Instructions to use RossAscends/Paradigm_7B_6bpw_exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RossAscends/Paradigm_7B_6bpw_exl2 with Transformers:

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

pipe = pipeline("text-generation", model="RossAscends/Paradigm_7B_6bpw_exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RossAscends/Paradigm_7B_6bpw_exl2")
model = AutoModelForCausalLM.from_pretrained("RossAscends/Paradigm_7B_6bpw_exl2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RossAscends/Paradigm_7B_6bpw_exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RossAscends/Paradigm_7B_6bpw_exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RossAscends/Paradigm_7B_6bpw_exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RossAscends/Paradigm_7B_6bpw_exl2

SGLang

How to use RossAscends/Paradigm_7B_6bpw_exl2 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 "RossAscends/Paradigm_7B_6bpw_exl2" \
    --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": "RossAscends/Paradigm_7B_6bpw_exl2",
		"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 "RossAscends/Paradigm_7B_6bpw_exl2" \
        --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": "RossAscends/Paradigm_7B_6bpw_exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RossAscends/Paradigm_7B_6bpw_exl2 with Docker Model Runner:
```
docker model run hf.co/RossAscends/Paradigm_7B_6bpw_exl2
```

Paradigm_7B_6bpw_exl2 / README.md

RossAscends

Update README.md

03c186d verified over 2 years ago

preview code

Raw

History Blame Contribute Delete

5.13 kB

metadata

language:
  - en
license: cc-by-sa-4.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - liminerity/Multiverse-Experiment-slerp-7b
  - jeiku/Alpaca_NSFW_Shuffled_Mistral
  - ResplendentAI/Datura_7B
  - ChaoticNeutrals/Eris_Remix_7B
datasets:
  - ResplendentAI/Alpaca_NSFW_Shuffled
  - unalignment/toxic-dpo-v0.2
model-index:
  - name: Paradigm_7B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 73.63
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Paradigm_7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 88.66
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Paradigm_7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.02
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Paradigm_7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 75.19
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Paradigm_7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 84.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Paradigm_7B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 66.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ResplendentAI/Paradigm_7B
          name: Open LLM Leaderboard

Paradigm

This is a 8bpw exl2 quant of the Paradigm 7B model. ChatML or Alpaca instruct sequences both work.

An incredibly effective and intelligent RP model designed to be the best bot you've ever used. I hope you like it!

GGUF available here: https://huggingface.co/Lewdiculous/Paradigm_7B-GGUF-IQ-Imatrix

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.47
AI2 Reasoning Challenge (25-Shot)	73.63
HellaSwag (10-Shot)	88.66
MMLU (5-Shot)	64.02
TruthfulQA (0-shot)	75.19
Winogrande (5-shot)	84.53
GSM8k (5-shot)	66.79

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: ChaoticNeutrals/Eris_Remix_7B
parameters:
  normalize: true
models:
  - model: ChaoticNeutrals/Eris_Remix_7B
    parameters:
      weight: 1
  - model: ResplendentAI/Datura_7B
    parameters:
      weight: 1
  - model: liminerity/Multiverse-Experiment-slerp-7b+jeiku/Alpaca_NSFW_Shuffled_Mistral
    parameters:
      weight: 0.33
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.47
AI2 Reasoning Challenge (25-Shot)	73.63
HellaSwag (10-Shot)	88.66
MMLU (5-Shot)	64.02
TruthfulQA (0-shot)	75.19
Winogrande (5-shot)	84.53
GSM8k (5-shot)	66.79