Instructions to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit with Transformers:

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

pipe = pipeline("text-generation", model="ncls-p/AI21-Jamba2-Mini-mlx-4Bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ncls-p/AI21-Jamba2-Mini-mlx-4Bit")
model = AutoModelForMultimodalLM.from_pretrained("ncls-p/AI21-Jamba2-Mini-mlx-4Bit")
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]:]))

MLX

How to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit 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("ncls-p/AI21-Jamba2-Mini-mlx-4Bit")

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

vLLM

How to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ncls-p/AI21-Jamba2-Mini-mlx-4Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ncls-p/AI21-Jamba2-Mini-mlx-4Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ncls-p/AI21-Jamba2-Mini-mlx-4Bit

SGLang

How to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit 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 "ncls-p/AI21-Jamba2-Mini-mlx-4Bit" \
    --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": "ncls-p/AI21-Jamba2-Mini-mlx-4Bit",
		"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 "ncls-p/AI21-Jamba2-Mini-mlx-4Bit" \
        --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": "ncls-p/AI21-Jamba2-Mini-mlx-4Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ncls-p/AI21-Jamba2-Mini-mlx-4Bit"

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": "ncls-p/AI21-Jamba2-Mini-mlx-4Bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit 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 "ncls-p/AI21-Jamba2-Mini-mlx-4Bit"

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 ncls-p/AI21-Jamba2-Mini-mlx-4Bit

Run Hermes

hermes

MLX LM

How to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "ncls-p/AI21-Jamba2-Mini-mlx-4Bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "ncls-p/AI21-Jamba2-Mini-mlx-4Bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "ncls-p/AI21-Jamba2-Mini-mlx-4Bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use ncls-p/AI21-Jamba2-Mini-mlx-4Bit with Docker Model Runner:
```
docker model run hf.co/ncls-p/AI21-Jamba2-Mini-mlx-4Bit
```

ncls-p commited on Jan 8

Commit

54ee1fb

verified ·

1 Parent(s): d2a4c82

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +179 -0

config.json ADDED Viewed

	@@ -0,0 +1,179 @@

+{
+    "architectures": [
+        "JambaForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "attn_layer_offset": 4,
+    "attn_layer_period": 8,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 519,
+    "expert_layer_offset": 1,
+    "expert_layer_period": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "mamba_conv_bias": true,
+    "mamba_d_conv": 4,
+    "mamba_d_state": 16,
+    "mamba_dt_rank": 256,
+    "mamba_expand": 2,
+    "mamba_proj_bias": false,
+    "max_position_embeddings": 262144,
+    "model_type": "jamba",
+    "num_attention_heads": 32,
+    "num_experts": 16,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_logits_to_keep": 1,
+    "output_router_logits": false,
+    "pad_token_id": 0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "model.layers.1.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "model.layers.1.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.feed_forward.router": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "rms_norm_eps": 1e-06,
+    "router_aux_loss_coef": 0.001,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.56.1",
+    "use_cache": true,
+    "use_mamba_kernels": true,
+    "vocab_size": 65536
+}