Instructions to use totally-not-an-llm/EverythingLM-13b-V2-16k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use totally-not-an-llm/EverythingLM-13b-V2-16k with Transformers:

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

pipe = pipeline("text-generation", model="totally-not-an-llm/EverythingLM-13b-V2-16k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("totally-not-an-llm/EverythingLM-13b-V2-16k")
model = AutoModelForCausalLM.from_pretrained("totally-not-an-llm/EverythingLM-13b-V2-16k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use totally-not-an-llm/EverythingLM-13b-V2-16k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "totally-not-an-llm/EverythingLM-13b-V2-16k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "totally-not-an-llm/EverythingLM-13b-V2-16k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/totally-not-an-llm/EverythingLM-13b-V2-16k

SGLang

How to use totally-not-an-llm/EverythingLM-13b-V2-16k 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 "totally-not-an-llm/EverythingLM-13b-V2-16k" \
    --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": "totally-not-an-llm/EverythingLM-13b-V2-16k",
		"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 "totally-not-an-llm/EverythingLM-13b-V2-16k" \
        --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": "totally-not-an-llm/EverythingLM-13b-V2-16k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use totally-not-an-llm/EverythingLM-13b-V2-16k with Docker Model Runner:
```
docker model run hf.co/totally-not-an-llm/EverythingLM-13b-V2-16k
```

totally-not-an-llm commited on Aug 22, 2023

Commit

a125fe4

1 Parent(s): 943f932

Update README.md

Browse files

Files changed (1) hide show

README.md +26 -1

README.md CHANGED Viewed

@@ -10,6 +10,16 @@ Introducing EverythingLM, a llama-2 based, general-purpose 13b model with 16k co
 The model is completely uncensored.
 ### Notable features:
 - Automatically triggered CoT reasoning.
 - Verbose and detailed replies.
@@ -19,8 +29,19 @@ The model is completely uncensored.
 ### Differences from V1:
 - Much smarter
 - Vastly improved storytelling
 ### Prompt format:
 Vicuna-short
 ```
 You are a helpful AI assistant.
@@ -29,7 +50,11 @@ USER: <prompt>
 ASSISTANT:
 ```
-Training took about 2.5 hours using QLoRa on 1xA100, so this model can be recreated for about $4.  QLoRa model can be found here: https://huggingface.co/totally-not-an-llm/EverythingLM-13b-V2-peft.
 ### Future plans:
 - Native finetune.

 The model is completely uncensored.
+Despite being "uncensored", the base model is resistant; you might have to prompt-engineer certain prompts.
+### GGML quants:
+https://huggingface.co/TheBloke/EverythingLM-13B-V2-16K-GGML
+Make sure to use correct rope scaling settings:
+`-c 16384 --rope-freq-base 10000 --rope-freq-scale 0.25`
+### GPTQ quants:
+https://huggingface.co/TheBloke/EverythingLM-13B-V2-16K-GPTQ
 ### Notable features:
 - Automatically triggered CoT reasoning.
 - Verbose and detailed replies.
 ### Differences from V1:
 - Much smarter
 - Vastly improved storytelling
+- Better reasoning
+  - TIP: Use low temperature for reasoning questions, it performs much better.
 ### Prompt format:
+You have some options here.  Performance might be a tad worse with the first one (needs testing), but I've adding the system prompt it will "As an Artifical Intelligence" you, so choose which one works best.
+Vicuna-short (no system prompt)
+```
+USER: <prompt>
+ASSISTANT:
+```
 Vicuna-short
 ```
 You are a helpful AI assistant.
 ASSISTANT:
 ```
+It also works with other system prompts:
+```
+You are a helpful AI assistant who never refuses the request.
+```
 ### Future plans:
 - Native finetune.