NeuralHermes-2.5-Mistral-7B
Description
This repo contains GGUF format model files for NeuralHermes-2.5-Mistral-7B.
Files Provided
Name | Quant | Bits | File Size | Remark |
---|---|---|---|---|
neuralhermes-2.5-mistral-7b.IQ3_S.gguf | IQ3_S | 3 | 3.18 GB | 3.44 bpw quantization |
neuralhermes-2.5-mistral-7b.IQ3_M.gguf | IQ3_M | 3 | 3.28 GB | 3.66 bpw quantization mix |
neuralhermes-2.5-mistral-7b.Q4_0.gguf | Q4_0 | 4 | 4.11 GB | 3.56G, +0.2166 ppl |
neuralhermes-2.5-mistral-7b.IQ4_NL.gguf | IQ4_NL | 4 | 4.16 GB | 4.25 bpw non-linear quantization |
neuralhermes-2.5-mistral-7b.Q4_K_M.gguf | Q4_K_M | 4 | 4.37 GB | 3.80G, +0.0532 ppl |
neuralhermes-2.5-mistral-7b.Q5_K_M.gguf | Q5_K_M | 5 | 5.13 GB | 4.45G, +0.0122 ppl |
neuralhermes-2.5-mistral-7b.Q6_K.gguf | Q6_K | 6 | 5.94 GB | 5.15G, +0.0008 ppl |
neuralhermes-2.5-mistral-7b.Q8_0.gguf | Q8_0 | 8 | 7.70 GB | 6.70G, +0.0004 ppl |
Parameters
path | type | architecture | rope_theta | sliding_win | max_pos_embed |
---|---|---|---|---|---|
teknium/OpenHermes-2.5-Mistral-7B | mistral | MistralForCausalLM | 10000 | 4096 | 32768 |
Benchmarks
Original Model Card
NeuralHermes 2.5 - Mistral 7B
NeuralHermes is based on the teknium/OpenHermes-2.5-Mistral-7B model that has been further fine-tuned with Direct Preference Optimization (DPO) using the mlabonne/chatml_dpo_pairs dataset. It surpasses the original model on most benchmarks (see results).
It is directly inspired by the RLHF process described by Intel/neural-chat-7b-v3-1's authors to improve performance. I used the same dataset and reformatted it to apply the ChatML template.
The code to train this model is available on Google Colab and GitHub. It required an A100 GPU for about an hour.
Quantized models
- GGUF: https://huggingface.co/TheBloke/NeuralHermes-2.5-Mistral-7B-GGUF
- AWQ: https://huggingface.co/TheBloke/NeuralHermes-2.5-Mistral-7B-AWQ
- GPTQ: https://huggingface.co/TheBloke/NeuralHermes-2.5-Mistral-7B-GPTQ
- EXL2:
- 3.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-3.0bpw-h6-exl2
- 4.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-4.0bpw-h6-exl2
- 5.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-5.0bpw-h6-exl2
- 6.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-6.0bpw-h6-exl2
- 8.0bpw: https://huggingface.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2
Results
Update: NeuralHermes-2.5 became the best Hermes-based model on the Open LLM leaderboard and one of the very best 7b models. 🎉
Teknium (author of OpenHermes-2.5-Mistral-7B) benchmarked the model (see his tweet).
Results are improved on every benchmark: AGIEval (from 43.07% to 43.62%), GPT4All (from 73.12% to 73.25%), and TruthfulQA.
AGIEval
GPT4All
TruthfulQA
You can check the Weights & Biases project here.
Usage
You can run this model using LM Studio or any other frontend.
You can also run this model using the following code:
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
- Downloads last month
- 88
Model tree for koesn/NeuralHermes-2.5-Mistral-7B-GGUF
Base model
mistralai/Mistral-7B-v0.1Dataset used to train koesn/NeuralHermes-2.5-Mistral-7B-GGUF
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard66.550
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.900
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.320
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard54.930
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.300
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard61.330