Instructions to use openbmb/BitCPM-CANN-3B-unquantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/BitCPM-CANN-3B-unquantized with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="openbmb/BitCPM-CANN-3B-unquantized", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openbmb/BitCPM-CANN-3B-unquantized", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("openbmb/BitCPM-CANN-3B-unquantized", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openbmb/BitCPM-CANN-3B-unquantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/BitCPM-CANN-3B-unquantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/BitCPM-CANN-3B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/BitCPM-CANN-3B-unquantized

SGLang

How to use openbmb/BitCPM-CANN-3B-unquantized with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "openbmb/BitCPM-CANN-3B-unquantized" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/BitCPM-CANN-3B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "openbmb/BitCPM-CANN-3B-unquantized" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/BitCPM-CANN-3B-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/BitCPM-CANN-3B-unquantized with Docker Model Runner:
```
docker model run hf.co/openbmb/BitCPM-CANN-3B-unquantized
```

guanwenyu1995 commited on 3 days ago

Commit

3f9e06f

verified ·

1 Parent(s): 10ea506

Upload configuration_llama.py with huggingface_hub

Browse files

Files changed (1) hide show

configuration_llama.py +5 -24

configuration_llama.py CHANGED Viewed

@@ -28,7 +28,6 @@ class LlamaConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`LlamaModel`]. It is used to instantiate an LLaMA
     model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
     defaults will yield a similar configuration to that of the LLaMA-7B.
-    e.g. [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
@@ -51,8 +50,8 @@ class LlamaConfig(PretrainedConfig):
             `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
             `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
             converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
-            by meanpooling all the original heads within that group. For more details, check out [this
-            paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
             `num_attention_heads`.
         hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
             The non-linear activation function (function or string) in the decoder.
@@ -106,11 +105,11 @@ class LlamaConfig(PretrainedConfig):
                 `beta_slow` (`float`, *optional*):
                     Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
                     ramp function. If unspecified, it defaults to 1.
-                `short_factor` (`list[float]`, *optional*):
                     Only used with 'longrope'. The scaling factor to be applied to short contexts (<
                     `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                     size divided by the number of attention heads divided by 2
-                `long_factor` (`list[float]`, *optional*):
                     Only used with 'longrope'. The scaling factor to be applied to long contexts (<
                     `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                     size divided by the number of attention heads divided by 2
@@ -125,7 +124,7 @@ class LlamaConfig(PretrainedConfig):
         mlp_bias (`bool`, *optional*, defaults to `False`):
             Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.
         head_dim (`int`, *optional*):
-            The attention head dimension. If None, it will default to hidden_size // num_attention_heads
     ```python
     >>> from transformers import LlamaModel, LlamaConfig
@@ -142,21 +141,6 @@ class LlamaConfig(PretrainedConfig):
     model_type = "llama"
     keys_to_ignore_at_inference = ["past_key_values"]
-    # Default tensor parallel plan for base model `LlamaModel`
-    base_model_tp_plan = {
-        "layers.*.self_attn.q_proj": "colwise",
-        "layers.*.self_attn.k_proj": "colwise",
-        "layers.*.self_attn.v_proj": "colwise",
-        "layers.*.self_attn.o_proj": "rowwise",
-        "layers.*.mlp.gate_proj": "colwise",
-        "layers.*.mlp.up_proj": "colwise",
-        "layers.*.mlp.down_proj": "rowwise",
-    }
-    base_model_pp_plan = {
-        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
-        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
-        "norm": (["hidden_states"], ["hidden_states"]),
-    }
     def __init__(
         self,
@@ -220,6 +204,3 @@ class LlamaConfig(PretrainedConfig):
             tie_word_embeddings=tie_word_embeddings,
             **kwargs,
         )
-__all__ = ["LlamaConfig"]

     This is the configuration class to store the configuration of a [`LlamaModel`]. It is used to instantiate an LLaMA
     model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
     defaults will yield a similar configuration to that of the LLaMA-7B.
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
             `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
             `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
             converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
             `num_attention_heads`.
         hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
             The non-linear activation function (function or string) in the decoder.
                 `beta_slow` (`float`, *optional*):
                     Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
                     ramp function. If unspecified, it defaults to 1.
+                `short_factor` (`List[float]`, *optional*):
                     Only used with 'longrope'. The scaling factor to be applied to short contexts (<
                     `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                     size divided by the number of attention heads divided by 2
+                `long_factor` (`List[float]`, *optional*):
                     Only used with 'longrope'. The scaling factor to be applied to long contexts (<
                     `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                     size divided by the number of attention heads divided by 2
         mlp_bias (`bool`, *optional*, defaults to `False`):
             Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.
         head_dim (`int`, *optional*):
+            The attention head dimension. If None, it will default to hidden_size // num_heads
     ```python
     >>> from transformers import LlamaModel, LlamaConfig
     model_type = "llama"
     keys_to_ignore_at_inference = ["past_key_values"]
     def __init__(
         self,
             tie_word_embeddings=tie_word_embeddings,
             **kwargs,
         )