Instructions to use the-fall-of-man/didact-20b-march-hare-mxfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use the-fall-of-man/didact-20b-march-hare-mxfp4 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("the-fall-of-man/didact-20b-march-hare-mxfp4")

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 the-fall-of-man/didact-20b-march-hare-mxfp4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "the-fall-of-man/didact-20b-march-hare-mxfp4"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "the-fall-of-man/didact-20b-march-hare-mxfp4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use the-fall-of-man/didact-20b-march-hare-mxfp4 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 "the-fall-of-man/didact-20b-march-hare-mxfp4"

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 the-fall-of-man/didact-20b-march-hare-mxfp4

Run Hermes

hermes

MLX LM

How to use the-fall-of-man/didact-20b-march-hare-mxfp4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "the-fall-of-man/didact-20b-march-hare-mxfp4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "the-fall-of-man/didact-20b-march-hare-mxfp4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "the-fall-of-man/didact-20b-march-hare-mxfp4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

didact-20b-march-hare-mxfp4 / config.json

the-fall-of-man

Add files using upload-large-folder tool

aa621cd verified 4 months ago

Raw

History Blame Contribute Delete

6.98 kB

	{
	"architectures": [
	"GptOssForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"eos_token_id": [
	200002,
	199999
	],
	"experts_per_token": 4,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 2880,
	"initial_context_length": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 2880,
	"layer_types": [
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 131072,
	"model_type": "gpt_oss",
	"num_attention_heads": 64,
	"num_experts_per_tok": 4,
	"num_hidden_layers": 24,
	"num_key_value_heads": 8,
	"num_local_experts": 32,
	"output_router_logits": false,
	"pad_token_id": 199999,
	"quantization": {
	"group_size": 32,
	"bits": 4,
	"mode": "mxfp4",
	"model.layers.0.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.1.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.2.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.3.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.4.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.5.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.6.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.7.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.8.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.9.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.10.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.11.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.12.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.13.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.14.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.15.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.16.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.17.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.18.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.19.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.20.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.21.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.22.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.23.mlp.router": {
	"group_size": 64,
	"bits": 8
	}
	},
	"quantization_config": {
	"group_size": 32,
	"bits": 4,
	"mode": "mxfp4",
	"model.layers.0.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.1.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.2.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.3.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.4.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.5.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.6.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.7.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.8.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.9.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.10.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.11.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.12.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.13.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.14.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.15.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.16.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.17.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.18.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.19.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.20.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.21.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.22.mlp.router": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.23.mlp.router": {
	"group_size": 64,
	"bits": 8
	}
	},
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"beta_fast": 32.0,
	"beta_slow": 1.0,
	"factor": 32.0,
	"original_max_position_embeddings": 4096,
	"rope_type": "yarn",
	"truncate": false
	},
	"rope_theta": 150000,
	"router_aux_loss_coef": 0.9,
	"sliding_window": 128,
	"swiglu_limit": 7.0,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.56.0.dev0",
	"use_cache": true,
	"vocab_size": 201088
	}