Instructions to use rustformers/bloom-ggml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rustformers/bloom-ggml with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rustformers/bloom-ggml")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rustformers/bloom-ggml", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use rustformers/bloom-ggml with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rustformers/bloom-ggml" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rustformers/bloom-ggml", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rustformers/bloom-ggml
- SGLang
How to use rustformers/bloom-ggml 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 "rustformers/bloom-ggml" \ --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": "rustformers/bloom-ggml", "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 "rustformers/bloom-ggml" \ --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": "rustformers/bloom-ggml", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rustformers/bloom-ggml with Docker Model Runner:
docker model run hf.co/rustformers/bloom-ggml
Generated README.md
Browse files
README.md
CHANGED
|
@@ -67,7 +67,7 @@ tags:
|
|
| 67 |
pipeline_tag: text-generation
|
| 68 |
---
|
| 69 |
|
| 70 |
-
# GGML
|
| 71 |
|
| 72 |
## Description
|
| 73 |
|
|
@@ -80,18 +80,22 @@ BLOOM is an autoregressive Large Language Model (LLM), trained to continue text
|
|
| 80 |
| [bloom-1b1-f16.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-f16.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | F16 | GGML | V3 |
|
| 81 |
| [bloom-1b1-q4_0.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-q4_0.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | Q4_0 | GGML | V3 |
|
| 82 |
| [bloom-1b1-q4_0-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-q4_0-ggjt.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | Q4_0 | GGJT | V3 |
|
|
|
|
| 83 |
| [bloom-1b1-q5_1-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-q5_1-ggjt.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | Q5_1 | GGJT | V3 |
|
| 84 |
| [bloom-1b7-f16.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-f16.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | F16 | GGML | V3 |
|
| 85 |
| [bloom-1b7-q4_0.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-q4_0.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | Q4_0 | GGML | V3 |
|
| 86 |
| [bloom-1b7-q4_0-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-q4_0-ggjt.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | Q4_0 | GGJT | V3 |
|
|
|
|
| 87 |
| [bloom-1b7-q5_1-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-q5_1-ggjt.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | Q5_1 | GGJT | V3 |
|
| 88 |
| [bloom-3b-f16.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-f16.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | F16 | GGML | V3 |
|
| 89 |
| [bloom-3b-q4_0.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-q4_0.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | Q4_0 | GGML | V3 |
|
| 90 |
| [bloom-3b-q4_0-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-q4_0-ggjt.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | Q4_0 | GGJT | V3 |
|
|
|
|
| 91 |
| [bloom-3b-q5_1-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-q5_1-ggjt.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | Q5_1 | GGJT | V3 |
|
| 92 |
| [bloom-560m-f16.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-f16.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | F16 | GGML | V3 |
|
| 93 |
| [bloom-560m-q4_0.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-q4_0.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | Q4_0 | GGML | V3 |
|
| 94 |
| [bloom-560m-q4_0-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-q4_0-ggjt.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | Q4_0 | GGJT | V3 |
|
|
|
|
| 95 |
| [bloom-560m-q5_1-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-q5_1-ggjt.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | Q5_1 | GGJT | V3 |
|
| 96 |
|
| 97 |
## Usage
|
|
|
|
| 67 |
pipeline_tag: text-generation
|
| 68 |
---
|
| 69 |
|
| 70 |
+
# GGML converted versions of [BigScience](https://huggingface.co/bigscience)'s Bloom models
|
| 71 |
|
| 72 |
## Description
|
| 73 |
|
|
|
|
| 80 |
| [bloom-1b1-f16.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-f16.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | F16 | GGML | V3 |
|
| 81 |
| [bloom-1b1-q4_0.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-q4_0.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | Q4_0 | GGML | V3 |
|
| 82 |
| [bloom-1b1-q4_0-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-q4_0-ggjt.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | Q4_0 | GGJT | V3 |
|
| 83 |
+
| [bloom-1b1-q5_1.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-q5_1.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | Q5_1 | GGML | V3 |
|
| 84 |
| [bloom-1b1-q5_1-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b1-q5_1-ggjt.bin) | [bigscience/bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) | Q5_1 | GGJT | V3 |
|
| 85 |
| [bloom-1b7-f16.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-f16.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | F16 | GGML | V3 |
|
| 86 |
| [bloom-1b7-q4_0.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-q4_0.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | Q4_0 | GGML | V3 |
|
| 87 |
| [bloom-1b7-q4_0-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-q4_0-ggjt.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | Q4_0 | GGJT | V3 |
|
| 88 |
+
| [bloom-1b7-q5_1.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-q5_1.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | Q5_1 | GGML | V3 |
|
| 89 |
| [bloom-1b7-q5_1-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-1b7-q5_1-ggjt.bin) | [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) | Q5_1 | GGJT | V3 |
|
| 90 |
| [bloom-3b-f16.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-f16.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | F16 | GGML | V3 |
|
| 91 |
| [bloom-3b-q4_0.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-q4_0.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | Q4_0 | GGML | V3 |
|
| 92 |
| [bloom-3b-q4_0-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-q4_0-ggjt.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | Q4_0 | GGJT | V3 |
|
| 93 |
+
| [bloom-3b-q5_1.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-q5_1.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | Q5_1 | GGML | V3 |
|
| 94 |
| [bloom-3b-q5_1-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-3b-q5_1-ggjt.bin) | [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) | Q5_1 | GGJT | V3 |
|
| 95 |
| [bloom-560m-f16.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-f16.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | F16 | GGML | V3 |
|
| 96 |
| [bloom-560m-q4_0.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-q4_0.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | Q4_0 | GGML | V3 |
|
| 97 |
| [bloom-560m-q4_0-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-q4_0-ggjt.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | Q4_0 | GGJT | V3 |
|
| 98 |
+
| [bloom-560m-q5_1.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-q5_1.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | Q5_1 | GGML | V3 |
|
| 99 |
| [bloom-560m-q5_1-ggjt.bin](https://huggingface.co/rustformers/bloom-ggml/blob/main/bloom-560m-q5_1-ggjt.bin) | [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) | Q5_1 | GGJT | V3 |
|
| 100 |
|
| 101 |
## Usage
|