Downloads · 30 days
52
2% of all-time downloads
RichardErkhov/Nelathan_-_Qwen2-7B-FocusMix-gguf
Nelathan_-_Qwen2-7B-FocusMix-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
52
2% of all-time downloads
All-time downloads
2.5K
Public
Repo size
88.1 GB
Likes
1
Public
Click a slice to open those files.
.gguf102 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen2-7B-FocusMix - GGUF
| Name | Quant method | Size |
|---|---|---|
| Qwen2-7B-FocusMix.Q2_K.gguf | Q2_K | 2.81GB |
| Qwen2-7B-FocusMix.IQ3_XS.gguf | IQ3_XS | 3.11GB |
| Qwen2-7B-FocusMix.IQ3_S.gguf | IQ3_S | 3.26GB |
| Qwen2-7B-FocusMix.Q3_K_S.gguf | Q3_K_S | 3.25GB |
| Qwen2-7B-FocusMix.IQ3_M.gguf | IQ3_M | 3.33GB |
| Qwen2-7B-FocusMix.Q3_K.gguf | Q3_K | 3.55GB |
| Qwen2-7B-FocusMix.Q3_K_M.gguf | Q3_K_M | 3.55GB |
| Qwen2-7B-FocusMix.Q3_K_L.gguf | Q3_K_L | 3.81GB |
| Qwen2-7B-FocusMix.IQ4_XS.gguf | IQ4_XS | 3.96GB |
| Qwen2-7B-FocusMix.Q4_0.gguf | Q4_0 | 4.13GB |
| Qwen2-7B-FocusMix.IQ4_NL.gguf | IQ4_NL | 4.15GB |
| Qwen2-7B-FocusMix.Q4_K_S.gguf | Q4_K_S | 4.15GB |
| Qwen2-7B-FocusMix.Q4_K.gguf | Q4_K | 4.36GB |
| Qwen2-7B-FocusMix.Q4_K_M.gguf | Q4_K_M | 4.36GB |
| Qwen2-7B-FocusMix.Q4_1.gguf | Q4_1 | 4.54GB |
| Qwen2-7B-FocusMix.Q5_0.gguf | Q5_0 | 4.95GB |
| Qwen2-7B-FocusMix.Q5_K_S.gguf | Q5_K_S | 4.95GB |
| Qwen2-7B-FocusMix.Q5_K.gguf | Q5_K | 5.07GB |
| Qwen2-7B-FocusMix.Q5_K_M.gguf | Q5_K_M | 5.07GB |
| Qwen2-7B-FocusMix.Q5_1.gguf | Q5_1 | 5.36GB |
| Qwen2-7B-FocusMix.Q6_K.gguf | Q6_K | 5.82GB |
| Qwen2-7B-FocusMix.Q8_0.gguf | Q8_0 | 7.54GB |
base_model:
This is a model created by merging several powerful language models:
FocusMix inherits the strengths of its component models, resulting in a model with:
Purpose: aims to provide a powerful and versatile language model that excels in:
The following YAML configuration was used to produce this model:
merge_method: model_stock
base_model: Qwen/Qwen2-7B
models:
- model: Replete-AI/Replete-LLM-Qwen2-7b
- model: arcee-ai/Arcee-Spark
- model: Weyaxi/Einstein-v7-Qwen2-7B
- model: MaziyarPanahi/calme-2.8-qwen2-7b
dtype: bfloat16
tokenizer_source: base