Downloads · 30 days
59
9% of all-time downloads
RichardErkhov/senseable_-_Westlake-7B-gguf
senseable_-_Westlake-7B-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.
Downloads · 30 days
59
9% of all-time downloads
All-time downloads
646
Public
Repo size
82.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf95.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Westlake-7B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Westlake-7B.Q2_K.gguf | Q2_K | 2.53GB |
| Westlake-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| Westlake-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
| Westlake-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| Westlake-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
| Westlake-7B.Q3_K.gguf | Q3_K | 3.28GB |
| Westlake-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| Westlake-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| Westlake-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| Westlake-7B.Q4_0.gguf | Q4_0 | 3.83GB |
| Westlake-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| Westlake-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| Westlake-7B.Q4_K.gguf | Q4_K | 4.07GB |
| Westlake-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| Westlake-7B.Q4_1.gguf | Q4_1 | 4.24GB |
| Westlake-7B.Q5_0.gguf | Q5_0 | 4.65GB |
| Westlake-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| Westlake-7B.Q5_K.gguf | Q5_K | 4.78GB |
| Westlake-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| Westlake-7B.Q5_1.gguf | Q5_1 | 5.07GB |
| Westlake-7B.Q6_K.gguf | Q6_K | 5.53GB |
| Westlake-7B.Q8_0.gguf | Q8_0 | 7.17GB |
language:

Welcome to the documentation of Westlake-7B, a cutting-edge language model designed for exceptional role-play and text generation tasks. This README file aims to provide an overview of our capabilities, usage guidelines, and potential applications.
Westlake-7B is built upon a vast corpus of diverse texts, enabling it to generate contextually relevant responses in various scenarios. With its impressive size of 7 billion parameters, this model excels at understanding nuances in language and producing creative outputs.
To utilize Westlake-7B for your projects or experiments, follow these steps: 2. Prompting: Provide clear and concise prompts that outline the desired role-play scenario or text generation task. The quality of output depends heavily on the clarity and relevance of input instructions. 3. Feedback Loop: For optimal results, consider incorporating a feedback loop into your application to refine generated outputs based on user preferences or additional contextual information. This iterative process can significantly enhance the model's performance in specific domains. 4. Ethical Considerations: As with any AI system, ensure responsible usage of Westlake-7B by avoiding harmful content generation or misuse of its capabilities.
Westlake-7B's versatility makes it suitable for various applications across different industries:
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 74.48 |
| AI2 Reasoning Challenge (25-Shot) | 73.21 |
| HellaSwag (10-Shot) | 88.49 |
| MMLU (5-Shot) | 64.64 |
| TruthfulQA (0-shot) | 67.36 |
| Winogrande (5-shot) | 86.03 |
| GSM8k (5-shot) | 67.17 |