Instructions to use mlx-community/JoyAI-LLM-Flash-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/JoyAI-LLM-Flash-5bit 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("mlx-community/JoyAI-LLM-Flash-5bit")

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
LM Studio

Pi new

How to use mlx-community/JoyAI-LLM-Flash-5bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/JoyAI-LLM-Flash-5bit"

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": "mlx-community/JoyAI-LLM-Flash-5bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/JoyAI-LLM-Flash-5bit 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 "mlx-community/JoyAI-LLM-Flash-5bit"

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 mlx-community/JoyAI-LLM-Flash-5bit

Run Hermes

hermes

MLX LM

How to use mlx-community/JoyAI-LLM-Flash-5bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/JoyAI-LLM-Flash-5bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/JoyAI-LLM-Flash-5bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/JoyAI-LLM-Flash-5bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

JoyAI-LLM-Flash-5bit / config.json

ivanfioravanti

Add files using upload-large-folder tool

6ee8f0b verified 3 months ago

raw

history blame contribute delete

1.61 kB

	{
	"architectures": [
	"DeepseekV3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_deepseek.DeepseekV3Config",
	"AutoModel": "modeling_deepseek.DeepseekV3Model",
	"AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
	},
	"bos_token_id": 0,
	"eos_token_id": 1,
	"ep_size": 1,
	"first_k_dense_replace": 1,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 7168,
	"kv_lora_rank": 512,
	"max_position_embeddings": 131072,
	"model_type": "joyai_llm_flash",
	"moe_intermediate_size": 768,
	"moe_layer_freq": 1,
	"n_group": 1,
	"n_routed_experts": 256,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 32,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 40,
	"num_key_value_heads": 32,
	"num_nextn_predict_layers": 1,
	"q_lora_rank": 1536,
	"qk_nope_head_dim": 128,
	"qk_rope_head_dim": 64,
	"quantization": {
	"group_size": 64,
	"bits": 5,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 5,
	"mode": "affine"
	},
	"rms_norm_eps": 1e-06,
	"rope_theta": 32000000,
	"routed_scaling_factor": 2.5,
	"scoring_func": "sigmoid",
	"tie_word_embeddings": false,
	"topk_group": 1,
	"topk_method": "noaux_tc",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.44.2",
	"use_cache": true,
	"v_head_dim": 128,
	"vocab_size": 129280
	}