Instructions to use qvac/TranslatePsy-AfriSLM-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qvac/TranslatePsy-AfriSLM-4B with Transformers:

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

pipe = pipeline("text-generation", model="qvac/TranslatePsy-AfriSLM-4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("qvac/TranslatePsy-AfriSLM-4B")
model = AutoModelForMultimodalLM.from_pretrained("qvac/TranslatePsy-AfriSLM-4B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use qvac/TranslatePsy-AfriSLM-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qvac/TranslatePsy-AfriSLM-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qvac/TranslatePsy-AfriSLM-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qvac/TranslatePsy-AfriSLM-4B

SGLang

How to use qvac/TranslatePsy-AfriSLM-4B 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 "qvac/TranslatePsy-AfriSLM-4B" \
    --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": "qvac/TranslatePsy-AfriSLM-4B",
		"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 "qvac/TranslatePsy-AfriSLM-4B" \
        --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": "qvac/TranslatePsy-AfriSLM-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qvac/TranslatePsy-AfriSLM-4B with Docker Model Runner:
```
docker model run hf.co/qvac/TranslatePsy-AfriSLM-4B
```

milangritta commited on Aug 20

Commit

3f97d4b

verified ·

1 Parent(s): cd621bf

Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

config.json +10 -18
generation_config.json +3 -1
model.safetensors +2 -2
preprocessor_config.json +21 -0
tokenizer.json +2 -2
tokenizer_config.json +1 -2
video_preprocessor_config.json +21 -0

config.json CHANGED Viewed

@@ -2,19 +2,14 @@
   "architectures": [
     "Qwen3_5ForConditionalGeneration"
   ],
-  "bos_token_id": null,
-  "dtype": "bfloat16",
-  "eos_token_id": 248046,
   "image_token_id": 248056,
   "model_type": "qwen3_5",
-  "pad_token_id": 248044,
   "text_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,
     "attn_output_gate": true,
-    "bos_token_id": null,
     "dtype": "bfloat16",
-    "eos_token_id": 248044,
     "full_attention_interval": 4,
     "head_dim": 256,
     "hidden_act": "silu",
@@ -69,8 +64,7 @@
     "num_attention_heads": 16,
     "num_hidden_layers": 32,
     "num_key_value_heads": 4,
-    "pad_token_id": null,
-    "partial_rotary_factor": 0.25,
     "rms_norm_eps": 1e-06,
     "rope_parameters": {
       "mrope_interleaved": true,
@@ -83,30 +77,28 @@
       "rope_theta": 10000000,
       "rope_type": "default"
     },
-    "tie_word_embeddings": true,
-    "use_cache": true,
     "vocab_size": 248320
   },
   "tie_word_embeddings": true,
-  "transformers_version": "5.4.0",
   "video_token_id": 248057,
   "vision_config": {
     "deepstack_visual_indexes": [],
-    "depth": 24,
-    "dtype": "bfloat16",
     "hidden_act": "gelu_pytorch_tanh",
-    "hidden_size": 1024,
     "in_channels": 3,
     "initializer_range": 0.02,
-    "intermediate_size": 4096,
     "model_type": "qwen3_5",
-    "num_heads": 16,
     "num_position_embeddings": 2304,
-    "out_hidden_size": 2560,
     "patch_size": 16,
     "spatial_merge_size": 2,
     "temporal_patch_size": 2
   },
   "vision_end_token_id": 248054,
   "vision_start_token_id": 248053
-}

   "architectures": [
     "Qwen3_5ForConditionalGeneration"
   ],
   "image_token_id": 248056,
   "model_type": "qwen3_5",
   "text_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,
     "attn_output_gate": true,
     "dtype": "bfloat16",
+    "eos_token_id": 248046,
     "full_attention_interval": 4,
     "head_dim": 256,
     "hidden_act": "silu",
     "num_attention_heads": 16,
     "num_hidden_layers": 32,
     "num_key_value_heads": 4,
+    "pad_token_id": 248044,
     "rms_norm_eps": 1e-06,
     "rope_parameters": {
       "mrope_interleaved": true,
       "rope_theta": 10000000,
       "rope_type": "default"
     },
+    "use_cache": false,
     "vocab_size": 248320
   },
   "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
   "video_token_id": 248057,
   "vision_config": {
     "deepstack_visual_indexes": [],
+    "depth": 12,
     "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
     "in_channels": 3,
     "initializer_range": 0.02,
+    "intermediate_size": 3072,
     "model_type": "qwen3_5",
+    "num_heads": 12,
     "num_position_embeddings": 2304,
+    "out_hidden_size": 1024,
     "patch_size": 16,
     "spatial_merge_size": 2,
     "temporal_patch_size": 2
   },
   "vision_end_token_id": 248054,
   "vision_start_token_id": 248053
+}

generation_config.json CHANGED Viewed

@@ -1,8 +1,10 @@
 {
   "eos_token_id": [
     248046,
     248044
   ],
-  "transformers_version": "5.4.0",
   "use_cache": true
 }

 {
+  "_from_model_config": true,
   "eos_token_id": [
     248046,
     248044
   ],
+  "pad_token_id": 248044,
+  "transformers_version": "5.8.1",
   "use_cache": true
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2e3539ea60d81e897f74a92ab0e294f5f58c22c9b88e365e5b5a6fda7d8a289
-size 10350017512

 version https://git-lfs.github.com/spec/v1
+oid sha256:fafce3903441b34d037206e0b5cde958afbe490bc6ce85c2dcad1a92e6b2bb6b
+size 9884159784

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
-size 19989343

 version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json CHANGED Viewed

@@ -23,9 +23,8 @@
   },
   "pad_token": "<|endoftext|>",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
-  "processor_class": "Qwen3VLProcessor",
   "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend",
   "unk_token": null,
   "video_token": "<|video_pad|>",
   "vision_bos_token": "<|vision_start|>",

   },
   "pad_token": "<|endoftext|>",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
   "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null,
   "video_token": "<|video_pad|>",
   "vision_bos_token": "<|vision_start|>",

video_preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}