Quantization made by Richard Erkhov.
Novocode7b-v2 - GGUF
- Model creator: https://huggingface.co/NovoCode/
- Original model: https://huggingface.co/NovoCode/Novocode7b-v2/
Name | Quant method | Size |
---|---|---|
Novocode7b-v2.Q2_K.gguf | Q2_K | 2.53GB |
Novocode7b-v2.IQ3_XS.gguf | IQ3_XS | 2.81GB |
Novocode7b-v2.IQ3_S.gguf | IQ3_S | 2.96GB |
Novocode7b-v2.Q3_K_S.gguf | Q3_K_S | 2.95GB |
Novocode7b-v2.IQ3_M.gguf | IQ3_M | 3.06GB |
Novocode7b-v2.Q3_K.gguf | Q3_K | 3.28GB |
Novocode7b-v2.Q3_K_M.gguf | Q3_K_M | 3.28GB |
Novocode7b-v2.Q3_K_L.gguf | Q3_K_L | 3.56GB |
Novocode7b-v2.IQ4_XS.gguf | IQ4_XS | 3.67GB |
Novocode7b-v2.Q4_0.gguf | Q4_0 | 3.83GB |
Novocode7b-v2.IQ4_NL.gguf | IQ4_NL | 3.87GB |
Novocode7b-v2.Q4_K_S.gguf | Q4_K_S | 3.86GB |
Novocode7b-v2.Q4_K.gguf | Q4_K | 4.07GB |
Novocode7b-v2.Q4_K_M.gguf | Q4_K_M | 4.07GB |
Novocode7b-v2.Q4_1.gguf | Q4_1 | 4.24GB |
Novocode7b-v2.Q5_0.gguf | Q5_0 | 4.65GB |
Novocode7b-v2.Q5_K_S.gguf | Q5_K_S | 4.65GB |
Novocode7b-v2.Q5_K.gguf | Q5_K | 4.78GB |
Novocode7b-v2.Q5_K_M.gguf | Q5_K_M | 4.78GB |
Novocode7b-v2.Q5_1.gguf | Q5_1 | 5.07GB |
Novocode7b-v2.Q6_K.gguf | Q6_K | 5.53GB |
Novocode7b-v2.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0 tags: - generated_from_trainer model-index: - name: out results: []
See axolotl config
axolotl version: 0.3.0
base_model: out/
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: cognitivecomputations/leet10k-alpaca
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
out
This model was trained from scratch on the /leet10k-alpaca dataset. It achieves the following results on the evaluation set:
- Loss: 0.5907
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: 5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7842 | 0.01 | 1 | 0.8053 |
0.5057 | 0.26 | 35 | 0.5694 |
0.3987 | 0.51 | 70 | 0.5752 |
0.2964 | 0.77 | 105 | 0.5907 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 56.57 |
AI2 Reasoning Challenge (25-Shot) | 61.01 |
HellaSwag (10-Shot) | 84.12 |
MMLU (5-Shot) | 64.05 |
TruthfulQA (0-shot) | 42.21 |
Winogrande (5-shot) | 79.87 |
GSM8k (5-shot) | 8.19 |