Instructions to use CohereLabs/North-Mini-Code-1.0-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/North-Mini-Code-1.0-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="CohereLabs/North-Mini-Code-1.0-fp8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/North-Mini-Code-1.0-fp8")
model = AutoModelForCausalLM.from_pretrained("CohereLabs/North-Mini-Code-1.0-fp8")
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 Settings

vLLM

How to use CohereLabs/North-Mini-Code-1.0-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CohereLabs/North-Mini-Code-1.0-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": "CohereLabs/North-Mini-Code-1.0-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CohereLabs/North-Mini-Code-1.0-fp8

SGLang

How to use CohereLabs/North-Mini-Code-1.0-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 "CohereLabs/North-Mini-Code-1.0-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": "CohereLabs/North-Mini-Code-1.0-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 "CohereLabs/North-Mini-Code-1.0-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": "CohereLabs/North-Mini-Code-1.0-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CohereLabs/North-Mini-Code-1.0-fp8 with Docker Model Runner:
```
docker model run hf.co/CohereLabs/North-Mini-Code-1.0-fp8
```

North-Mini-Code-1.0-fp8 / config.json

Terrencez

Initial commit

d7bddec verified 1 day ago

raw

history blame contribute delete

13.6 kB

	{
	"architectures": [
	"Cohere2MoeForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 2,
	"dtype": "bfloat16",
	"eos_token_id": 255001,
	"expert_selection_fn": "sigmoid",
	"first_k_dense_replace": 1,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 768,
	"layer_norm_eps": 1e-05,
	"layer_types": [
	"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": 1.0,
	"max_position_embeddings": 500000,
	"model_type": "cohere2_moe",
	"norm_topk_prob": false,
	"num_attention_heads": 32,
	"num_experts": 128,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 49,
	"num_key_value_heads": 4,
	"num_shared_experts": 0,
	"pad_token_id": 0,
	"prefix_dense_intermediate_size": 3072,
	"prefix_dense_sliding_window_pattern": 1,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 50000,
	"shared_expert_combination_strategy": "average",
	"sliding_window": 4096,
	"transformers_version": "5.8.0",
	"use_cache": true,
	"use_gated_activation": true,
	"use_parallel_block": true,
	"use_parallel_embedding": false,
	"use_qk_norm": false,
	"vocab_size": 262144,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "float-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": true,
	"group_size": null,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "token",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": null,
	"num_bits": 8,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "channel",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	}
	}
	},
	"format": "float-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"model.layers.0.self_attn.q_proj",
	"model.layers.0.self_attn.k_proj",
	"model.layers.0.self_attn.v_proj",
	"model.layers.0.self_attn.o_proj",
	"model.layers.0.mlp.gate_proj",
	"model.layers.0.mlp.up_proj",
	"model.layers.0.mlp.down_proj",
	"model.layers.1.self_attn.q_proj",
	"model.layers.1.self_attn.k_proj",
	"model.layers.1.self_attn.v_proj",
	"model.layers.1.self_attn.o_proj",
	"model.layers.1.mlp.gate",
	"model.layers.2.self_attn.q_proj",
	"model.layers.2.self_attn.k_proj",
	"model.layers.2.self_attn.v_proj",
	"model.layers.2.self_attn.o_proj",
	"model.layers.2.mlp.gate",
	"model.layers.3.self_attn.q_proj",
	"model.layers.3.self_attn.k_proj",
	"model.layers.3.self_attn.v_proj",
	"model.layers.3.self_attn.o_proj",
	"model.layers.3.mlp.gate",
	"model.layers.4.self_attn.q_proj",
	"model.layers.4.self_attn.k_proj",
	"model.layers.4.self_attn.v_proj",
	"model.layers.4.self_attn.o_proj",
	"model.layers.4.mlp.gate",
	"model.layers.5.self_attn.q_proj",
	"model.layers.5.self_attn.k_proj",
	"model.layers.5.self_attn.v_proj",
	"model.layers.5.self_attn.o_proj",
	"model.layers.5.mlp.gate",
	"model.layers.6.self_attn.q_proj",
	"model.layers.6.self_attn.k_proj",
	"model.layers.6.self_attn.v_proj",
	"model.layers.6.self_attn.o_proj",
	"model.layers.6.mlp.gate",
	"model.layers.7.self_attn.q_proj",
	"model.layers.7.self_attn.k_proj",
	"model.layers.7.self_attn.v_proj",
	"model.layers.7.self_attn.o_proj",
	"model.layers.7.mlp.gate",
	"model.layers.8.self_attn.q_proj",
	"model.layers.8.self_attn.k_proj",
	"model.layers.8.self_attn.v_proj",
	"model.layers.8.self_attn.o_proj",
	"model.layers.8.mlp.gate",
	"model.layers.9.self_attn.q_proj",
	"model.layers.9.self_attn.k_proj",
	"model.layers.9.self_attn.v_proj",
	"model.layers.9.self_attn.o_proj",
	"model.layers.9.mlp.gate",
	"model.layers.10.self_attn.q_proj",
	"model.layers.10.self_attn.k_proj",
	"model.layers.10.self_attn.v_proj",
	"model.layers.10.self_attn.o_proj",
	"model.layers.10.mlp.gate",
	"model.layers.11.self_attn.q_proj",
	"model.layers.11.self_attn.k_proj",
	"model.layers.11.self_attn.v_proj",
	"model.layers.11.self_attn.o_proj",
	"model.layers.11.mlp.gate",
	"model.layers.12.self_attn.q_proj",
	"model.layers.12.self_attn.k_proj",
	"model.layers.12.self_attn.v_proj",
	"model.layers.12.self_attn.o_proj",
	"model.layers.12.mlp.gate",
	"model.layers.13.self_attn.q_proj",
	"model.layers.13.self_attn.k_proj",
	"model.layers.13.self_attn.v_proj",
	"model.layers.13.self_attn.o_proj",
	"model.layers.13.mlp.gate",
	"model.layers.14.self_attn.q_proj",
	"model.layers.14.self_attn.k_proj",
	"model.layers.14.self_attn.v_proj",
	"model.layers.14.self_attn.o_proj",
	"model.layers.14.mlp.gate",
	"model.layers.15.self_attn.q_proj",
	"model.layers.15.self_attn.k_proj",
	"model.layers.15.self_attn.v_proj",
	"model.layers.15.self_attn.o_proj",
	"model.layers.15.mlp.gate",
	"model.layers.16.self_attn.q_proj",
	"model.layers.16.self_attn.k_proj",
	"model.layers.16.self_attn.v_proj",
	"model.layers.16.self_attn.o_proj",
	"model.layers.16.mlp.gate",
	"model.layers.17.self_attn.q_proj",
	"model.layers.17.self_attn.k_proj",
	"model.layers.17.self_attn.v_proj",
	"model.layers.17.self_attn.o_proj",
	"model.layers.17.mlp.gate",
	"model.layers.18.self_attn.q_proj",
	"model.layers.18.self_attn.k_proj",
	"model.layers.18.self_attn.v_proj",
	"model.layers.18.self_attn.o_proj",
	"model.layers.18.mlp.gate",
	"model.layers.19.self_attn.q_proj",
	"model.layers.19.self_attn.k_proj",
	"model.layers.19.self_attn.v_proj",
	"model.layers.19.self_attn.o_proj",
	"model.layers.19.mlp.gate",
	"model.layers.20.self_attn.q_proj",
	"model.layers.20.self_attn.k_proj",
	"model.layers.20.self_attn.v_proj",
	"model.layers.20.self_attn.o_proj",
	"model.layers.20.mlp.gate",
	"model.layers.21.self_attn.q_proj",
	"model.layers.21.self_attn.k_proj",
	"model.layers.21.self_attn.v_proj",
	"model.layers.21.self_attn.o_proj",
	"model.layers.21.mlp.gate",
	"model.layers.22.self_attn.q_proj",
	"model.layers.22.self_attn.k_proj",
	"model.layers.22.self_attn.v_proj",
	"model.layers.22.self_attn.o_proj",
	"model.layers.22.mlp.gate",
	"model.layers.23.self_attn.q_proj",
	"model.layers.23.self_attn.k_proj",
	"model.layers.23.self_attn.v_proj",
	"model.layers.23.self_attn.o_proj",
	"model.layers.23.mlp.gate",
	"model.layers.24.self_attn.q_proj",
	"model.layers.24.self_attn.k_proj",
	"model.layers.24.self_attn.v_proj",
	"model.layers.24.self_attn.o_proj",
	"model.layers.24.mlp.gate",
	"model.layers.25.self_attn.q_proj",
	"model.layers.25.self_attn.k_proj",
	"model.layers.25.self_attn.v_proj",
	"model.layers.25.self_attn.o_proj",
	"model.layers.25.mlp.gate",
	"model.layers.26.self_attn.q_proj",
	"model.layers.26.self_attn.k_proj",
	"model.layers.26.self_attn.v_proj",
	"model.layers.26.self_attn.o_proj",
	"model.layers.26.mlp.gate",
	"model.layers.27.self_attn.q_proj",
	"model.layers.27.self_attn.k_proj",
	"model.layers.27.self_attn.v_proj",
	"model.layers.27.self_attn.o_proj",
	"model.layers.27.mlp.gate",
	"model.layers.28.self_attn.q_proj",
	"model.layers.28.self_attn.k_proj",
	"model.layers.28.self_attn.v_proj",
	"model.layers.28.self_attn.o_proj",
	"model.layers.28.mlp.gate",
	"model.layers.29.self_attn.q_proj",
	"model.layers.29.self_attn.k_proj",
	"model.layers.29.self_attn.v_proj",
	"model.layers.29.self_attn.o_proj",
	"model.layers.29.mlp.gate",
	"model.layers.30.self_attn.q_proj",
	"model.layers.30.self_attn.k_proj",
	"model.layers.30.self_attn.v_proj",
	"model.layers.30.self_attn.o_proj",
	"model.layers.30.mlp.gate",
	"model.layers.31.self_attn.q_proj",
	"model.layers.31.self_attn.k_proj",
	"model.layers.31.self_attn.v_proj",
	"model.layers.31.self_attn.o_proj",
	"model.layers.31.mlp.gate",
	"model.layers.32.self_attn.q_proj",
	"model.layers.32.self_attn.k_proj",
	"model.layers.32.self_attn.v_proj",
	"model.layers.32.self_attn.o_proj",
	"model.layers.32.mlp.gate",
	"model.layers.33.self_attn.q_proj",
	"model.layers.33.self_attn.k_proj",
	"model.layers.33.self_attn.v_proj",
	"model.layers.33.self_attn.o_proj",
	"model.layers.33.mlp.gate",
	"model.layers.34.self_attn.q_proj",
	"model.layers.34.self_attn.k_proj",
	"model.layers.34.self_attn.v_proj",
	"model.layers.34.self_attn.o_proj",
	"model.layers.34.mlp.gate",
	"model.layers.35.self_attn.q_proj",
	"model.layers.35.self_attn.k_proj",
	"model.layers.35.self_attn.v_proj",
	"model.layers.35.self_attn.o_proj",
	"model.layers.35.mlp.gate",
	"model.layers.36.self_attn.q_proj",
	"model.layers.36.self_attn.k_proj",
	"model.layers.36.self_attn.v_proj",
	"model.layers.36.self_attn.o_proj",
	"model.layers.36.mlp.gate",
	"model.layers.37.self_attn.q_proj",
	"model.layers.37.self_attn.k_proj",
	"model.layers.37.self_attn.v_proj",
	"model.layers.37.self_attn.o_proj",
	"model.layers.37.mlp.gate",
	"model.layers.38.self_attn.q_proj",
	"model.layers.38.self_attn.k_proj",
	"model.layers.38.self_attn.v_proj",
	"model.layers.38.self_attn.o_proj",
	"model.layers.38.mlp.gate",
	"model.layers.39.self_attn.q_proj",
	"model.layers.39.self_attn.k_proj",
	"model.layers.39.self_attn.v_proj",
	"model.layers.39.self_attn.o_proj",
	"model.layers.39.mlp.gate",
	"model.layers.40.self_attn.q_proj",
	"model.layers.40.self_attn.k_proj",
	"model.layers.40.self_attn.v_proj",
	"model.layers.40.self_attn.o_proj",
	"model.layers.40.mlp.gate",
	"model.layers.41.self_attn.q_proj",
	"model.layers.41.self_attn.k_proj",
	"model.layers.41.self_attn.v_proj",
	"model.layers.41.self_attn.o_proj",
	"model.layers.41.mlp.gate",
	"model.layers.42.self_attn.q_proj",
	"model.layers.42.self_attn.k_proj",
	"model.layers.42.self_attn.v_proj",
	"model.layers.42.self_attn.o_proj",
	"model.layers.42.mlp.gate",
	"model.layers.43.self_attn.q_proj",
	"model.layers.43.self_attn.k_proj",
	"model.layers.43.self_attn.v_proj",
	"model.layers.43.self_attn.o_proj",
	"model.layers.43.mlp.gate",
	"model.layers.44.self_attn.q_proj",
	"model.layers.44.self_attn.k_proj",
	"model.layers.44.self_attn.v_proj",
	"model.layers.44.self_attn.o_proj",
	"model.layers.44.mlp.gate",
	"model.layers.45.self_attn.q_proj",
	"model.layers.45.self_attn.k_proj",
	"model.layers.45.self_attn.v_proj",
	"model.layers.45.self_attn.o_proj",
	"model.layers.45.mlp.gate",
	"model.layers.46.self_attn.q_proj",
	"model.layers.46.self_attn.k_proj",
	"model.layers.46.self_attn.v_proj",
	"model.layers.46.self_attn.o_proj",
	"model.layers.46.mlp.gate",
	"model.layers.47.self_attn.q_proj",
	"model.layers.47.self_attn.k_proj",
	"model.layers.47.self_attn.v_proj",
	"model.layers.47.self_attn.o_proj",
	"model.layers.47.mlp.gate",
	"model.layers.48.self_attn.q_proj",
	"model.layers.48.self_attn.k_proj",
	"model.layers.48.self_attn.v_proj",
	"model.layers.48.self_attn.o_proj",
	"model.layers.48.mlp.gate",
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.15.1.dev6+g077e752"
	}
	}