Downloads · 30 days
231
5% of all-time downloads
RichardErkhov/aloobun_-_Cypher-7B-gguf
aloobun_-_Cypher-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
231
5% of all-time downloads
All-time downloads
4.7K
Public
Repo size
82.2 GB
Likes
1
Public
Click a slice to open those files.
.gguf95.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Cypher-7B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Cypher-7B.Q2_K.gguf | Q2_K | 2.53GB |
| Cypher-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| Cypher-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
| Cypher-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| Cypher-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
| Cypher-7B.Q3_K.gguf | Q3_K | 3.28GB |
| Cypher-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| Cypher-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| Cypher-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| Cypher-7B.Q4_0.gguf | Q4_0 | 3.83GB |
| Cypher-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| Cypher-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| Cypher-7B.Q4_K.gguf | Q4_K | 4.07GB |
| Cypher-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| Cypher-7B.Q4_1.gguf | Q4_1 | 4.24GB |
| Cypher-7B.Q5_0.gguf | Q5_0 | 4.65GB |
| Cypher-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| Cypher-7B.Q5_K.gguf | Q5_K | 4.78GB |
| Cypher-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| Cypher-7B.Q5_1.gguf | Q5_1 | 5.07GB |
| Cypher-7B.Q6_K.gguf | Q6_K | 5.53GB |
| Cypher-7B.Q8_0.gguf | Q8_0 | 7.17GB |
base_model:
Quants by @mradermacher: https://huggingface.co/mradermacher/Cypher-7B-GGUF
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: "NousResearch/Nous-Hermes-2-Mistral-7B-DPO"
layer_range: [0, 32]
- model: "cognitivecomputations/samantha-1.1-westlake-7b-laser"
layer_range: [0, 32]
merge_method: slerp
base_model: "NousResearch/Nous-Hermes-2-Mistral-7B-DPO"
parameters:
t:
- filter: lm_head
value: [0.55]
- filter: embed_tokens
value: [0.7]
- filter: self_attn
value: [0.65, 0.35]
- filter: mlp
value: [0.35, 0.65]
- filter: layernorm
value: [0.4, 0.6]
- filter: modelnorm
value: [0.6]
- value: 0.5
dtype: bfloat16
This model was merged using the SLERP merge method.
The following models were included in the merge: