Instructions to use generalagents/tiny-mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use generalagents/tiny-mistral with Transformers:

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

pipe = pipeline("image-text-to-text", model="generalagents/tiny-mistral")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("generalagents/tiny-mistral")
model = AutoModelForImageTextToText.from_pretrained("generalagents/tiny-mistral")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use generalagents/tiny-mistral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "generalagents/tiny-mistral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "generalagents/tiny-mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/generalagents/tiny-mistral

SGLang

How to use generalagents/tiny-mistral 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 "generalagents/tiny-mistral" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "generalagents/tiny-mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "generalagents/tiny-mistral" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "generalagents/tiny-mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use generalagents/tiny-mistral with Docker Model Runner:
```
docker model run hf.co/generalagents/tiny-mistral
```

peiyuan-generalagents commited on Nov 21, 2025

Commit

e0cecfe

verified ·

1 Parent(s): b3874d6

Upload Mistral3ForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +46 -0
generation_config.json +6 -0
model.safetensors +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,46 @@

+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "projector_hidden_act": "gelu",
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 32,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 128,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 1,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": 2,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "transformers_version": "4.57.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "image_size": 1540,
+    "initializer_range": 0.02,
+    "intermediate_size": 128,
+    "model_type": "pixtral",
+    "num_attention_heads": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 14,
+    "rope_theta": 10000.0
+  },
+  "vision_feature_layer": -1
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.1"
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:13886fcc5327c5866842e51d14b48845fb3dd644c616aea8ec385d1ee2a5e2a9
+size 16964440