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

Libraries

How to use yujiepan/jamba-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/jamba-tiny-random", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/jamba-tiny-random", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("yujiepan/jamba-tiny-random", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yujiepan/jamba-tiny-random with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yujiepan/jamba-tiny-random

SGLang

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

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

yujiepan commited on Mar 30, 2024

Commit

b4cf276

verified ·

1 Parent(s): 0879af7

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

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

config.json CHANGED Viewed

@@ -24,7 +24,7 @@
   "mamba_conv_bias": true,
   "mamba_d_conv": 4,
   "mamba_d_state": 16,
-  "mamba_dt_rank": 16,
   "mamba_expand": 2,
   "mamba_inner_layernorms": true,
   "mamba_proj_bias": false,
@@ -33,7 +33,7 @@
   "num_attention_heads": 4,
   "num_experts": 16,
   "num_experts_per_tok": 2,
-  "num_hidden_layers": 8,
   "num_key_value_heads": 2,
   "output_router_logits": false,
   "pad_token_id": 0,

   "mamba_conv_bias": true,
   "mamba_d_conv": 4,
   "mamba_d_state": 16,
+  "mamba_dt_rank": 256,
   "mamba_expand": 2,
   "mamba_inner_layernorms": true,
   "mamba_proj_bias": false,
   "num_attention_heads": 4,
   "num_experts": 16,
   "num_experts_per_tok": 2,
+  "num_hidden_layers": 16,
   "num_key_value_heads": 2,
   "output_router_logits": false,
   "pad_token_id": 0,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b4e57ac4ceec101688588be8355951597e7aacbe04c8e32b42078fb9143ef7
-size 1104560

 version https://git-lfs.github.com/spec/v1
+oid sha256:b6ab01c6269c51bc084de15f4b817241cfa38699b5775f4f290889e9ac8f6ef9
+size 1274744