You can deploy this model and start earning money today!

RichardErkhov/
klcsp_-_mistral-7b-0.3-gpt4o_100k_summarize-fft-gguf

Name: klcsp_-_mistral-7b-0.3-gpt4o_100k_summarize-fft-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-7b-0.3-gpt4o_100k_summarize-fft - GGUF

Model creator: https://huggingface.co/klcsp/
Original model: https://huggingface.co/klcsp/mistral-7b-0.3-gpt4o_100k_summarize-fft/

Name	Quant method	Size
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q2_K.gguf	Q2_K	2.54GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.IQ3_XS.gguf	IQ3_XS	2.82GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.IQ3_S.gguf	IQ3_S	2.97GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q3_K_S.gguf	Q3_K_S	2.95GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.IQ3_M.gguf	IQ3_M	3.06GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q3_K.gguf	Q3_K	3.28GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q3_K_M.gguf	Q3_K_M	3.28GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q3_K_L.gguf	Q3_K_L	3.56GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.IQ4_XS.gguf	IQ4_XS	3.68GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q4_0.gguf	Q4_0	3.83GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.IQ4_NL.gguf	IQ4_NL	3.87GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q4_K_S.gguf	Q4_K_S	3.86GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q4_K.gguf	Q4_K	4.07GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q4_K_M.gguf	Q4_K_M	4.07GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q4_1.gguf	Q4_1	4.24GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q5_0.gguf	Q5_0	4.66GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q5_K_S.gguf	Q5_K_S	4.66GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q5_K.gguf	Q5_K	4.78GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q5_K_M.gguf	Q5_K_M	4.78GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q5_1.gguf	Q5_1	5.07GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q6_K.gguf	Q6_K	5.54GB
mistral-7b-0.3-gpt4o_100k_summarize-fft.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: apache-2.0 base_model: mistralai/Mistral-7B-v0.3 tags:

alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
llama-duo/synth_summarize_dataset_dedup model-index:
name: mistral-7b-0.3-gpt4o_100k_summarize-fft results: []

mistral-7b-0.3-gpt4o_100k_summarize-fft

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:

Loss: 7.1395

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 32
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
3.9549	1.0	438	7.1395

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0

RichardErkhov/klcsp_-_mistral-7b-0.3-gpt4o_100k_summarize-fft-gguf

Original model description:

mistral-7b-0.3-gpt4o_100k_summarize-fft

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
klcsp_-_mistral-7b-0.3-gpt4o_100k_summarize-fft-gguf