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)

# 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")
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-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 14 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+34

-11

Files changed (3) hide show

config.json +31 -8
generation_config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -7,16 +7,18 @@
   "bos_token_id": 0,
   "dtype": "bfloat16",
   "eos_token_id": 1,
   "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": 4096,
   "model_type": "deepseek_v3",
   "moe_intermediate_size": 2048,
   "n_group": 8,
   "n_routed_experts": 256,
   "n_shared_experts": 1,
@@ -25,20 +27,41 @@
   "num_experts_per_tok": 8,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "pretraining_tp": 1,
-  "q_lora_rank": 1536,
   "qk_head_dim": 192,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
   "rms_norm_eps": 1e-06,
   "rope_interleave": true,
-  "rope_scaling": null,
   "rope_theta": 10000.0,
   "routed_scaling_factor": 2.5,
   "tie_word_embeddings": false,
   "topk_group": 4,
-  "transformers_version": "4.57.3",
   "use_cache": true,
   "v_head_dim": 128,
-  "vocab_size": 128815
 }

   "bos_token_id": 0,
   "dtype": "bfloat16",
   "eos_token_id": 1,
+  "ep_size": 1,
   "first_k_dense_replace": 3,
   "head_dim": 64,
   "hidden_act": "silu",
+  "hidden_size": 128,
   "initializer_range": 0.02,
+  "intermediate_size": 128,
+  "kv_lora_rank": 128,
+  "max_position_embeddings": 163840,
   "model_type": "deepseek_v3",
   "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
   "n_group": 8,
   "n_routed_experts": 256,
   "n_shared_experts": 1,
   "num_experts_per_tok": 8,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
+  "num_nextn_predict_layers": 1,
   "pretraining_tp": 1,
+  "q_lora_rank": 128,
   "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": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 40.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
   "rope_theta": 10000.0,
   "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
   "tie_word_embeddings": false,
   "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "transformers_version": "4.56.2",
   "use_cache": true,
   "v_head_dim": 128,
+  "vocab_size": 129280
 }

generation_config.json CHANGED Viewed

@@ -5,5 +5,5 @@
   "eos_token_id": 1,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.57.3"
 }

   "eos_token_id": 1,
   "temperature": 0.6,
   "top_p": 0.95,
+  "transformers_version": "4.56.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d811212ee31acf7be29b2188fa9d8f16bf99919e1b071474b5ab96cfe6cb7a62
-size 11036056

 version https://git-lfs.github.com/spec/v1
+oid sha256:c151d7a9bc82a83de81dae611ec26e839aae67f878a89130440870632f95c337
+size 66968648