<![CDATA[==((====))== Unsloth 2025.2.15: Fast Qwen2 patching. Transformers: 4.48.3.
\\ /| GPU: Tesla T4. Max memory: 14.741 GB. Platform: Linux.
O^O/ \_/ \ Torch: 2.6.0+cu124. CUDA: 7.5. CUDA Toolkit: 12.4. Triton: 3.2.0
\ / Bfloat16 = FALSE. FA [Xformers = 0.0.29.post3. FA2 = False]
"-____-" Free Apache license: http://github.com/unslothai/unsloth
Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!
Unsloth: unsloth/qwen2.5-3b-bnb-4bit can only handle sequence lengths of at most 32768.
But with kaiokendev's RoPE scaling of 2.136, it can be magically be extended to 70000!
PeftModelForCausalLM(
(base_model): LoraModel(
(model): Qwen2ForCausalLM(
(model): Qwen2Model(
(embed_tokens): Embedding(151936, 2048, padding_idx=151654)
(layers): ModuleList(
(0-35): 36 x Qwen2DecoderLayer(
(self_attn): Qwen2Attention(
(q_proj): lora.Linear4bit(
(base_layer): Linear4bit(in_features=2048, out_features=2048, bias=True)
(lora_dropout): ModuleDict(
(default): Identity()
)
(lora_A): ModuleDict(
(default): Linear(in_features=2048, out_features=16, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=16, out_features=2048, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(lora_magnitude_vector): ModuleDict()
)
(k_proj): lora.Linear4bit(
(base_layer): Linear4bit(in_features=2048, out_features=256, bias=True)
(lora_dropout): ModuleDict(
(default): Identity()
)
(lora_A): ModuleDict(
(default): Linear(in_features=2048, out_features=16, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=16, out_features=256, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(lora_magnitude_vector): ModuleDict()
)
(v_proj): lora.Linear4bit(
(base_layer): Linear4bit(in_features=2048, out_features=256, bias=True)
(lora_dropout): ModuleDict(
(default): Identity()
)
(lora_A): ModuleDict(
(default): Linear(in_features=2048, out_features=16, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=16, out_features=256, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(lora_magnitude_vector): ModuleDict()
)
(o_proj): lora.Linear4bit(
(base_layer): Linear4bit(in_features=2048, out_features=2048, bias=False)
(lora_dropout): ModuleDict(
(default): Identity()
)
(lora_A): ModuleDict(
(default): Linear(in_features=2048, out_features=16, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=16, out_features=2048, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(lora_magnitude_vector): ModuleDict()
)
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): Qwen2MLP(
(gate_proj): lora.Linear4bit(
(base_layer): Linear4bit(in_features=2048, out_features=11008, bias=False)
(lora_dropout): ModuleDict(
(default): Identity()
)
(lora_A): ModuleDict(
(default): Linear(in_features=2048, out_features=16, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=16, out_features=11008, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(lora_magnitude_vector): ModuleDict()
)
(up_proj): lora.Linear4bit(
(base_layer): Linear4bit(in_features=2048, out_features=11008, bias=False)
(lora_dropout): ModuleDict(
(default): Identity()
)
(lora_A): ModuleDict(
(default): Linear(in_features=2048, out_features=16, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=16, out_features=11008, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(lora_magnitude_vector): ModuleDict()
)
(down_proj): lora.Linear4bit(
(base_layer): Linear4bit(in_features=11008, out_features=2048, bias=False)
(lora_dropout): ModuleDict(
(default): Identity()
)
(lora_A): ModuleDict(
(default): Linear(in_features=11008, out_features=16, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=16, out_features=2048, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(lora_magnitude_vector): ModuleDict()
)
(act_fn): SiLU()
)
(input_layernorm): Qwen2RMSNorm((2048,), eps=1e-06)
(post_attention_layernorm): Qwen2RMSNorm((2048,), eps=1e-06)
)
)
(norm): Qwen2RMSNorm((2048,), eps=1e-06)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=2048, out_features=151936, bias=False)
)
)
)]]>
