bartowski's picture
Llamacpp quants
ae1ffb1 verified
---
license: apache-2.0
library_name: transformers
tags:
- chemistry
- biology
- code
- medical
- not-for-all-audiences
datasets:
- Locutusque/Hercules-v3.0
model-index:
- name: Hercules-3.1-Mistral-7B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 61.18
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 83.55
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 63.65
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 42.83
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 79.01
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 42.3
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B
name: Open LLM Leaderboard
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp Quantizations of Hercules-3.1-Mistral-7B
Using <a href="https://github.com/ggerganov/llama.cpp/commit/fa974646e1a2024fc7dc9e6f27cf1f2f5d4a3763">llama.cpp commit fa97464</a> for quantization.
Original model: https://huggingface.co/Locutusque/Hercules-3.1-Mistral-7B
Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Hercules-3.1-Mistral-7B-Q8_0.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
| [Hercules-3.1-Mistral-7B-Q6_K.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
| [Hercules-3.1-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
| [Hercules-3.1-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
| [Hercules-3.1-Mistral-7B-Q5_0.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
| [Hercules-3.1-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
| [Hercules-3.1-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
| [Hercules-3.1-Mistral-7B-Q4_0.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
| [Hercules-3.1-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
| [Hercules-3.1-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
| [Hercules-3.1-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
| [Hercules-3.1-Mistral-7B-Q2_K.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski