Instructions to use trl-internal-testing/tiny-DeepseekV4ForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-DeepseekV4ForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-DeepseekV4ForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-DeepseekV4ForCausalLM")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-DeepseekV4ForCausalLM")
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 trl-internal-testing/tiny-DeepseekV4ForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-DeepseekV4ForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-DeepseekV4ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-DeepseekV4ForCausalLM

SGLang

How to use trl-internal-testing/tiny-DeepseekV4ForCausalLM 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 "trl-internal-testing/tiny-DeepseekV4ForCausalLM" \
    --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": "trl-internal-testing/tiny-DeepseekV4ForCausalLM",
		"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 "trl-internal-testing/tiny-DeepseekV4ForCausalLM" \
        --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": "trl-internal-testing/tiny-DeepseekV4ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-DeepseekV4ForCausalLM with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-DeepseekV4ForCausalLM
```

qgallouedec HF Staff commited on 21 days ago

Commit

58f90bd

verified ·

1 Parent(s): db6aed2

Upload DeepseekV4ForCausalLM

Browse files

Files changed (2) hide show

config.json +7 -6
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -7,7 +7,8 @@
   "bos_token_id": 0,
   "compress_ratios": [
     0,
-    0
   ],
   "compress_rope_parameters": {
     "partial_rotary_factor": 0.125,
@@ -17,7 +18,7 @@
   "compress_rope_theta": 160000.0,
   "dtype": "bfloat16",
   "eos_token_id": 1,
-  "first_k_dense_replace": null,
   "hc_eps": 1e-06,
   "hc_mult": 4,
   "hc_sinkhorn_iters": 20,
@@ -34,13 +35,13 @@
   "model_type": "deepseek_v4",
   "moe_intermediate_size": 2048,
   "n_group": null,
-  "n_routed_experts": 256,
   "n_shared_experts": 1,
   "norm_topk_prob": true,
   "num_attention_heads": 4,
-  "num_experts_per_tok": 6,
-  "num_hash_layers": 3,
-  "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "num_nextn_predict_layers": 1,
   "o_groups": 8,

   "bos_token_id": 0,
   "compress_ratios": [
     0,
+    4,
+    128
   ],
   "compress_rope_parameters": {
     "partial_rotary_factor": 0.125,
   "compress_rope_theta": 160000.0,
   "dtype": "bfloat16",
   "eos_token_id": 1,
+  "first_k_dense_replace": 1,
   "hc_eps": 1e-06,
   "hc_mult": 4,
   "hc_sinkhorn_iters": 20,
   "model_type": "deepseek_v4",
   "moe_intermediate_size": 2048,
   "n_group": null,
+  "n_routed_experts": 4,
   "n_shared_experts": 1,
   "norm_topk_prob": true,
   "num_attention_heads": 4,
+  "num_experts_per_tok": 2,
+  "num_hash_layers": 2,
+  "num_hidden_layers": 3,
   "num_key_value_heads": 2,
   "num_nextn_predict_layers": 1,
   "o_groups": 8,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f6bf42b1d190e81a90dc7b9f30eaa4b3fa650313fe4785d26b4cb11bf7adef
-size 83997562

 version https://git-lfs.github.com/spec/v1
+oid sha256:e5c0682e334f5e114dc223c4196864ef67442228dcfe4eec24c953d386ecd5e6
+size 52073390