Downloads · 30 days
161
10% of all-time downloads
axxd_-_wizardllama-7b-gguf
RichardErkhov/axxd_-_wizardllama-7b-gguf
axxd_-_wizardllama-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.
All-time downloads
1.6K
Public
Repo size
76.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf88.7 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 14, 2024
- Updated
- Sep 14, 2024
- SHA
- 13480bb2
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
wizardllama-7b - GGUF
- Model creator: https://huggingface.co/axxd/
- Original model: https://huggingface.co/axxd/wizardllama-7b/
| Name | Quant method | Size |
|---|---|---|
| wizardllama-7b.Q2_K.gguf | Q2_K | 2.36GB |
| wizardllama-7b.IQ3_XS.gguf | IQ3_XS | 2.6GB |
| wizardllama-7b.IQ3_S.gguf | IQ3_S | 2.75GB |
| wizardllama-7b.Q3_K_S.gguf | Q3_K_S | 2.75GB |
| wizardllama-7b.IQ3_M.gguf | IQ3_M | 2.9GB |
| wizardllama-7b.Q3_K.gguf | Q3_K | 3.07GB |
| wizardllama-7b.Q3_K_M.gguf | Q3_K_M | 3.07GB |
| wizardllama-7b.Q3_K_L.gguf | Q3_K_L | 3.35GB |
| wizardllama-7b.IQ4_XS.gguf | IQ4_XS | 3.4GB |
| wizardllama-7b.Q4_0.gguf | Q4_0 | 3.56GB |
| wizardllama-7b.IQ4_NL.gguf | IQ4_NL | 3.58GB |
| wizardllama-7b.Q4_K_S.gguf | Q4_K_S | 3.59GB |
| wizardllama-7b.Q4_K.gguf | Q4_K | 3.8GB |
| wizardllama-7b.Q4_K_M.gguf | Q4_K_M | 3.8GB |
| wizardllama-7b.Q4_1.gguf | Q4_1 | 3.95GB |
| wizardllama-7b.Q5_0.gguf | Q5_0 | 4.33GB |
| wizardllama-7b.Q5_K_S.gguf | Q5_K_S | 4.33GB |
| wizardllama-7b.Q5_K.gguf | Q5_K | 4.45GB |
| wizardllama-7b.Q5_K_M.gguf | Q5_K_M | 4.45GB |
| wizardllama-7b.Q5_1.gguf | Q5_1 | 4.72GB |
| wizardllama-7b.Q6_K.gguf | Q6_K | 5.15GB |
| wizardllama-7b.Q8_0.gguf | Q8_0 | 6.67GB |
Original model description:
base_model:
- codellama/CodeLlama-7b-Python-hf
- WizardLM/WizardCoder-Python-7B-V1.0 library_name: transformers tags:
- mergekit
- merge
- code license: apache-2.0
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: WizardLM/WizardCoder-Python-7B-V1.0
layer_range: [0, 32]
- model: codellama/CodeLlama-7b-Python-hf
layer_range: [0, 32]
merge_method: slerp
base_model: codellama/CodeLlama-7b-Python-hf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
- Created
- Sep 14, 2024
- Updated
- Sep 14, 2024