GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ArchiveStudio
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ArchiveStudio
Model Tree
mistralai/Mixtral-8x22B-v0.1
Input Modalities
Output Modalities
Supported Functionality
mistral_commonpy
from mistral_common.tokens.tokenizers.mistral import MistralTokenizerfrom mistral_common.protocol.instruct.messages import UserMessagefrom mistral_common.protocol.instruct.request import ChatCompletionRequest mistral_models_path = "MISTRAL_MODELS_PATH" tokenizer = MistralTokenizer.v3() completion_request = ChatCompletionRequest(messages=[UserMessage(content="Explain Machine Learning to me in a nutshell.")]) tokens = tokenizer.encode_chat_completion(completion_request).tokensmistral_inferencepy
from mistral_inference.transformer import Transformerfrom mistral_inference.generate import generate model = Transformer.from_folder(mistral_models_path)out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id) result = tokenizer.decode(out_tokens[0]) print(result)transformerspy
from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1") chat = [{"role": "user", "content": "Explain Machine Learning to me in a nutshell."}] tokens = tokenizer.apply_chat_template(chat, return_dict=True, return_tensors="pt", add_generation_prompt=True)transformerspy
from transformers import AutoModelForCausalLMimport torch # You can also use 8-bit or 4-bit quantization heremodel = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1", torch_dtype=torch.bfloat16, device_map="auto")model.to("cuda") generated_ids = model.generate(**tokens, max_new_tokens=1000, do_sample=True) # decode with HF tokenizerresult = tokenizer.decode(generated_ids[0])print(result)[!TIP] PRs to correct the
transformerstokenizer so that it gives 1-to-1 the same results as themistral_commonreference implementation are very welcome!
The Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B-v0.1.
python
from transformers import AutoModelForCausalLMfrom mistral_common.protocol.instruct.messages import ( AssistantMessage, UserMessage,)from mistral_common.protocol.instruct.tool_calls import ( Tool, Function,)from mistral_common.tokens.tokenizers.mistral import MistralTokenizerfrom mistral_common.tokens.instruct.normalize import ChatCompletionRequest device = "cuda" # the device to load the model onto tokenizer_v3 = MistralTokenizer.v3() mistral_query = ChatCompletionRequest( tools=[ Tool( function=Function( name="get_current_weather", description="Get the current weather", parameters={ "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", }, "format": { "type": "string", "enum": ["celsius", "fahrenheit"], "description": "The temperature unit to use. Infer this from the users location.", }, }, "required": ["location", "format"], }, ) ) ], messages=[ UserMessage(content="What's the weather like today in Paris"), ], model="test",) encodeds = tokenizer_v3.encode_chat_completion(mistral_query).tokensmodel = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")model_inputs = encodeds.to(device)model.to(device) generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)sp_tokenizer = tokenizer_v3.instruct_tokenizer.tokenizerdecoded = sp_tokenizer.decode(generated_ids[0])print(decoded)transformersTo use this example, you'll need transformers version 4.42.0 or higher. Please see the
function calling guide
in the transformers docs for more information.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_id = "mistralai/Mixtral-8x22B-Instruct-v0.1"tokenizer = AutoTokenizer.from_pretrained(model_id) def get_current_weather(location: str, format: str): """ Get the current weather Args: location: The city and state, e.g. San Francisco, CA format: The temperature unit to use. Infer this from the users location. (choices: ["celsius", "fahrenheit"]) """ pass conversation = [{"role": "user", "content": "What's the weather like in Paris?"}]tools = [get_current_weather] # format and tokenize the tool use prompt inputs = tokenizer.apply_chat_template( conversation, tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt",) model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto") inputs.to(model.device)outputs = model.generate(**inputs, max_new_tokens=1000)print(tokenizer.decode(outputs[0], skip_special_tokens=True))Note that, for reasons of space, this example does not show a complete cycle of calling a tool and adding the tool call and tool results to the chat history so that the model can use them in its next generation. For a full tool calling example, please see the function calling guide, and note that Mixtral does use tool call IDs, so these must be included in your tool calls and tool results. They should be exactly 9 alphanumeric characters.
The HuggingFace tokenizer included in this release should match our own. To compare:
pip install mistral-common
py
from mistral_common.protocol.instruct.messages import ( AssistantMessage, UserMessage,)from mistral_common.tokens.tokenizers.mistral import MistralTokenizerfrom mistral_common.tokens.instruct.normalize import ChatCompletionRequest from transformers import AutoTokenizer tokenizer_v3 = MistralTokenizer.v3() mistral_query = ChatCompletionRequest( messages=[ UserMessage(content="How many experts ?"), AssistantMessage(content="8"), UserMessage(content="How big ?"), AssistantMessage(content="22B"), UserMessage(content="Noice 🎉 !"), ], model="test",)hf_messages = mistral_query.model_dump()['messages'] tokenized_mistral = tokenizer_v3.encode_chat_completion(mistral_query).tokens tokenizer_hf = AutoTokenizer.from_pretrained('mistralai/Mixtral-8x22B-Instruct-v0.1')tokenized_hf = tokenizer_hf.apply_chat_template(hf_messages, tokenize=True) assert tokenized_hf == tokenized_mistralThis tokenizer includes more special tokens, related to function calling :
If you want to use this model with function calling, please be sure to apply it similarly to what is done in our SentencePieceTokenizerV3.
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang, Valera Nemychnikova, William El Sayed, William Marshall
from mistral_common.tokens.tokenizers.mistral import MistralTokenizerfrom mistral_common.protocol.instruct.messages import UserMessagefrom mistral_common.protocol.instruct.request import ChatCompletionRequest mistral_models_path = "MISTRAL_MODELS_PATH" tokenizer = MistralTokenizer.v3() completion_request = ChatCompletionRequest(messages=[UserMessage(content="Explain Machine Learning to me in a nutshell.")]) tokens = tokenizer.encode_chat_completion(completion_request).tokensfrom mistral_inference.transformer import Transformerfrom mistral_inference.generate import generate model = Transformer.from_folder(mistral_models_path)out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id) result = tokenizer.decode(out_tokens[0]) print(result)from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1") chat = [{"role": "user", "content": "Explain Machine Learning to me in a nutshell."}] tokens = tokenizer.apply_chat_template(chat, return_dict=True, return_tensors="pt", add_generation_prompt=True)from transformers import AutoModelForCausalLMimport torch # You can also use 8-bit or 4-bit quantization heremodel = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1", torch_dtype=torch.bfloat16, device_map="auto")model.to("cuda") generated_ids = model.generate(**tokens, max_new_tokens=1000, do_sample=True) # decode with HF tokenizerresult = tokenizer.decode(generated_ids[0])print(result)from transformers import AutoModelForCausalLMfrom mistral_common.protocol.instruct.messages import ( AssistantMessage, UserMessage,)from mistral_common.protocol.instruct.tool_calls import ( Tool, Function,)from mistral_common.tokens.tokenizers.mistral import MistralTokenizerfrom mistral_common.tokens.instruct.normalize import ChatCompletionRequest device = "cuda" # the device to load the model onto tokenizer_v3 = MistralTokenizer.v3() mistral_query = ChatCompletionRequest( tools=[ Tool( function=Function( name="get_current_weather", description="Get the current weather", parameters={ "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", }, "format": { "type": "string", "enum": ["celsius", "fahrenheit"], "description": "The temperature unit to use. Infer this from the users location.", }, }, "required": ["location", "format"], }, ) ) ], messages=[ UserMessage(content="What's the weather like today in Paris"), ], model="test",) encodeds = tokenizer_v3.encode_chat_completion(mistral_query).tokensmodel = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")model_inputs = encodeds.to(device)model.to(device) generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)sp_tokenizer = tokenizer_v3.instruct_tokenizer.tokenizerdecoded = sp_tokenizer.decode(generated_ids[0])print(decoded)from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_id = "mistralai/Mixtral-8x22B-Instruct-v0.1"tokenizer = AutoTokenizer.from_pretrained(model_id) def get_current_weather(location: str, format: str): """ Get the current weather Args: location: The city and state, e.g. San Francisco, CA format: The temperature unit to use. Infer this from the users location. (choices: ["celsius", "fahrenheit"]) """ pass conversation = [{"role": "user", "content": "What's the weather like in Paris?"}]tools = [get_current_weather] # format and tokenize the tool use prompt inputs = tokenizer.apply_chat_template( conversation, tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt",) model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto") inputs.to(model.device)outputs = model.generate(**inputs, max_new_tokens=1000)print(tokenizer.decode(outputs[0], skip_special_tokens=True))from mistral_common.protocol.instruct.messages import ( AssistantMessage, UserMessage,)from mistral_common.tokens.tokenizers.mistral import MistralTokenizerfrom mistral_common.tokens.instruct.normalize import ChatCompletionRequest from transformers import AutoTokenizer tokenizer_v3 = MistralTokenizer.v3() mistral_query = ChatCompletionRequest( messages=[ UserMessage(content="How many experts ?"), AssistantMessage(content="8"), UserMessage(content="How big ?"), AssistantMessage(content="22B"), UserMessage(content="Noice 🎉 !"), ], model="test",)hf_messages = mistral_query.model_dump()['messages'] tokenized_mistral = tokenizer_v3.encode_chat_completion(mistral_query).tokens tokenizer_hf = AutoTokenizer.from_pretrained('mistralai/Mixtral-8x22B-Instruct-v0.1')tokenized_hf = tokenizer_hf.apply_chat_template(hf_messages, tokenize=True) assert tokenized_hf == tokenized_mistral