Instructions to use optimum-intel-internal-testing/tiny-random-gigachat3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use optimum-intel-internal-testing/tiny-random-gigachat3 with Transformers:

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

pipe = pipeline("text-generation", model="optimum-intel-internal-testing/tiny-random-gigachat3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("optimum-intel-internal-testing/tiny-random-gigachat3")
model = AutoModelForCausalLM.from_pretrained("optimum-intel-internal-testing/tiny-random-gigachat3")
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 optimum-intel-internal-testing/tiny-random-gigachat3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "optimum-intel-internal-testing/tiny-random-gigachat3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "optimum-intel-internal-testing/tiny-random-gigachat3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/optimum-intel-internal-testing/tiny-random-gigachat3

SGLang

How to use optimum-intel-internal-testing/tiny-random-gigachat3 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 "optimum-intel-internal-testing/tiny-random-gigachat3" \
    --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": "optimum-intel-internal-testing/tiny-random-gigachat3",
		"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 "optimum-intel-internal-testing/tiny-random-gigachat3" \
        --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": "optimum-intel-internal-testing/tiny-random-gigachat3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use optimum-intel-internal-testing/tiny-random-gigachat3 with Docker Model Runner:
```
docker model run hf.co/optimum-intel-internal-testing/tiny-random-gigachat3
```

mohamedahraf273 commited on Mar 5

Commit

c10a920

verified ·

1 Parent(s): 6f1aa1e

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

config.json +13 -14
generation_config.json +1 -1
model.safetensors +2 -2
tokenizer.json +2 -2

config.json CHANGED Viewed

@@ -9,30 +9,30 @@
   "eos_token_id": 2,
   "ep_size": 1,
   "first_k_dense_replace": 1,
-  "head_dim": 16,
   "hidden_act": "silu",
-  "hidden_size": 256,
   "initializer_range": 0.006,
-  "intermediate_size": 512,
-  "kv_lora_rank": 64,
   "max_position_embeddings": 262144,
   "model_type": "deepseek_v3",
-  "moe_intermediate_size": 256,
   "moe_layer_freq": 1,
   "n_group": 1,
   "n_routed_experts": 4,
   "n_shared_experts": 1,
   "norm_topk_prob": true,
-  "num_attention_heads": 4,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 2,
-  "num_key_value_heads": 4,
   "num_nextn_predict_layers": 1,
   "pretraining_tp": 1,
   "q_lora_rank": null,
-  "qk_head_dim": 48,
-  "qk_nope_head_dim": 32,
-  "qk_rope_head_dim": 16,
   "rms_norm_eps": 1e-06,
   "rope_interleave": true,
   "rope_scaling": {
@@ -51,9 +51,8 @@
   "tie_word_embeddings": false,
   "topk_group": 1,
   "topk_method": "noaux_tc",
-  "torch_dtype": "float32",
-  "transformers_version": "4.53.3",
   "use_cache": true,
-  "v_head_dim": 32,
-  "vocab_size": 128256
 }

   "eos_token_id": 2,
   "ep_size": 1,
   "first_k_dense_replace": 1,
+  "head_dim": 2,
   "hidden_act": "silu",
+  "hidden_size": 32,
   "initializer_range": 0.006,
+  "intermediate_size": 64,
+  "kv_lora_rank": 8,
   "max_position_embeddings": 262144,
   "model_type": "deepseek_v3",
+  "moe_intermediate_size": 32,
   "moe_layer_freq": 1,
   "n_group": 1,
   "n_routed_experts": 4,
   "n_shared_experts": 1,
   "norm_topk_prob": true,
+  "num_attention_heads": 2,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
   "num_nextn_predict_layers": 1,
   "pretraining_tp": 1,
   "q_lora_rank": null,
+  "qk_head_dim": 6,
+  "qk_nope_head_dim": 4,
+  "qk_rope_head_dim": 2,
   "rms_norm_eps": 1e-06,
   "rope_interleave": true,
   "rope_scaling": {
   "tie_word_embeddings": false,
   "topk_group": 1,
   "topk_method": "noaux_tc",
+  "transformers_version": "4.57.6",
   "use_cache": true,
+  "v_head_dim": 4,
+  "vocab_size": 32000
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.53.3"
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "transformers_version": "4.57.6"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632aadf26d1207997826637896a4d61bfb3c68a1658d51ba9bc59927b2abaf9e
-size 269137576

 version https://git-lfs.github.com/spec/v1
+oid sha256:4849d415de47276e86a8a8e094fd22d511a27fe17a4d0f927620df3629fbf63d
+size 4148048

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fdb3c045850a565109244ef3b89475cc2582769417647a41c46da14a3782aa5
-size 10680605

 version https://git-lfs.github.com/spec/v1
+oid sha256:6c28a86aef25706f0664c264e436b8ff99d29187ea70ebb291097307400c3cb5
+size 673497