43 lines
1.7 KiB
Markdown
43 lines
1.7 KiB
Markdown
|
---
|
|||
|
|
license: apache-2.0
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
base_model:
|
|||
|
|
- OpenBuddy/SimpleChat-4B-V1
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
library_name: transformers
|
|||
|
|
tags:
|
|||
|
|
- text-generation-inference
|
|||
|
|
- Non-CoT
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **SimpleChat-4B-V1-f32-GGUF**
|
|||
|
|
|
|||
|
|
> OpenBuddy’s SimpleChat-4B-V1 is a 4B-parameter conversational AI model built for streamlined, casual everyday interactions, emphasizing concise, rational, and creative responses without relying on complex chain-of-thought reasoning. Optimized for natural dialogue, SimpleChat-4B-V1 is part of the SimpleChat series exploring Non-Chain-of-Thought (Non-CoT) models, making it especially suitable for direct, engaging conversations that prioritize clarity and brevity while retaining the ability to enhance creativity and expressive capacity in outputs.
|
|||
|
|
|
|||
|
|
## Model Files
|
|||
|
|
|
|||
|
|
| File Name | Quant Type | File Size |
|
|||
|
|
| - | - | - |
|
|||
|
|
| SimpleChat-4B-V1.BF16.gguf | BF16 | 8.05 GB |
|
|||
|
|
| SimpleChat-4B-V1.F16.gguf | F16 | 8.05 GB |
|
|||
|
|
| SimpleChat-4B-V1.F32.gguf | F32 | 16.1 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q2_K.gguf | Q2_K | 1.67 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q3_K_L.gguf | Q3_K_L | 2.24 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q3_K_M.gguf | Q3_K_M | 2.08 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q3_K_S.gguf | Q3_K_S | 1.89 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q4_K_M.gguf | Q4_K_M | 2.5 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q4_K_S.gguf | Q4_K_S | 2.38 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q5_K_M.gguf | Q5_K_M | 2.89 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q5_K_S.gguf | Q5_K_S | 2.82 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q6_K.gguf | Q6_K | 3.31 GB |
|
|||
|
|
| SimpleChat-4B-V1.Q8_0.gguf | Q8_0 | 4.28 GB |
|
|||
|
|
|
|||
|
|
## Quants Usage
|
|||
|
|
|
|||
|
|
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
|||
|
|
|
|||
|
|
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|||
|
|
types (lower is better):
|
|||
|
|
|
|||
|
|
|