Downloads · 30 days
117
5% of all-time downloads
TeeZee_-_DarkSapling-7B-v1.1-gguf
RichardErkhov/TeeZee_-_DarkSapling-7B-v1.1-gguf
TeeZee_-_DarkSapling-7B-v1.1-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
2.4K
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 7, 2024
- Updated
- Sep 7, 2024
- SHA
- 43e81eda
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
DarkSapling-7B-v1.1 - GGUF
- Model creator: https://huggingface.co/TeeZee/
- Original model: https://huggingface.co/TeeZee/DarkSapling-7B-v1.1/
| Name | Quant method | Size |
|---|---|---|
| DarkSapling-7B-v1.1.Q2_K.gguf | Q2_K | 2.53GB |
| DarkSapling-7B-v1.1.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| DarkSapling-7B-v1.1.IQ3_S.gguf | IQ3_S | 2.96GB |
| DarkSapling-7B-v1.1.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| DarkSapling-7B-v1.1.IQ3_M.gguf | IQ3_M | 3.06GB |
| DarkSapling-7B-v1.1.Q3_K.gguf | Q3_K | 3.28GB |
| DarkSapling-7B-v1.1.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| DarkSapling-7B-v1.1.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| DarkSapling-7B-v1.1.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| DarkSapling-7B-v1.1.Q4_0.gguf | Q4_0 | 3.83GB |
| DarkSapling-7B-v1.1.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| DarkSapling-7B-v1.1.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| DarkSapling-7B-v1.1.Q4_K.gguf | Q4_K | 4.07GB |
| DarkSapling-7B-v1.1.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| DarkSapling-7B-v1.1.Q4_1.gguf | Q4_1 | 4.24GB |
| DarkSapling-7B-v1.1.Q5_0.gguf | Q5_0 | 4.65GB |
| DarkSapling-7B-v1.1.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| DarkSapling-7B-v1.1.Q5_K.gguf | Q5_K | 4.78GB |
| DarkSapling-7B-v1.1.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| DarkSapling-7B-v1.1.Q5_1.gguf | Q5_1 | 5.07GB |
| DarkSapling-7B-v1.1.Q6_K.gguf | Q6_K | 5.53GB |
| DarkSapling-7B-v1.1.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
language:
- en license: apache-2.0 tags:
- mistral
- not-for-all-audiences
- merge pipeline_tag: text-generation inference: false model-index:
- name: DarkSapling-7B-v1.1
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: 63.48 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkSapling-7B-v1.1 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: 85.09 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkSapling-7B-v1.1 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: 64.47 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkSapling-7B-v1.1 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: 52.04 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkSapling-7B-v1.1 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: 78.53 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkSapling-7B-v1.1 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: 45.19 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkSapling-7B-v1.1 name: Open LLM Leaderboard
- 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:
DarkSapling-7B-v1.1
Model Details
- A result of 4 models merge.
- models used for merge: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser KoboldAI/Mistral-7B-Holodeck-1 KoboldAI/Mistral-7B-Erebus-v3 cognitivecomputations/samantha-mistral-7b
- See mergekit-config.yml for details on the merge method used.
Warning: This model can produce NSFW content!
Results
- a little different than version v1.0, more romantic and empathetic.
- best for one-on-one ERP.
- produces SFW nad NSFW content without issues, switches context seamlessly.
- sticks to character card
- pretty smart due to mistral, empathetic after Samantha and sometimes produces dark scenarions - Erebus.
- storytelling is satisfactory due to Holodeck
- good at following instructions
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel: <a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 64.80 |
| AI2 Reasoning Challenge (25-Shot) | 63.48 |
| HellaSwag (10-Shot) | 85.09 |
| MMLU (5-Shot) | 64.47 |
| TruthfulQA (0-shot) | 52.04 |
| Winogrande (5-shot) | 78.53 |
| GSM8k (5-shot) | 45.19 |
- Created
- Sep 7, 2024
- Updated
- Sep 7, 2024