Instructions to use pankajmathur/Lima_Unchained_70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/Lima_Unchained_70b with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/Lima_Unchained_70b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/Lima_Unchained_70b")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/Lima_Unchained_70b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pankajmathur/Lima_Unchained_70b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajmathur/Lima_Unchained_70b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajmathur/Lima_Unchained_70b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pankajmathur/Lima_Unchained_70b

SGLang

How to use pankajmathur/Lima_Unchained_70b 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 "pankajmathur/Lima_Unchained_70b" \
    --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": "pankajmathur/Lima_Unchained_70b",
		"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 "pankajmathur/Lima_Unchained_70b" \
        --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": "pankajmathur/Lima_Unchained_70b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pankajmathur/Lima_Unchained_70b with Docker Model Runner:
```
docker model run hf.co/pankajmathur/Lima_Unchained_70b
```

psmathur commited on Aug 21, 2023

Commit

f64f7df

1 Parent(s): f996410

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -2

README.md CHANGED Viewed

@@ -8,9 +8,9 @@ datasets:
 # model_42_70b
-An Llama2-70b model fine-tuned exclusively on carefully selected ~900 conversations from the [Lima](https://arxiv.org/pdf/2305.11206.pdf) datasets.
-**I am actively seeking sponsorship and partnership opportunities. If you're interested, please connect with me at www.linkedin.com/in/pankajam.**
 ## Evaluation
@@ -28,6 +28,8 @@ Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](htt
 |**Total Average**|-|**0.6867**||
 ## Example Usage
 Here is the prompt format
@@ -66,6 +68,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 #### Limitations & Biases:
@@ -76,6 +79,7 @@ Despite diligent efforts in refining the pretraining data, there remains a possi
 Exercise caution and cross-check information when necessary.
 ### Citiation:

 # model_42_70b
+A Llama2-70b model fine-tuned using QLora on all the linear layers with carefully selected ~900 conversations from the [Lima](https://arxiv.org/pdf/2305.11206.pdf)
+<br>
 ## Evaluation
 |**Total Average**|-|**0.6867**||
+<br>
 ## Example Usage
 Here is the prompt format
 ```
+<br>
 #### Limitations & Biases:
 Exercise caution and cross-check information when necessary.
+<br>
 ### Citiation: