Instructions to use hmellor/tiny-random-BambaForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hmellor/tiny-random-BambaForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="hmellor/tiny-random-BambaForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hmellor/tiny-random-BambaForCausalLM")
model = AutoModelForCausalLM.from_pretrained("hmellor/tiny-random-BambaForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hmellor/tiny-random-BambaForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hmellor/tiny-random-BambaForCausalLM

SGLang

How to use hmellor/tiny-random-BambaForCausalLM 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 "hmellor/tiny-random-BambaForCausalLM" \
    --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": "hmellor/tiny-random-BambaForCausalLM",
		"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 "hmellor/tiny-random-BambaForCausalLM" \
        --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": "hmellor/tiny-random-BambaForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hmellor/tiny-random-BambaForCausalLM with Docker Model Runner:
```
docker model run hf.co/hmellor/tiny-random-BambaForCausalLM
```

hmellor HF Staff commited on Apr 29, 2025

Commit

cff7661

1 Parent(s): d85c3c0

Upload BambaForCausalLM

Browse files

Files changed (2) hide show

config.json +2 -2
model.safetensors +3 -0

config.json CHANGED Viewed

@@ -17,7 +17,7 @@
   "mamba_chunk_size": 256,
   "mamba_conv_bias": true,
   "mamba_d_conv": 4,
-  "mamba_d_head": 8,
   "mamba_d_state": 8,
   "mamba_dt_rank": 256,
   "mamba_expand": 4,
@@ -37,7 +37,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "use_cache": true,
   "use_mamba_kernels": true,

   "mamba_chunk_size": 256,
   "mamba_conv_bias": true,
   "mamba_d_conv": 4,
+  "mamba_d_head": 32,
   "mamba_d_state": 8,
   "mamba_dt_rank": 256,
   "mamba_expand": 4,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
   "use_cache": true,
   "use_mamba_kernels": true,

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f050db2d01ca759c9b99b314eaaae34ed41945b205efb1a2f66f488d83b7f617
+size 32990648