Instructions to use Flyoz/asr2_ru with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Flyoz/asr2_ru with Transformers:

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

pipe = pipeline("text-generation", model="Flyoz/asr2_ru")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Flyoz/asr2_ru")
model = AutoModelForCausalLM.from_pretrained("Flyoz/asr2_ru", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Flyoz/asr2_ru with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Flyoz/asr2_ru"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Flyoz/asr2_ru",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Flyoz/asr2_ru

SGLang

How to use Flyoz/asr2_ru 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 "Flyoz/asr2_ru" \
    --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": "Flyoz/asr2_ru",
		"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 "Flyoz/asr2_ru" \
        --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": "Flyoz/asr2_ru",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Flyoz/asr2_ru with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Flyoz/asr2_ru to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Flyoz/asr2_ru to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Flyoz/asr2_ru to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Flyoz/asr2_ru",
    max_seq_length=2048,
)

Docker Model Runner
How to use Flyoz/asr2_ru with Docker Model Runner:
```
docker model run hf.co/Flyoz/asr2_ru
```

Flyoz commited on Jul 8, 2025

Commit

4be2e06

verified ·

1 Parent(s): f453e6d

(Trained with Unsloth)

Browse files

Files changed (6) hide show

chat_template.jinja +5 -15
config.json +2 -2
generation_config.json +1 -1
special_tokens_map.json +21 -3
tokenizer.json +1 -1
tokenizer_config.json +10 -6

chat_template.jinja CHANGED Viewed

@@ -1,15 +1,5 @@
-{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user
-' + message['content'] + '<|im_end|>
-'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant
-' + message['content'] + '<|im_end|>
-' }}{% else %}{{ '<|im_start|>system
-' + message['content'] + '<|im_end|>
-' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user
-' + message['value'] + '<|im_end|>
-'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant
-' + message['value'] + '<|im_end|>
-' }}{% else %}{{ '<|im_start|>system
-' + message['value'] + '<|im_end|>
-' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}{% endif %}

+{{ bos_token }}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+'+ message['content'] | trim + '<|eot_id|>' %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+' }}{% endif %}

config.json CHANGED Viewed

@@ -34,8 +34,8 @@
     "rope_theta": 500000.0,
     "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
-    "transformers_version": "4.52.4",
-    "unsloth_version": "2025.6.2",
     "use_cache": true,
     "vocab_size": 128256
 }

     "rope_theta": 500000.0,
     "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
+    "transformers_version": "4.53.1",
+    "unsloth_version": "2025.6.12",
     "use_cache": true,
     "vocab_size": 128256
 }

generation_config.json CHANGED Viewed

@@ -10,5 +10,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.52.4"
 }

   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.53.1"
 }

special_tokens_map.json CHANGED Viewed

@@ -1,5 +1,23 @@
 {
-  "bos_token": "<|begin_of_text|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|reserved_special_token_0|>"
 }

 {
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|reserved_special_token_0|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a113717b4505b4f56b3bc1032540fa90b686c05b875e25bac0e1825441f38984
 size 17209920

 version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
 size 17209920

tokenizer_config.json CHANGED Viewed

@@ -73,7 +73,7 @@
       "special": true
     },
     "128009": {
-      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2050,11 +2050,15 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|reserved_special_token_0|>",
-  "tokenizer_class": "PreTrainedTokenizer",
-  "unk_token": null
 }

       "special": true
     },
     "128009": {
+      "content": "<|eot_id|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
     }
   },
   "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
   "pad_token": "<|reserved_special_token_0|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }