Instructions to use DreamFoundries/Laguna-S-2.1-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreamFoundries/Laguna-S-2.1-6bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("DreamFoundries/Laguna-S-2.1-6bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use DreamFoundries/Laguna-S-2.1-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DreamFoundries/Laguna-S-2.1-6bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DreamFoundries/Laguna-S-2.1-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use DreamFoundries/Laguna-S-2.1-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "DreamFoundries/Laguna-S-2.1-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "DreamFoundries/Laguna-S-2.1-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "DreamFoundries/Laguna-S-2.1-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use DreamFoundries/Laguna-S-2.1-6bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DreamFoundries/Laguna-S-2.1-6bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default DreamFoundries/Laguna-S-2.1-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DreamFoundries/Laguna-S-2.1-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DreamFoundries/Laguna-S-2.1-6bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "DreamFoundries/Laguna-S-2.1-6bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Laguna-S-2.1-6bit / config.json

DreamFoundries

Upload MLX metadata

8f1ee35 verified about 2 months ago

Raw

History Blame Contribute Delete

5.81 kB

	{
	"architectures": [
	"LagunaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_laguna.LagunaConfig",
	"AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM"
	},
	"bos_token_id": 2,
	"decoder_sparse_step": 1,
	"eos_token_id": [
	2,
	24
	],
	"gating": "per-head",
	"gating_types": [
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head"
	],
	"head_dim": 128,
	"hidden_size": 3072,
	"intermediate_size": 12288,
	"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"
	],
	"max_position_embeddings": 1048576,
	"mlp_layer_types": [
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"mlp_only_layers": [
	0
	],
	"model_type": "laguna",
	"moe_apply_router_weight_on_input": false,
	"moe_intermediate_size": 1024,
	"moe_routed_scaling_factor": 2.5,
	"moe_router_logit_softcapping": 0.0,
	"norm_topk_prob": true,
	"num_attention_heads": 48,
	"num_attention_heads_per_layer": [
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72
	],
	"num_experts": 256,
	"num_experts_per_tok": 10,
	"num_hidden_layers": 48,
	"num_key_value_heads": 8,
	"pad_token_id": 9,
	"quantization": {
	"group_size": 64,
	"bits": 6,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 6,
	"mode": "affine"
	},
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"full_attention": {
	"rope_theta": 500000.0,
	"rope_type": "yarn",
	"factor": 128.0,
	"original_max_position_embeddings": 8192,
	"beta_slow": 1.0,
	"beta_fast": 32.0,
	"attention_factor": 1.4852030263919618,
	"partial_rotary_factor": 0.5
	},
	"sliding_attention": {
	"rope_type": "default",
	"rope_theta": 10000.0,
	"partial_rotary_factor": 1.0
	}
	},
	"router_aux_loss_coef": 0.0,
	"shared_expert_intermediate_size": 1024,
	"sliding_window": 512,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"vocab_size": 100352
	}