Instructions to use internlm/internlm2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use internlm/internlm2-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="internlm/internlm2-7b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-7b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use internlm/internlm2-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "internlm/internlm2-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "internlm/internlm2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/internlm/internlm2-7b
- SGLang
How to use internlm/internlm2-7b 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 "internlm/internlm2-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "internlm/internlm2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "internlm/internlm2-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "internlm/internlm2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use internlm/internlm2-7b with Docker Model Runner:
docker model run hf.co/internlm/internlm2-7b
x54-729 commited on
Commit ·
554cf12
1
Parent(s): 848badb
rename config to internlm2
Browse files- config.json +2 -2
- tokenizer_config.json +4 -4
config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"InternLM2ForCausalLM"
|
| 4 |
],
|
| 5 |
"auto_map": {
|
| 6 |
-
"AutoConfig": "
|
| 7 |
"AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
|
| 8 |
"AutoModel": "modeling_internlm2.InternLM2ForCausalLM"
|
| 9 |
},
|
|
@@ -15,7 +15,7 @@
|
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 14336,
|
| 17 |
"max_position_embeddings": 32768,
|
| 18 |
-
"model_type": "
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_hidden_layers": 32,
|
| 21 |
"num_key_value_heads": 8,
|
|
|
|
| 3 |
"InternLM2ForCausalLM"
|
| 4 |
],
|
| 5 |
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_internlm2.InternLM2Config",
|
| 7 |
"AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
|
| 8 |
"AutoModel": "modeling_internlm2.InternLM2ForCausalLM"
|
| 9 |
},
|
|
|
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 14336,
|
| 17 |
"max_position_embeddings": 32768,
|
| 18 |
+
"model_type": "internlm2",
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_hidden_layers": 32,
|
| 21 |
"num_key_value_heads": 8,
|
tokenizer_config.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"auto_map": {
|
| 3 |
"AutoTokenizer": [
|
| 4 |
-
"
|
| 5 |
-
|
| 6 |
]
|
| 7 |
},
|
| 8 |
"bos_token": "<s>",
|
|
@@ -10,6 +10,6 @@
|
|
| 10 |
"eos_token": "</s>",
|
| 11 |
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
"pad_token": "</s>",
|
| 13 |
-
"tokenizer_class": "
|
| 14 |
"unk_token": "<unk>"
|
| 15 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"auto_map": {
|
| 3 |
"AutoTokenizer": [
|
| 4 |
+
"tokenization_internlm2.InternLM2Tokenizer",
|
| 5 |
+
"tokenization_internlm2_fast.InternLM2TokenizerFast"
|
| 6 |
]
|
| 7 |
},
|
| 8 |
"bos_token": "<s>",
|
|
|
|
| 10 |
"eos_token": "</s>",
|
| 11 |
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
"pad_token": "</s>",
|
| 13 |
+
"tokenizer_class": "InternLM2Tokenizer",
|
| 14 |
"unk_token": "<unk>"
|
| 15 |
+
}
|