🥷 Safurai-Csharp-34B

This is a codellama/CodeLlama-34b-hf model fine-tuned using QLoRA (4-bit precision) on 13B tokens of csharp evolved Q&A

We obtained state-of-the-art performance on the MultiPL-E code LLM benchmark for csharp, reaching 56% at pass@1 with n=5.

💻 Quantization

These are GGUF quantized versions of Safurai-Csharp-34B, it has been made by using the amazing llama.cpp library.

🔧 Training

It was trained on 2 x NVIDIA A100 PCIe 80GB in 7h 40m with the following configuration file:

base_model: codellama/CodeLlama-34b-hf
base_model_config: codellama/CodeLlama-34b-hf
model_type: LlamaForCausalLM
tokenizer_type: CodeLlamaTokenizer
is_llama_derived_model: true
hub_model_id: "Safurai/Evol-csharp-v1"

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: Safurai/EvolInstruct-csharp-16k-13B-Alpaca
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: ./qlora-out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: codellama-csharp
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0003

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: 40
eval_steps: 40
save_steps:
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

📉 Training loss curve:

📊 Dataset composition:

💻 Usage for GGUF

# disclaimer: you have to use the llama.gguf library to run this code

import os

model_list = [file for file in os.listdir(MODEL_NAME) if GGML_VERSION in file]

prompt = input("Enter your prompt: ")
chosen_method = input("Please specify the quantization method to run the model (options: " + ", ".join(model_list) + "): ")

# Verify the chosen method is in the list
if chosen_method not in model_list:
    print("Invalid method chosen!")
else:
    qtype = f"{MODEL_NAME}/{MODEL_NAME.lower()}.{GGML_VERSION}.{method}.bin"
    !./llama.cpp/main -m {qtype} -n 128 --color -ngl 35 -p "{prompt}"