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
```

Upload DeepseekV4ForCausalLM

by qgallouedec HF Staff - opened Apr 24

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

+15

-4

Files changed (2) hide show

config.json +14 -3
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -12,9 +12,14 @@
     128
   ],
   "compress_rope_parameters": {
     "partial_rotary_factor": 0.125,
     "rope_theta": 160000.0,
-    "rope_type": "default"
   },
   "compress_rope_theta": 160000.0,
   "dtype": "bfloat16",
@@ -43,7 +48,7 @@
   "num_experts_per_tok": 2,
   "num_hash_layers": 3,
   "num_hidden_layers": 4,
-  "num_key_value_heads": 2,
   "num_nextn_predict_layers": 1,
   "o_groups": 8,
   "o_lora_rank": 1024,
@@ -57,9 +62,14 @@
   "rms_norm_eps": 1e-06,
   "rope_interleave": true,
   "rope_parameters": {
     "partial_rotary_factor": 0.125,
     "rope_theta": 10000.0,
-    "rope_type": "default"
   },
   "rope_theta": 10000.0,
   "routed_scaling_factor": 1.5,
@@ -70,6 +80,7 @@
   "swiglu_limit": 10.0,
   "tie_word_embeddings": false,
   "topk_group": null,
   "transformers_version": "5.7.0.dev0",
   "use_cache": true,
   "v_head_dim": null,

     128
   ],
   "compress_rope_parameters": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 16,
+    "original_max_position_embeddings": 65536,
     "partial_rotary_factor": 0.125,
     "rope_theta": 160000.0,
+    "rope_type": "yarn",
+    "type": "yarn"
   },
   "compress_rope_theta": 160000.0,
   "dtype": "bfloat16",
   "num_experts_per_tok": 2,
   "num_hash_layers": 3,
   "num_hidden_layers": 4,
+  "num_key_value_heads": 1,
   "num_nextn_predict_layers": 1,
   "o_groups": 8,
   "o_lora_rank": 1024,
   "rms_norm_eps": 1e-06,
   "rope_interleave": true,
   "rope_parameters": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 16,
+    "original_max_position_embeddings": 65536,
     "partial_rotary_factor": 0.125,
     "rope_theta": 10000.0,
+    "rope_type": "yarn",
+    "type": "yarn"
   },
   "rope_theta": 10000.0,
   "routed_scaling_factor": 1.5,
   "swiglu_limit": 10.0,
   "tie_word_embeddings": false,
   "topk_group": null,
+  "topk_method": "noaux_tc",
   "transformers_version": "5.7.0.dev0",
   "use_cache": true,
   "v_head_dim": null,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb246e5c57a24315997e93d55e759f78457690fe73efc19e5e58be0bb0f28a5
 size 37758460

 version https://git-lfs.github.com/spec/v1
+oid sha256:4076740c031a3b6670e03573ec7f9ea4095e54c5dde682ac8e2eb629572cd39c
 size 37758460