Instructions to use deepseek-ai/ESFT-token-code-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/ESFT-token-code-lite with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/ESFT-token-code-lite", 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("deepseek-ai/ESFT-token-code-lite", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/ESFT-token-code-lite", 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 deepseek-ai/ESFT-token-code-lite with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/deepseek-ai/ESFT-token-code-lite

SGLang

How to use deepseek-ai/ESFT-token-code-lite 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 "deepseek-ai/ESFT-token-code-lite" \
    --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": "deepseek-ai/ESFT-token-code-lite",
		"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 "deepseek-ai/ESFT-token-code-lite" \
        --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": "deepseek-ai/ESFT-token-code-lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/ESFT-token-code-lite with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/ESFT-token-code-lite
```

ESFT-token-code-lite / config.json

ZihanWang314

Upload folder using huggingface_hub

71cd39e verified almost 2 years ago

raw

history blame contribute delete

1.36 kB

	{
	"architectures": [
	"DeepseekV2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_deepseek.DeepseekV2Config",
	"AutoModel": "modeling_deepseek.DeepseekV2Model",
	"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
	},
	"aux_loss_alpha": 0.001,
	"bos_token_id": 100000,
	"eos_token_id": 100001,
	"ep_size": 1,
	"first_k_dense_replace": 1,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 10944,
	"kv_lora_rank": 512,
	"max_position_embeddings": 4096,
	"model_type": "deepseek_v2",
	"moe_intermediate_size": 1408,
	"moe_layer_freq": 1,
	"n_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 2,
	"norm_topk_prob": false,
	"num_attention_heads": 16,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 27,
	"num_key_value_heads": 16,
	"pretraining_tp": 1,
	"q_lora_rank": null,
	"qk_nope_head_dim": 128,
	"qk_rope_head_dim": 64,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 10000,
	"routed_scaling_factor": 1.0,
	"scoring_func": "softmax",
	"seq_aux": true,
	"tie_word_embeddings": false,
	"topk_group": 1,
	"topk_method": "greedy",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.42.3",
	"use_cache": true,
	"v_head_dim": 128,
	"vocab_size": 102400
	}