GGUF
Merge
mergekit
lazymergekit
Locutusque/Hercules-2.5-Mistral-7B
openchat/openchat-3.5-0106
Eval Results (legacy)
output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)ChatHercules-2.5-Mistral-7B
ChatHercules-2.5-Mistral-7B is a merge of the following models using LazyMergekit:
🧩 Configuration
slices:
- sources:
- model: Locutusque/Hercules-2.5-Mistral-7B
layer_range: [0, 32]
- model: openchat/openchat-3.5-0106
layer_range: [0, 32]
merge_method: slerp
base_model: Locutusque/Hercules-2.5-Mistral-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "hydra-project/ChatHercules-2.5-Mistral-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 68.24 |
| AI2 Reasoning Challenge (25-Shot) | 65.10 |
| HellaSwag (10-Shot) | 84.61 |
| MMLU (5-Shot) | 65.35 |
| TruthfulQA (0-shot) | 47.52 |
| Winogrande (5-shot) | 81.85 |
| GSM8k (5-shot) | 64.97 |
Quantization of Model hydra-project/ChatHercules-2.5-Mistral-7B. Created using llm-quantizer Pipeline
- Downloads last month
- 39
Hardware compatibility
Log In to add your hardware
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nold/ChatHercules-2.5-Mistral-7B-GGUF
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard65.100
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.610
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.350
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard47.520
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard81.850
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard64.970
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="nold/ChatHercules-2.5-Mistral-7B-GGUF", filename="", )