README.md

metadata

base_model: flammenai/flammen-mistral-7B
inference: false
library_name: transformers
license: apache-2.0
merged_models:
  - bardsai/jaskier-7b-dpo-v5.6
  - nbeerbower/bruphin-zeta
  - Gille/StrangeMerges_16-7B-slerp
model-index:
  - name: flammen
    results:
      - dataset:
          args:
            num_few_shot: 25
          config: ARC-Challenge
          name: AI2 Reasoning Challenge (25-Shot)
          split: test
          type: ai2_arc
        metrics:
          - name: normalized accuracy
            type: acc_norm
            value: 68.17
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/flammen
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 10
          name: HellaSwag (10-Shot)
          split: validation
          type: hellaswag
        metrics:
          - name: normalized accuracy
            type: acc_norm
            value: 87.06
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/flammen
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 5
          config: all
          name: MMLU (5-Shot)
          split: test
          type: cais/mmlu
        metrics:
          - name: accuracy
            type: acc
            value: 64.68
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/flammen
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 0
          config: multiple_choice
          name: TruthfulQA (0-shot)
          split: validation
          type: truthful_qa
        metrics:
          - type: mc2
            value: 63.02
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/flammen
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 5
          config: winogrande_xl
          name: Winogrande (5-shot)
          split: validation
          type: winogrande
        metrics:
          - name: accuracy
            type: acc
            value: 81.45
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/flammen
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 5
          config: main
          name: GSM8k (5-shot)
          split: test
          type: gsm8k
        metrics:
          - name: accuracy
            type: acc
            value: 66.03
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/flammen
        task:
          name: Text Generation
          type: text-generation
pipeline_tag: text-generation
quantized_by: Suparious
tags:
  - 4-bit
  - AWQ
  - text-generation
  - autotrain_compatible
  - endpoints_compatible
  - mergekit
  - merge

flammenai/flammen-mistral-7B AWQ

• Model creator: flammenai
• Original model: flammen-mistral-7B

How to use

Install the necessary packages

pip install --upgrade autoawq autoawq-kernels

Example Python code

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer

model_path = "solidrust/flammen-mistral-7B-AWQ"
system_message = "You are flammen-mistral-7B, incarnated as a powerful AI. You were created by flammenai."

# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
                                          fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
                                          trust_remote_code=True)
streamer = TextStreamer(tokenizer,
                        skip_prompt=True,
                        skip_special_tokens=True)

# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""

prompt = "You're standing on the surface of the Earth. "\
        "You walk one mile south, one mile west and one mile north. "\
        "You end up exactly where you started. Where are you?"

tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
                  return_tensors='pt').input_ids.cuda()

# Generate output
generation_output = model.generate(tokens,
                                  streamer=streamer,
                                  max_new_tokens=512)

About AWQ

AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.

AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.

It is supported by:

• Text Generation Webui - using Loader: AutoAWQ
• vLLM - version 0.2.2 or later for support for all model types.
• Hugging Face Text Generation Inference (TGI)
• Transformers version 4.35.0 and later, from any code or client that supports Transformers
• AutoAWQ - for use from Python code