PharMolix

/

BioMedGPT-LM-7B

like 84

Follow

PharMolix 37

I tried to load the model via the above code, it shows:

Some weights of LlamaForCausalLM were not initialized from the model checkpoint at /content/drive/MyDrive/mimic/BioMedGPT-LM-7B and are newly initialized: ['model.layers.13.mlp.down_proj.weight', 'model.layers.7.self_attn.q_proj.weight', 'model.layers.13.self_attn.k_proj.weight', 'model.layers.10.self_attn.k_proj.weight', 'model.layers.0.post_attention_layernorm.weight', 'model.layers.22.self_attn.v_proj.weight', 'model.layers.11.self_attn.v_proj.weight', 'model.layers.3.self_attn.k_proj.weight', 'model.layers.16.input_layernorm.weight', 'model.layers.17.self_attn.o_proj.weight', 'model.layers.6.self_attn.o_proj.weight', 'model.layers.0.self_attn.k_proj.weight', 'model.layers.4.self_attn.o_proj.weight', 'model.layers.7.self_attn.o_proj.weight', 'model.layers.9.self_attn.k_proj.weight', 'model.layers.1.mlp.up_proj.weight', 'model.layers.15.self_attn.v_proj.weight', 'model.layers.1.self_attn.q_proj.weight', 'model.layers.19.mlp.gate_proj.weight', 'model.layers.17.mlp.gate_proj.weight', 'model.layers.2.self_attn.q_proj.weight', 'model.embed_tokens.weight', 'model.layers.18.mlp.up_proj.weight', 'model.layers.9.self_attn.q_proj.weight', 'model.layers.19.self_attn.o_proj.weight', 'model.layers.20.self_attn.q_proj.weight', 'model.layers.16.self_attn.v_proj.weight', 'model.layers.20.self_attn.k_proj.weight', 'model.layers.14.post_attention_layernorm.weight', 'model.layers.20.self_attn.o_proj.weight', 'model.layers.18.self_attn.q_proj.weight', 'model.layers.12.input_layernorm.weight', 'model.layers.22.mlp.up_proj.weight', 'model.layers.23.self_attn.o_proj.weight', 'model.layers.23.mlp.down_proj.weight', 'model.layers.9.post_attention_layernorm.weight', 'model.layers.6.post_attention_layernorm.weight', 'model.layers.0.self_attn.v_proj.weight', 'model.layers.21.mlp.down_proj.weight', 'model.layers.3.post_attention_layernorm.weight', 'model.layers.7.self_attn.k_proj.weight', 'model.layers.7.mlp.up_proj.weight', 'model.layers.21.mlp.up_proj.weight', 'model.layers.7.mlp.gate_proj.weight', 'model.layers.9.mlp.up_proj.weight', 'model.layers.7.input_layernorm.weight', 'model.layers.15.mlp.up_proj.weight', 'model.layers.8.self_attn.q_proj.weight', 'model.layers.17.post_attention_layernorm.weight', 'model.layers.13.self_attn.q_proj.weight', 'model.layers.14.self_attn.k_proj.weight', 'model.layers.4.mlp.gate_proj.weight', 'model.layers.6.mlp.gate_proj.weight', 'model.layers.6.self_attn.q_proj.weight', 'model.layers.8.mlp.up_proj.weight', 'model.layers.21.self_attn.q_proj.weight', 'model.layers.12.self_attn.q_proj.weight', 'model.layers.4.input_layernorm.weight', 'model.layers.11.mlp.gate_proj.weight', 'model.layers.2.input_layernorm.weight', 'model.layers.18.post_attention_layernorm.weight', 'model.layers.17.self_attn.q_proj.weight', 'model.layers.20.mlp.gate_proj.weight', 'model.layers.0.input_layernorm.weight', 'model.layers.23.self_attn.q_proj.weight', 'model.layers.18.mlp.down_proj.weight', 'model.layers.5.self_attn.q_proj.weight', 'model.layers.0.mlp.up_proj.weight', 'model.layers.9.self_attn.o_proj.weight', 'model.layers.1.input_layernorm.weight', 'model.layers.0.mlp.down_proj.weight', 'model.layers.5.mlp.down_proj.weight', 'model.layers.7.mlp.down_proj.weight', 'model.layers.17.input_layernorm.weight', 'model.layers.8.mlp.gate_proj.weight', 'model.layers.16.self_attn.q_proj.weight', 'model.layers.4.mlp.up_proj.weight', 'model.layers.19.mlp.down_proj.weight', 'model.layers.9.mlp.down_proj.weight', 'model.layers.2.self_attn.v_proj.weight', 'model.layers.11.input_layernorm.weight', 'model.layers.19.mlp.up_proj.weight', 'model.layers.22.mlp.down_proj.weight', 'model.layers.2.mlp.down_proj.weight', 'model.layers.4.mlp.down_proj.weight', 'model.layers.4.self_attn.k_proj.weight', 'model.layers.6.mlp.down_proj.weight', 'model.layers.10.post_attention_layernorm.weight', 'model.layers.6.mlp.up_proj.weight', 'model.layers.17.mlp.down_proj.weight', 'model.layers.12.mlp.down_proj.weight', 'model.layers.14.mlp.up_proj.weight', 'model.layers.14.mlp.down_proj.weight', 'model.layers.21.post_attention_layernorm.weight', 'model.layers.0.mlp.gate_proj.weight', 'model.layers.2.self_attn.o_proj.weight', 'model.layers.10.mlp.up_proj.weight', 'model.layers.2.mlp.gate_proj.weight', 'model.layers.12.post_attention_layernorm.weight', 'model.layers.18.self_attn.k_proj.weight', 'model.layers.11.mlp.up_proj.weight', 'model.layers.3.mlp.down_proj.weight', 'model.layers.12.self_attn.o_proj.weight', 'model.layers.20.input_layernorm.weight', 'model.layers.18.self_attn.v_proj.weight', 'model.layers.2.post_attention_layernorm.weight', 'model.layers.15.self_attn.q_proj.weight', 'model.layers.16.post_attention_layernorm.weight', 'model.layers.21.self_attn.o_proj.weight', 'model.layers.19.self_attn.q_proj.weight', 'model.layers.19.self_attn.k_proj.weight', 'model.layers.14.mlp.gate_proj.weight', 'model.layers.15.self_attn.o_proj.weight', 'model.layers.22.post_attention_layernorm.weight', 'model.layers.14.self_attn.q_proj.weight', 'model.layers.6.self_attn.v_proj.weight', 'model.layers.23.self_attn.v_proj.weight', 'model.layers.10.input_layernorm.weight', 'model.layers.22.self_attn.o_proj.weight', 'model.layers.11.post_attention_layernorm.weight', 'model.layers.2.self_attn.k_proj.weight', 'model.layers.12.mlp.gate_proj.weight', 'model.layers.11.self_attn.q_proj.weight', 'model.layers.4.self_attn.q_proj.weight', 'model.layers.9.mlp.gate_proj.weight', 'model.layers.16.mlp.down_proj.weight', 'model.layers.20.self_attn.v_proj.weight', 'model.layers.22.self_attn.k_proj.weight', 'model.layers.13.self_attn.o_proj.weight', 'model.layers.1.self_attn.k_proj.weight', 'model.layers.3.mlp.gate_proj.weight', 'model.layers.3.input_layernorm.weight', 'model.layers.8.post_attention_layernorm.weight', 'model.layers.19.input_layernorm.weight', 'model.layers.21.input_layernorm.weight', 'model.layers.0.self_attn.o_proj.weight', 'model.layers.14.input_layernorm.weight', 'model.layers.10.mlp.down_proj.weight', 'model.layers.19.self_attn.v_proj.weight', 'model.layers.5.self_attn.v_proj.weight', 'model.layers.20.mlp.down_proj.weight', 'model.layers.6.self_attn.k_proj.weight', 'model.layers.23.mlp.gate_proj.weight', 'model.layers.21.self_attn.v_proj.weight', 'model.layers.15.self_attn.k_proj.weight', 'model.layers.4.post_attention_layernorm.weight', 'model.layers.5.mlp.up_proj.weight', 'model.layers.20.post_attention_layernorm.weight', 'model.layers.15.mlp.gate_proj.weight', 'model.layers.3.mlp.up_proj.weight', 'model.layers.15.mlp.down_proj.weight', 'model.layers.1.self_attn.v_proj.weight', 'model.layers.2.mlp.up_proj.weight', 'model.layers.21.mlp.gate_proj.weight', 'model.layers.11.self_attn.k_proj.weight', 'model.layers.16.mlp.gate_proj.weight', 'model.layers.5.mlp.gate_proj.weight', 'model.layers.4.self_attn.v_proj.weight', 'model.layers.1.mlp.down_proj.weight', 'model.layers.3.self_attn.o_proj.weight', 'model.layers.16.self_attn.k_proj.weight', 'model.layers.18.input_layernorm.weight', 'model.layers.5.self_attn.k_proj.weight', 'model.layers.17.self_attn.k_proj.weight', 'model.layers.19.post_attention_layernorm.weight', 'model.layers.5.post_attention_layernorm.weight', 'model.layers.1.mlp.gate_proj.weight', 'model.layers.23.self_attn.k_proj.weight', 'model.layers.0.self_attn.q_proj.weight', 'model.layers.9.self_attn.v_proj.weight', 'model.layers.1.self_attn.o_proj.weight', 'model.layers.8.mlp.down_proj.weight', 'model.layers.22.mlp.gate_proj.weight', 'model.layers.6.input_layernorm.weight', 'model.layers.11.self_attn.o_proj.weight', 'model.layers.12.self_attn.v_proj.weight', 'model.layers.5.self_attn.o_proj.weight', 'model.layers.13.mlp.gate_proj.weight', 'model.layers.17.self_attn.v_proj.weight', 'model.layers.10.self_attn.q_proj.weight', 'model.layers.11.mlp.down_proj.weight', 'model.layers.12.mlp.up_proj.weight', 'model.layers.13.self_attn.v_proj.weight', 'model.layers.13.input_layernorm.weight', 'model.layers.8.self_attn.k_proj.weight', 'model.layers.13.mlp.up_proj.weight', 'model.layers.10.mlp.gate_proj.weight', 'model.layers.7.self_attn.v_proj.weight', 'model.layers.5.input_layernorm.weight', 'model.layers.22.self_attn.q_proj.weight', 'model.layers.3.self_attn.q_proj.weight', 'model.layers.16.mlp.up_proj.weight', 'model.layers.3.self_attn.v_proj.weight', 'model.layers.18.self_attn.o_proj.weight', 'model.layers.20.mlp.up_proj.weight', 'model.layers.10.self_attn.v_proj.weight', 'model.layers.17.mlp.up_proj.weight', 'model.layers.21.self_attn.k_proj.weight', 'model.layers.15.input_layernorm.weight', 'model.layers.22.input_layernorm.weight', 'model.layers.12.self_attn.k_proj.weight', 'model.layers.14.self_attn.v_proj.weight', 'model.layers.18.mlp.gate_proj.weight', 'model.layers.16.self_attn.o_proj.weight', 'model.layers.10.self_attn.o_proj.weight', 'model.layers.8.self_attn.v_proj.weight', 'model.layers.14.self_attn.o_proj.weight', 'model.layers.8.input_layernorm.weight', 'model.layers.9.input_layernorm.weight', 'model.layers.8.self_attn.o_proj.weight', 'model.layers.1.post_attention_layernorm.weight', 'model.layers.15.post_attention_layernorm.weight', 'model.layers.7.post_attention_layernorm.weight', 'model.layers.13.post_attention_layernorm.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

Hi, Did you successfully run it?

I am also having issues doing inference on this model. I am trying to follow llama2 prompting as much as possible but getting errors/exception when I call generate.

model = AutoModelForCausalLM.from_pretrained(
                "PharMolix/BioMedGPT-LM-7B", device_map="auto", torch_dtype=torch.float32
            )
tokenizer = AutoTokenizer.from_pretrained("PharMolix/BioMedGPT-LM-7B")

message = """
            <s>[INST] <<SYS>>
            {{ system_prompt }}
            <</SYS>>

            {{ user_message }} [/INST]
            """.format(system_prompt="You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.", user_message=input)
model_inputs = tokenizer(message, return_tensors="pt").to(self.model.device)
with torch.no_grad():
    result = model.generate(model_inputs, max_new_tokens=max_new_tokens, do_sample=False, return_dict_in_generate=True, output_scores=True)
response = tokenizer.decode(result.sequences[0, model_inputs.shape[1]:], skip_special_tokens=True)

I was able to get this work using torch_dtype=torch.float16 and passing the input_ids to the model.generate() function.

I'm new to inferencing, how do I deploy to azure ml?