57.6",
	"unsloth_fixed": true,
	"unsloth_version": "2025.3.19",
	"use_cache": false,
	"use_embedding_sharing": true,
	"use_gated_activation": true,
	"use_parallel_block": true,
	"use_parallel_embedding": true,
	"vocab_size": 256000,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"input_activations": {
	"dynamic": true,
	"num_bits": 4,
	"type": "float",
	"group_size": 16
	},
	"weights": {
	"dynamic": false,
	"num_bits": 4,
	"type": "float",
	"group_size": 16
	},
	"targets": [
	"Linear"
	]
	}
	},
	"ignore": [
	"lm_head"
	],
	"quant_algo": "NVFP4",
	"producer": {
	"name": "modelopt",
	"version": "0.43.0"
	},
	"quant_method": "modelopt"
	}
	}