Triangle104/Dumpling-Qwen2.5-1.5B-v2-Q5_K_M-GGUF

This model was converted to GGUF format from nbeerbower/Dumpling-Qwen2.5-1.5B-v2 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B finetuned on:

nbeerbower/GreatFirewall-DPO
nbeerbower/Schule-DPO
nbeerbower/Purpura-DPO
nbeerbower/Arkhaios-DPO
jondurbin/truthy-dpo-v0.1
antiven0m/physical-reasoning-dpo
flammenai/Date-DPO-NoAsterisks
flammenai/Prude-Phi3-DPO
Atsunori/HelpSteer2-DPO (1,000 samples)
jondurbin/gutenberg-dpo-v0.1
nbeerbower/gutenberg2-dpo
nbeerbower/gutenberg-moderne-dpo.

Method

QLoRA ORPO tune with 2x RTX 3090 for 2 epochs.

QLoRA config

bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch_dtype, bnb_4bit_use_double_quant=True, )

LoRA config

peft_config = LoraConfig( r=64, lora_alpha=64, lora_dropout=0.05, bias="none", task_type="CAUSAL_LM", target_modules=['up_proj', 'down_proj', 'gate_proj', 'k_proj', 'q_proj', 'v_proj', 'o_proj'] )

Training config

orpo_args = ORPOConfig( run_name=new_model, learning_rate=2e-5, lr_scheduler_type="linear", max_length=2048, max_prompt_length=1024, max_completion_length=1024, beta=0.1, per_device_train_batch_size=1, per_device_eval_batch_size=1, gradient_accumulation_steps=8, optim="paged_adamw_8bit", num_train_epochs=2, evaluation_strategy="steps", eval_steps=0.2, logging_steps=1, warmup_steps=10, max_grad_norm=10, report_to="wandb", output_dir="./results/", bf16=True, )

---

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/Dumpling-Qwen2.5-1.5B-v2-Q5_K_M-GGUF --hf-file dumpling-qwen2.5-1.5b-v2-q5_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Dumpling-Qwen2.5-1.5B-v2-Q5_K_M-GGUF --hf-file dumpling-qwen2.5-1.5b-v2-q5_k_m.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Triangle104/Dumpling-Qwen2.5-1.5B-v2-Q5_K_M-GGUF --hf-file dumpling-qwen2.5-1.5b-v2-q5_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Dumpling-Qwen2.5-1.5B-v2-Q5_K_M-GGUF --hf-file dumpling-qwen2.5-1.5b-v2-q5_k_m.gguf -c 2048