Instructions to use royleibov/Jamba-v0.1-ZipNN-Compressed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use royleibov/Jamba-v0.1-ZipNN-Compressed with Transformers:

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

pipe = pipeline("text-generation", model="royleibov/Jamba-v0.1-ZipNN-Compressed", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use royleibov/Jamba-v0.1-ZipNN-Compressed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "royleibov/Jamba-v0.1-ZipNN-Compressed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "royleibov/Jamba-v0.1-ZipNN-Compressed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/royleibov/Jamba-v0.1-ZipNN-Compressed

SGLang

How to use royleibov/Jamba-v0.1-ZipNN-Compressed 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 "royleibov/Jamba-v0.1-ZipNN-Compressed" \
    --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": "royleibov/Jamba-v0.1-ZipNN-Compressed",
		"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 "royleibov/Jamba-v0.1-ZipNN-Compressed" \
        --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": "royleibov/Jamba-v0.1-ZipNN-Compressed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use royleibov/Jamba-v0.1-ZipNN-Compressed with Docker Model Runner:
```
docker model run hf.co/royleibov/Jamba-v0.1-ZipNN-Compressed
```

royleibov commited on Sep 15, 2024

Commit

cd0f0e0

verified ·

1 Parent(s): ec5620e

Fix zipnn patch

Browse files

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -20,9 +20,9 @@ pip install zipnn
 Then simply add at the beginning of the file
 ```python
-from zipnn import zipnn_hf_patch
-zipnn_hf_patch()
 ```
 And continue as usual. The patch will take care of decompressing the model correctly and safely.
@@ -64,9 +64,9 @@ You can run the model not using the optimized Mamba kernels, but it is **not** r
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from zipnn import zipnn_hf_patch
-zipnn_hf_patch()
 model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed")
 tokenizer = AutoTokenizer.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed")
@@ -89,9 +89,9 @@ Please note that if you're using `transformers<4.40.0`, `trust_remote_code=True`
 ```python
 from transformers import AutoModelForCausalLM
 import torch
-from zipnn import zipnn_hf_patch
-zipnn_hf_patch()
 model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed",
                                              torch_dtype=torch.bfloat16)    # you can also use torch_dtype=torch.float16
@@ -100,9 +100,9 @@ model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compres
 When using half precision, you can enable the [FlashAttention2](https://github.com/Dao-AILab/flash-attention) implementation of the Attention blocks. In order to use it, you also need the model on a CUDA device. Since in this precision the model is to big to fit on a single 80GB GPU, you'll also need to parallelize it using [accelerate](https://huggingface.co/docs/accelerate/index):
 ```python
 from transformers import AutoModelForCausalLM
-from zipnn import zipnn_hf_patch
-zipnn_hf_patch()
 import torch
 model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed",
@@ -118,9 +118,9 @@ model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compres
 ```python
 from transformers import AutoModelForCausalLM, BitsAndBytesConfig
-from zipnn import zipnn_hf_patch
-zipnn_hf_patch()
 quantization_config = BitsAndBytesConfig(load_in_8bit=True,
                                          llm_int8_skip_modules=["mamba"])
@@ -140,9 +140,9 @@ from datasets import load_dataset
 from trl import SFTTrainer, SFTConfig
 from peft import LoraConfig
 from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments
-from zipnn import zipnn_hf_patch
-zipnn_hf_patch()
 tokenizer = AutoTokenizer.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed")
 model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed",

 Then simply add at the beginning of the file
 ```python
+from zipnn import zipnn_hf
+zipnn_hf()
 ```
 And continue as usual. The patch will take care of decompressing the model correctly and safely.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from zipnn import zipnn_hf
+zipnn_hf()
 model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed")
 tokenizer = AutoTokenizer.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed")
 ```python
 from transformers import AutoModelForCausalLM
 import torch
+from zipnn import zipnn_hf
+zipnn_hf()
 model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed",
                                              torch_dtype=torch.bfloat16)    # you can also use torch_dtype=torch.float16
 When using half precision, you can enable the [FlashAttention2](https://github.com/Dao-AILab/flash-attention) implementation of the Attention blocks. In order to use it, you also need the model on a CUDA device. Since in this precision the model is to big to fit on a single 80GB GPU, you'll also need to parallelize it using [accelerate](https://huggingface.co/docs/accelerate/index):
 ```python
 from transformers import AutoModelForCausalLM
+from zipnn import zipnn_hf
+zipnn_hf()
 import torch
 model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed",
 ```python
 from transformers import AutoModelForCausalLM, BitsAndBytesConfig
+from zipnn import zipnn_hf
+zipnn_hf()
 quantization_config = BitsAndBytesConfig(load_in_8bit=True,
                                          llm_int8_skip_modules=["mamba"])
 from trl import SFTTrainer, SFTConfig
 from peft import LoraConfig
 from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments
+from zipnn import zipnn_hf
+zipnn_hf()
 tokenizer = AutoTokenizer.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed")
 model = AutoModelForCausalLM.from_pretrained("royleibov/Jamba-v0.1-ZipNN-Compressed",