Downloads · 30 days
42
6% of all-time downloads
RichardErkhov/tdot604_-_Hazy-Llama-70b-gguf
tdot604_-_Hazy-Llama-70b-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
42
6% of all-time downloads
All-time downloads
712
Public
Repo size
790 GB
Likes
0
Public
Click a slice to open those files.
.gguf916 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Hazy-Llama-70b - GGUF
| Name | Quant method | Size |
|---|---|---|
| Hazy-Llama-70b.Q2_K.gguf | Q2_K | 24.56GB |
| Hazy-Llama-70b.IQ3_XS.gguf | IQ3_XS | 27.3GB |
| Hazy-Llama-70b.IQ3_S.gguf | IQ3_S | 28.79GB |
| Hazy-Llama-70b.Q3_K_S.gguf | Q3_K_S | 28.79GB |
| Hazy-Llama-70b.IQ3_M.gguf | IQ3_M | 29.74GB |
| Hazy-Llama-70b.Q3_K.gguf | Q3_K | 31.91GB |
| Hazy-Llama-70b.Q3_K_M.gguf | Q3_K_M | 31.91GB |
| Hazy-Llama-70b.Q3_K_L.gguf | Q3_K_L | 25.15GB |
| Hazy-Llama-70b.IQ4_XS.gguf | IQ4_XS | 35.64GB |
| Hazy-Llama-70b.Q4_0.gguf | Q4_0 | 37.22GB |
| Hazy-Llama-70b.IQ4_NL.gguf | IQ4_NL | 37.58GB |
| Hazy-Llama-70b.Q4_K_S.gguf | Q4_K_S | 37.58GB |
| Hazy-Llama-70b.Q4_K.gguf | Q4_K | 39.6GB |
| Hazy-Llama-70b.Q4_K_M.gguf | Q4_K_M | 39.6GB |
| Hazy-Llama-70b.Q4_1.gguf | Q4_1 | 41.27GB |
| Hazy-Llama-70b.Q5_0.gguf | Q5_0 | 45.32GB |
| Hazy-Llama-70b.Q5_K_S.gguf | Q5_K_S | 45.32GB |
| Hazy-Llama-70b.Q5_K.gguf | Q5_K | 46.52GB |
| Hazy-Llama-70b.Q5_K_M.gguf | Q5_K_M | 46.52GB |
| Hazy-Llama-70b.Q5_1.gguf | Q5_1 | 49.36GB |
| Hazy-Llama-70b.Q6_K.gguf | Q6_K | 53.91GB |
| Hazy-Llama-70b.Q8_0.gguf | Q8_0 | 69.83GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using mattshumer/Reflection-Llama-3.1-70B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: mattshumer/Reflection-Llama-3.1-70B
parameters:
weight: 0.8
- model: Sao10K/L3-70B-Euryale-v2.1
parameters:
weight: 0.2
merge_method: ties
base_model: mattshumer/Reflection-Llama-3.1-70B
parameters:
density: 0.7
normalize: true
dtype: float16
tokenizer_source: base