RichardErkhov/numind_-_NuExtract-tiny-exl2

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NuExtract-tiny - EXL2

• Model creator: https://huggingface.co/numind/
• Original model: https://huggingface.co/numind/NuExtract-tiny/

Available sizes

| Branch | Bits | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ | | 8_0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | | 6_5 | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, recommended. | | 5_0 | 5.0 | Slightly lower quality vs 6.5, but usable on 8GB cards. | | 4_25 | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. | | 3_5 | 3.5 | Lower quality, only use if you have to. |

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/numind_-_NuExtract-tiny-exl2 NuExtract-tiny-6_5

With huggingface hub:

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch: Linux:

huggingface-cli download numind_-_NuExtract-tiny-exl2 --revision 6_5 --local-dir NuExtract-tiny-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download numind_-_NuExtract-tiny-exl2 --revision 6_5 --local-dir NuExtract-tiny-6.5 --local-dir-use-symlinks False

Original model description:

license: mit language: - en base_model: Qwen/Qwen1.5-0.5B new_version: numind/NuExtract-v1.5

⚠️ NOTE: This model is out-dated. Find the updated version here

Structure Extraction Model by NuMind 🔥

NuExtract_tiny is a version of Qwen1.5-0.5, fine-tuned on a private high-quality synthetic dataset for information extraction. To use the model, provide an input text (less than 2000 tokens) and a JSON template describing the information you need to extract.

Note: This model is purely extractive, so all text output by the model is present as is in the original text. You can also provide an example of output formatting to help the model understand your task more precisely.

Note: While this model provides good 0 shot performance, it is intended to be fine-tuned on a specific task (>=30 examples).

We also provide a base (3.8B) and large(7B) version of this model: NuExtract and NuExtract-large

Checkout other models by NuMind:

• SOTA Zero-shot NER Model NuNER Zero
• SOTA Multilingual Entity Recognition Foundation Model: link
• SOTA Sentiment Analysis Foundation Model: English, Multilingual

Usage

To use the model:

import json
from transformers import AutoModelForCausalLM, AutoTokenizer


def predict_NuExtract(model, tokenizer, text, schema, example=["","",""]):
    schema = json.dumps(json.loads(schema), indent=4)
    input_llm =  "<|input|>\n### Template:\n" +  schema + "\n"
    for i in example:
      if i != "":
          input_llm += "### Example:\n"+ json.dumps(json.loads(i), indent=4)+"\n"
    
    input_llm +=  "### Text:\n"+text +"\n<|output|>\n"
    input_ids = tokenizer(input_llm, return_tensors="pt", truncation=True, max_length=4000).to("cuda")

    output = tokenizer.decode(model.generate(**input_ids)[0], skip_special_tokens=True)
    return output.split("<|output|>")[1].split("<|end-output|>")[0]


model = AutoModelForCausalLM.from_pretrained("numind/NuExtract-tiny", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("numind/NuExtract-tiny", trust_remote_code=True)

model.to("cuda")

model.eval()

text = """We introduce Mistral 7B, a 7–billion-parameter language model engineered for
superior performance and efficiency. Mistral 7B outperforms the best open 13B
model (Llama 2) across all evaluated benchmarks, and the best released 34B
model (Llama 1) in reasoning, mathematics, and code generation. Our model
leverages grouped-query attention (GQA) for faster inference, coupled with sliding
window attention (SWA) to effectively handle sequences of arbitrary length with a
reduced inference cost. We also provide a model fine-tuned to follow instructions,
Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and
automated benchmarks. Our models are released under the Apache 2.0 license.
Code: https://github.com/mistralai/mistral-src
Webpage: https://mistral.ai/news/announcing-mistral-7b/"""

schema = """{
    "Model": {
        "Name": "",
        "Number of parameters": "",
        "Number of max token": "",
        "Architecture": []
    },
    "Usage": {
        "Use case": [],
        "Licence": ""
    }
}"""

prediction = predict_NuExtract(model, tokenizer, text, schema, example=["","",""])
print(prediction)