You can deploy this model and start earning money today!

RichardErkhov/
Nondzu_-_Mistral-7B-codealpaca-lora-gguf

Name: Nondzu_-_Mistral-7B-codealpaca-lora-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-codealpaca-lora - GGUF

Model creator: https://huggingface.co/Nondzu/
Original model: https://huggingface.co/Nondzu/Mistral-7B-codealpaca-lora/

Name	Quant method	Size
Mistral-7B-codealpaca-lora.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-codealpaca-lora.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-codealpaca-lora.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-codealpaca-lora.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-codealpaca-lora.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-codealpaca-lora.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-codealpaca-lora.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-codealpaca-lora.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-codealpaca-lora.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-codealpaca-lora.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-codealpaca-lora.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-codealpaca-lora.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-codealpaca-lora.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-codealpaca-lora.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-codealpaca-lora.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-codealpaca-lora.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-codealpaca-lora.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-codealpaca-lora.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-codealpaca-lora.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-codealpaca-lora.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-codealpaca-lora.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-codealpaca-lora.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 tags:

code
mistral

Mistral-7B-codealpaca

I am thrilled to introduce my Mistral-7B-codealpaca model. This variant is optimized and demonstrates potential in assisting developers as a coding companion. I welcome contributions from testers and enthusiasts to help evaluate its performance.

Training Details

I trained the model using 3xRTX 3090 for 118 hours.

Quantised Model Links:

Download by qBittorrent:

Torrent file: https://github.com/Nondzu/LlamaTor/blob/torrents/torrents/Nondzu_Mistral-7B-codealpaca-lora.torrent

Dataset:

Dataset Name: theblackcat102/evol-codealpaca-v1
Dataset Link: theblackcat102/evol-codealpaca-v1

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Performance (evalplus)

Human eval plus: https://github.com/evalplus/evalplus

Well, the results are better than I expected:

Base: {'pass@1': 0.47560975609756095}
Base + Extra: {'pass@1': 0.4329268292682927}

For reference, I've provided the performance of the original Mistral model alongside my Mistral-7B-code-16k-qlora model.

** Nondzu/Mistral-7B-code-16k-qlora**:

Base: {'pass@1': 0.3353658536585366}
Base + Extra: {'pass@1': 0.2804878048780488}

** mistralai/Mistral-7B-Instruct-v0.1**:

Base: {'pass@1': 0.2926829268292683}
Base + Extra: {'pass@1': 0.24390243902439024}

Model Configuration:

Here are the configurations for my Mistral-7B-codealpaca-lora:

yaml

base_model: mistralai/Mistral-7B-Instruct-v0.1
base_model_config: mistralai/Mistral-7B-Instruct-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
  - path: theblackcat102/evol-codealpaca-v1
    type: oasst
dataset_prepared_path:
val_set_size: 0.01
output_dir: ./nondzu/Mistral-7B-codealpaca-test14
adapter: lora
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true

Additional Projects:

For other related projects, you can check out:

LlamaTor on GitHub

RichardErkhov/Nondzu_-_Mistral-7B-codealpaca-lora-gguf