Instructions to use moos124/coolest-bamba-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moos124/coolest-bamba-v1 with Transformers:

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

pipe = pipeline("text-generation", model="moos124/coolest-bamba-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("moos124/coolest-bamba-v1")
model = AutoModelForCausalLM.from_pretrained("moos124/coolest-bamba-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moos124/coolest-bamba-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moos124/coolest-bamba-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moos124/coolest-bamba-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/moos124/coolest-bamba-v1

SGLang

How to use moos124/coolest-bamba-v1 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 "moos124/coolest-bamba-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moos124/coolest-bamba-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "moos124/coolest-bamba-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moos124/coolest-bamba-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use moos124/coolest-bamba-v1 with Docker Model Runner:
```
docker model run hf.co/moos124/coolest-bamba-v1
```

coolest-bamba-v1 / config.json

moos124

Training in progress, step 500

59d33ac verified about 1 month ago

Raw

History Blame Contribute Delete

907 Bytes

	{
	"architectures": [
	"Mamba2ForCausalLM"
	],
	"bos_token_id": 0,
	"chunk_size": 256,
	"conv_kernel": 4,
	"dtype": "float32",
	"eos_token_id": 2,
	"expand": 2,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 256,
	"initializer_range": 0.1,
	"intermediate_size": 256,
	"layer_norm_epsilon": 1e-05,
	"model_type": "mamba2",
	"n_groups": 8,
	"num_heads": 8,
	"num_hidden_layers": 24,
	"num_key_value_heads": 4,
	"pad_token_id": 1,
	"rescale_prenorm_residual": false,
	"residual_in_fp32": true,
	"rms_norm": true,
	"state_size": 128,
	"tie_word_embeddings": true,
	"time_step_floor": 0.0001,
	"time_step_limit": [
	0.0,
	{
	"__float__": "Infinity"
	}
	],
	"time_step_max": 0.1,
	"time_step_min": 0.001,
	"time_step_rank": 16,
	"transformers_version": "5.13.0",
	"use_bias": false,
	"use_cache": false,
	"use_conv_bias": true,
	"vocab_size": 50257
	}