Downloads · 30 days
97
6% of all-time downloads
RichardErkhov/aloobun_-_Synch-Qwen1.5-1.8B-gguf
aloobun_-_Synch-Qwen1.5-1.8B-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
97
6% of all-time downloads
All-time downloads
1.5K
Public
Repo size
19.8 GB
Likes
0
Public
Click a slice to open those files.
.gguf23.4 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Synch-Qwen1.5-1.8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Synch-Qwen1.5-1.8B.Q2_K.gguf | Q2_K | 0.79GB |
| Synch-Qwen1.5-1.8B.Q3_K_S.gguf | Q3_K_S | 0.89GB |
| Synch-Qwen1.5-1.8B.Q3_K.gguf | Q3_K | 0.95GB |
| Synch-Qwen1.5-1.8B.Q3_K_M.gguf | Q3_K_M | 0.95GB |
| Synch-Qwen1.5-1.8B.Q3_K_L.gguf | Q3_K_L | 0.98GB |
| Synch-Qwen1.5-1.8B.IQ4_XS.gguf | IQ4_XS | 1.01GB |
| Synch-Qwen1.5-1.8B.Q4_0.gguf | Q4_0 | 1.04GB |
| Synch-Qwen1.5-1.8B.IQ4_NL.gguf | IQ4_NL | 1.05GB |
| Synch-Qwen1.5-1.8B.Q4_K_S.gguf | Q4_K_S | 1.08GB |
| Synch-Qwen1.5-1.8B.Q4_K.gguf | Q4_K | 1.13GB |
| Synch-Qwen1.5-1.8B.Q4_K_M.gguf | Q4_K_M | 1.13GB |
| Synch-Qwen1.5-1.8B.Q4_1.gguf | Q4_1 | 1.13GB |
| Synch-Qwen1.5-1.8B.Q5_0.gguf | Q5_0 | 1.22GB |
| Synch-Qwen1.5-1.8B.Q5_K_S.gguf | Q5_K_S | 1.24GB |
| Synch-Qwen1.5-1.8B.Q5_K.gguf | Q5_K | 1.28GB |
| Synch-Qwen1.5-1.8B.Q5_K_M.gguf | Q5_K_M | 1.28GB |
| Synch-Qwen1.5-1.8B.Q5_1.gguf | Q5_1 | 1.31GB |
| Synch-Qwen1.5-1.8B.Q6_K.gguf | Q6_K | 1.47GB |
| Synch-Qwen1.5-1.8B.Q8_0.gguf | Q8_0 | 1.82GB |
base_model:
This experimental model is the result of TIES merging only on the embedding weights, with Qwen/Qwen1.5-1.8B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: ties
base_model: Qwen/Qwen1.5-1.8B
models:
- model: aloobun/Reyna-Mini-1.8B-v0.2
parameters:
weight: 0.7
density:
- filter: embed_tokens
value: 0.66
- value: 1.0
- model: aloobun/Reyna-Mini-1.8B-v0.1
parameters:
weight:
- filter: embed_tokens
value: 0.3
- value: 0.0
density: 0.66