Hugging Face's logo

RichardErkhov
/
PraneethSunku_-_vic7b_sqlcoder7b_trial-gguf

GGUF
Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

vic7b_sqlcoder7b_trial - GGUF

Name Quant method Size
vic7b_sqlcoder7b_trial.Q2_K.gguf Q2_K 2.36GB
vic7b_sqlcoder7b_trial.IQ3_XS.gguf IQ3_XS 2.6GB
vic7b_sqlcoder7b_trial.IQ3_S.gguf IQ3_S 2.75GB
vic7b_sqlcoder7b_trial.Q3_K_S.gguf Q3_K_S 2.75GB
vic7b_sqlcoder7b_trial.IQ3_M.gguf IQ3_M 2.9GB
vic7b_sqlcoder7b_trial.Q3_K.gguf Q3_K 3.07GB
vic7b_sqlcoder7b_trial.Q3_K_M.gguf Q3_K_M 3.07GB
vic7b_sqlcoder7b_trial.Q3_K_L.gguf Q3_K_L 3.35GB
vic7b_sqlcoder7b_trial.IQ4_XS.gguf IQ4_XS 3.4GB
vic7b_sqlcoder7b_trial.Q4_0.gguf Q4_0 3.56GB
vic7b_sqlcoder7b_trial.IQ4_NL.gguf IQ4_NL 3.58GB
vic7b_sqlcoder7b_trial.Q4_K_S.gguf Q4_K_S 3.59GB
vic7b_sqlcoder7b_trial.Q4_K.gguf Q4_K 3.8GB
vic7b_sqlcoder7b_trial.Q4_K_M.gguf Q4_K_M 3.8GB
vic7b_sqlcoder7b_trial.Q4_1.gguf Q4_1 3.95GB
vic7b_sqlcoder7b_trial.Q5_0.gguf Q5_0 4.33GB
vic7b_sqlcoder7b_trial.Q5_K_S.gguf Q5_K_S 4.33GB
vic7b_sqlcoder7b_trial.Q5_K.gguf Q5_K 4.45GB
vic7b_sqlcoder7b_trial.Q5_K_M.gguf Q5_K_M 4.45GB
vic7b_sqlcoder7b_trial.Q5_1.gguf Q5_1 4.72GB
vic7b_sqlcoder7b_trial.Q6_K.gguf Q6_K 5.15GB
vic7b_sqlcoder7b_trial.Q8_0.gguf Q8_0 6.67GB

Original model description:

base_model:

  • lmsys/vicuna-7b-v1.5
  • defog/sqlcoder-7b-2 library_name: transformers tags:
  • mergekit
  • merge

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: lmsys/vicuna-7b-v1.5
    layer_range:
    - 0
    - 32
  - model: defog/sqlcoder-7b-2
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: lmsys/vicuna-7b-v1.5
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
Downloads last month
464
GGUF
Model size
7B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support