Instructions to use trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528 with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528 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-DeepseekV3ForCausalLM-0528"
# 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-DeepseekV3ForCausalLM-0528",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528

SGLang

How to use trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528 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-DeepseekV3ForCausalLM-0528" \
    --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-DeepseekV3ForCausalLM-0528",
		"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-DeepseekV3ForCausalLM-0528" \
        --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-DeepseekV3ForCausalLM-0528",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528 with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-DeepseekV3ForCausalLM-0528
```

Upload DeepseekV3ForCausalLM

by qgallouedec HF Staff - opened about 5 hours ago

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

+13

-7

Files changed (2) hide show

config.json +11 -5
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,7 +1,4 @@
 {
-  "architectures": [
-    "DeepseekV3ForCausalLM"
-  ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 0,
@@ -11,9 +8,9 @@
   "first_k_dense_replace": 3,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 8,
   "initializer_range": 0.02,
-  "intermediate_size": 32,
   "kv_lora_rank": 512,
   "max_position_embeddings": 163840,
   "model_type": "deepseek_v3",
@@ -33,6 +30,15 @@
   "qk_head_dim": 192,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
   "rms_norm_eps": 1e-06,
   "rope_interleave": true,
   "rope_scaling": {

 {
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "first_k_dense_replace": 3,
   "head_dim": 64,
   "hidden_act": "silu",
+  "hidden_size": 128,
   "initializer_range": 0.02,
+  "intermediate_size": 128,
   "kv_lora_rank": 512,
   "max_position_embeddings": 163840,
   "model_type": "deepseek_v3",
   "qk_head_dim": 192,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
   "rms_norm_eps": 1e-06,
   "rope_interleave": true,
   "rope_scaling": {

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14c16538a2f8c8dfc6ad56e03a17eaad6fa44957ecdfbf2bd6e06d73801eafa
-size 7634864

 version https://git-lfs.github.com/spec/v1
+oid sha256:aabcc745f97d1029745d467d62c6adb4643ed47b60c4506c0127836977db5224
+size 68614632