Quantization made by Richard Erkhov.

mistral-nouns500 - GGUF

Model creator: https://huggingface.co/waterdrops0/
Original model: https://huggingface.co/waterdrops0/mistral-nouns500/

Name	Quant method	Size
mistral-nouns500.Q2_K.gguf	Q2_K	2.53GB
mistral-nouns500.IQ3_XS.gguf	IQ3_XS	2.81GB
mistral-nouns500.IQ3_S.gguf	IQ3_S	2.96GB
mistral-nouns500.Q3_K_S.gguf	Q3_K_S	2.95GB
mistral-nouns500.IQ3_M.gguf	IQ3_M	3.06GB
mistral-nouns500.Q3_K.gguf	Q3_K	3.28GB
mistral-nouns500.Q3_K_M.gguf	Q3_K_M	3.28GB
mistral-nouns500.Q3_K_L.gguf	Q3_K_L	3.56GB
mistral-nouns500.IQ4_XS.gguf	IQ4_XS	3.67GB
mistral-nouns500.Q4_0.gguf	Q4_0	3.83GB
mistral-nouns500.IQ4_NL.gguf	IQ4_NL	3.87GB
mistral-nouns500.Q4_K_S.gguf	Q4_K_S	3.86GB
mistral-nouns500.Q4_K.gguf	Q4_K	4.07GB
mistral-nouns500.Q4_K_M.gguf	Q4_K_M	4.07GB
mistral-nouns500.Q4_1.gguf	Q4_1	4.24GB
mistral-nouns500.Q5_0.gguf	Q5_0	4.65GB
mistral-nouns500.Q5_K_S.gguf	Q5_K_S	4.65GB
mistral-nouns500.Q5_K.gguf	Q5_K	4.78GB
mistral-nouns500.Q5_K_M.gguf	Q5_K_M	4.78GB
mistral-nouns500.Q5_1.gguf	Q5_1	5.07GB
mistral-nouns500.Q6_K.gguf	Q6_K	5.53GB
mistral-nouns500.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc0-1.0 library_name: transformers pipeline_tag: text-generation tags: - text-generation - causal-lm - mistral - fine-tuned language: en base_model: mistralai/Mistral-7B-v0.1

Mistral-7B Fine-Tuned on Nouns DAO Comments

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on a custom dataset of Nouns DAO comments.

Model Description

The model has been fine-tuned to generate comments by Nouns DAO members on proposals, focusing on community discussions and insights.

Intended Use

Primary Use Case: Generating realistic DAO member comments for proposals.
Languages Supported: English (en).

How to Use

You can use this model with the Transformers library:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "your_username/your_model_name"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to("cuda" or "cpu")

prompt = "The following is a comment by a Nouns DAO member on the proposal to gift 1000 glasses to kids in need:"

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100, repetition_penalty=1.15, temperature=0.7, top_p=0.9)

generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)