You can deploy this model and start earning money today!

RichardErkhov/
wolfeidau_-_NeuralHermes-2.5-Mistral-7B-gguf

Name: wolfeidau_-_NeuralHermes-2.5-Mistral-7B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NeuralHermes-2.5-Mistral-7B - GGUF

Model creator: https://huggingface.co/wolfeidau/
Original model: https://huggingface.co/wolfeidau/NeuralHermes-2.5-Mistral-7B/

Name	Quant method	Size
NeuralHermes-2.5-Mistral-7B.Q2_K.gguf	Q2_K	2.53GB
NeuralHermes-2.5-Mistral-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
NeuralHermes-2.5-Mistral-7B.IQ3_S.gguf	IQ3_S	2.96GB
NeuralHermes-2.5-Mistral-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
NeuralHermes-2.5-Mistral-7B.IQ3_M.gguf	IQ3_M	3.06GB
NeuralHermes-2.5-Mistral-7B.Q3_K.gguf	Q3_K	3.28GB
NeuralHermes-2.5-Mistral-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
NeuralHermes-2.5-Mistral-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
NeuralHermes-2.5-Mistral-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
NeuralHermes-2.5-Mistral-7B.Q4_0.gguf	Q4_0	3.83GB
NeuralHermes-2.5-Mistral-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
NeuralHermes-2.5-Mistral-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
NeuralHermes-2.5-Mistral-7B.Q4_K.gguf	Q4_K	4.07GB
NeuralHermes-2.5-Mistral-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
NeuralHermes-2.5-Mistral-7B.Q4_1.gguf	Q4_1	4.24GB
NeuralHermes-2.5-Mistral-7B.Q5_0.gguf	Q5_0	4.65GB
NeuralHermes-2.5-Mistral-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
NeuralHermes-2.5-Mistral-7B.Q5_K.gguf	Q5_K	4.78GB
NeuralHermes-2.5-Mistral-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
NeuralHermes-2.5-Mistral-7B.Q5_1.gguf	Q5_1	5.07GB
NeuralHermes-2.5-Mistral-7B.Q6_K.gguf	Q6_K	5.53GB
NeuralHermes-2.5-Mistral-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers tags:

dpo
mistral
finetune license: apache-2.0 datasets:
Intel/orca_dpo_pairs language:
en

NeuralHermes 2.5 - Mistral 7B

NeuralHermes-2.5 was created by fine-tuning OpenHermes-2.5 using a RLHF-like technique: Direct Preference Optimization (DPO) using the Intel/orca_dpo_pairs dataset.

Usage

You can also run this model using the following code:

python

import transformers
from transformers import AutoTokenizer

# Format prompt
message = [
    {"role": "system", "content": "You are a helpful assistant chatbot."},
    {"role": "user", "content": "What is a Large Language Model?"}
]
tokenizer = AutoTokenizer.from_pretrained(new_model)
prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)

# Create pipeline
pipeline = transformers.pipeline(
    "text-generation",
    model=new_model,
    tokenizer=tokenizer
)

# Generate text
sequences = pipeline(
    prompt,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    num_return_sequences=1,
    max_length=200,
)
print(sequences[0]['generated_text'])

Training hyperparameters

LoRA:

r=16
lora_alpha=16
lora_dropout=0.05
bias="none"
task_type="CAUSAL_LM"
target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']

Training arguments:

per_device_train_batch_size=4
gradient_accumulation_steps=4
gradient_checkpointing=True
learning_rate=5e-5
lr_scheduler_type="cosine"
max_steps=200
optim="paged_adamw_32bit"
warmup_steps=100

DPOTrainer:

beta=0.1
max_prompt_length=1024
max_length=1536

RichardErkhov/wolfeidau_-_NeuralHermes-2.5-Mistral-7B-gguf

Original model description:

NeuralHermes 2.5 - Mistral 7B

Usage

Training hyperparameters

RichardErkhov/
wolfeidau_-_NeuralHermes-2.5-Mistral-7B-gguf