Instructions to use yam-peleg/Experiment26-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yam-peleg/Experiment26-7B with Transformers:

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

pipe = pipeline("text-generation", model="yam-peleg/Experiment26-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Experiment26-7B")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Experiment26-7B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yam-peleg/Experiment26-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yam-peleg/Experiment26-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yam-peleg/Experiment26-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yam-peleg/Experiment26-7B

SGLang

How to use yam-peleg/Experiment26-7B 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 "yam-peleg/Experiment26-7B" \
    --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": "yam-peleg/Experiment26-7B",
		"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 "yam-peleg/Experiment26-7B" \
        --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": "yam-peleg/Experiment26-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yam-peleg/Experiment26-7B with Docker Model Runner:
```
docker model run hf.co/yam-peleg/Experiment26-7B
```

ollama version

by eramax - opened Mar 1, 2024

Discussion

eramax

Mar 1, 2024

ollama run eramax/yam-peleg-exp26-7b:Q5_K_M

eramax

Mar 1, 2024

It adds INSTANT everywhere , does it chat template issue.

My chat template

MaziyarPanahi

Mar 2, 2024

I tested mine (Q2) and I don't see that issue:

llama.cpp/main -m Experiment26-7B.Q2_K.gguf -p "please repeat back: apple, orange, juice" -n 400 -e

please repeat back: apple, orange, juice

I'm sorry, but it's more of a paraphrasing or rephrasing exercise I need help with. The given sentence or phrase is "apple, orange, juice". Now I want to make something like a new statement using the same words, while retaining its core meaning, albeit in a different way.

One possibility could be: "Fruits commonly chosen for juicing include apples and oranges." Here, we've kept the individual words 'apple,' 'orange,' and 'juice' (through the context of the verb 'including') to maintain the essence, while presenting a fresh, grammatically coherent structure. [end of text]

https://huggingface.co/MaziyarPanahi/Experiment26-7B-GGUF

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment