Instructions to use hyper-accel/tiny-random-minimax-m1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hyper-accel/tiny-random-minimax-m1 with Transformers:

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

pipe = pipeline("text-generation", model="hyper-accel/tiny-random-minimax-m1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("hyper-accel/tiny-random-minimax-m1", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hyper-accel/tiny-random-minimax-m1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hyper-accel/tiny-random-minimax-m1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyper-accel/tiny-random-minimax-m1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hyper-accel/tiny-random-minimax-m1

SGLang

How to use hyper-accel/tiny-random-minimax-m1 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 "hyper-accel/tiny-random-minimax-m1" \
    --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": "hyper-accel/tiny-random-minimax-m1",
		"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 "hyper-accel/tiny-random-minimax-m1" \
        --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": "hyper-accel/tiny-random-minimax-m1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hyper-accel/tiny-random-minimax-m1 with Docker Model Runner:
```
docker model run hf.co/hyper-accel/tiny-random-minimax-m1
```

HyperAccel commited on Mar 25

Commit

27cd617

verified ·

1 Parent(s): 6f6cc97

Upload tokenizer from minimax_m1

Browse files

Files changed (4) hide show

.gitattributes +1 -0
chat_template.jinja +24 -0
tokenizer.json +3 -0
tokenizer_config.json +13 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,24 @@

+{{ '<begin_of_document>' -}}{% set ns = namespace(system_prompt='') -%}{% for message in messages -%}{% if message['role'] == 'system' -%}{% set ns.system_prompt = ns.system_prompt + message['content'][0]['text'] -%}{% endif -%}{%- endfor -%}{% if ns.system_prompt != '' -%}{{ '<beginning_of_sentence>system ai_setting=assistant
+' + ns.system_prompt + '<end_of_sentence>
+' -}}{%- endif -%}{% if tools -%}{{ '<beginning_of_sentence>system tool_setting=tools
+You are provided with these tools:
+<tools>
+' -}}{% for tool in tools -%}{{ tool | tojson ~ '
+' -}}{%- endfor -%}{{ '</tools>
+If you need to call tools, please respond with <tool_calls></tool_calls> XML tags, and provide tool-name and json-object of arguments, following the format below:
+<tool_calls>
+{''name'': <tool-name-1>, ''arguments'': <args-json-object-1>}
+...
+</tool_calls><end_of_sentence>
+' -}}{%- endif -%}{% for message in messages -%}{% if message['role'] == 'user' -%}{{ '<beginning_of_sentence>user name=user
+' + message['content'][0]['text'] + '<end_of_sentence>
+' -}}{% elif message['role'] == 'assistant' -%}{{ '<beginning_of_sentence>ai name=assistant
+' -}}{% for content in message['content'] | selectattr('type', 'equalto', 'text') -%}{{ content['text'] -}}{%- endfor -%}{{ '<end_of_sentence>
+' -}}{% elif message['role'] == 'tool' -%}{{ '<beginning_of_sentence>tool name=tools
+' }} {%- for content in message['content'] -%}{{- 'tool name: ' + content['name'] + '
+' + 'tool result: ' + content['text'] + '
+' -}} {%- endfor -%}{{- '<end_of_sentence>
+' -}}{% endif -%}{%- endfor -%}{% if add_generation_prompt -%}{{ '<beginning_of_sentence>ai name=assistant
+' -}}{%- endif -%}

tokenizer.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f4201a1d9edc97b52b3927bd892299d129e5a54a92fe518f4a145715228f31
+size 15519168

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<beginning_of_sentence>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<end_of_sentence>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 40960000,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<end_of_document>"
+}