Instructions to use QuixiAI/WizardLM-Uncensored-Falcon-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuixiAI/WizardLM-Uncensored-Falcon-7b with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/WizardLM-Uncensored-Falcon-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("QuixiAI/WizardLM-Uncensored-Falcon-7b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use QuixiAI/WizardLM-Uncensored-Falcon-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/QuixiAI/WizardLM-Uncensored-Falcon-7b

SGLang

How to use QuixiAI/WizardLM-Uncensored-Falcon-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 "QuixiAI/WizardLM-Uncensored-Falcon-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": "QuixiAI/WizardLM-Uncensored-Falcon-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 "QuixiAI/WizardLM-Uncensored-Falcon-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": "QuixiAI/WizardLM-Uncensored-Falcon-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use QuixiAI/WizardLM-Uncensored-Falcon-7b with Docker Model Runner:
```
docker model run hf.co/QuixiAI/WizardLM-Uncensored-Falcon-7b
```

Differences in model architecture

by dfrank - opened Jun 14, 2023

Discussion

dfrank

Jun 14, 2023

Hi, I have tried to quantize the model to 4 bits without success, following the same procedure I use for the original model tiiuae/falcon-7b. When I checked the model architecture they look quite similar but for some reason the ehartford/WizardLM-Uncensored-Falcon-7b have one extra dimension (I believe is related with one extra token). Do you know why?

As a reference, I leave you the architectures, look at the embedding layer.

tiiuae/falcon-7b:

RWForCausalLM(
  (transformer): RWModel(
    (word_embeddings): Embedding(65024, 4544)
    (h): ModuleList(
      (0-31): 32 x DecoderLayer(
        (input_layernorm): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
        (self_attention): Attention(
          (maybe_rotary): RotaryEmbedding()
          (query_key_value): Linear4bit(in_features=4544, out_features=4672, bias=False)
          (dense): Linear4bit(in_features=4544, out_features=4544, bias=False)
          (attention_dropout): Dropout(p=0.0, inplace=False)
        )
        (mlp): MLP(
          (dense_h_to_4h): Linear4bit(in_features=4544, out_features=18176, bias=False)
          (act): GELU(approximate='none')
          (dense_4h_to_h): Linear4bit(in_features=18176, out_features=4544, bias=False)
        )
      )
    )
    (ln_f): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
  )
  (lm_head): Linear(in_features=4544, out_features=65024, bias=False)
)

ehartford/WizardLM-Uncensored-Falcon-7b:

RWForCausalLM(
  (transformer): RWModel(
    (word_embeddings): Embedding(65025, 4544)
    (h): ModuleList(
      (0-31): 32 x DecoderLayer(
        (input_layernorm): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
        (self_attention): Attention(
          (maybe_rotary): RotaryEmbedding()
          (query_key_value): Linear4bit(in_features=4544, out_features=4672, bias=False)
          (dense): Linear4bit(in_features=4544, out_features=4544, bias=False)
          (attention_dropout): Dropout(p=0.0, inplace=False)
        )
        (mlp): MLP(
          (dense_h_to_4h): Linear4bit(in_features=4544, out_features=18176, bias=False)
          (act): GELU(approximate='none')
          (dense_4h_to_h): Linear4bit(in_features=18176, out_features=4544, bias=False)
        )
      )
    )
    (ln_f): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
  )
  (lm_head): Linear(in_features=4544, out_features=65025, bias=False)

ehartford

Quixi AI org Jun 14, 2023

I don't really know the reason why it is that way

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