Update README.md

.gitattributes

@@ -33,4 +33,3 @@ 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
-tokenizer.model.v3 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,99 +1,17 @@
 ---
-library_name: vllm
-language:
-- en
-- es
-- it
-- de
-- fr
 license: apache-2.0
-base_model: mistralai/Mixtral-8x22B-v0.1
-extra_gated_description: >-
-  If you want to learn more about how we process your personal data, please read
-  our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
-tags:
-- mistral-common
 ---
 
 # Model Card for Mixtral-8x22B-Instruct-v0.1
+The Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B-v0.1.
 
-
-## Encode and Decode with `mistral_common`
-            
-```py
-from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
-from mistral_common.protocol.instruct.messages import UserMessage
-from 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).tokens
-```
- 
-## Inference with `mistral_inference`
- 
- ```py
-from mistral_inference.transformer import Transformer
-from 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)
-```
-
-## Preparing inputs with Hugging Face `transformers`
-
-```py
-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)
+## Run the model 
 ```
-
-## Inference with hugging face `transformers`
- 
-```py
-from transformers import AutoModelForCausalLM
-import torch
-
-# You can also use 8-bit or 4-bit quantization here
-model = 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 tokenizer
-result = tokenizer.decode(generated_ids[0])
-print(result)
-```
-
-> [!TIP]
-> PRs to correct the `transformers` tokenizer so that it gives 1-to-1 the same results as the `mistral_common` reference 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](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1).
-
-## Function calling example
-```python
 from transformers import AutoModelForCausalLM
 from 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 MistralTokenizer
 from mistral_common.tokens.instruct.normalize import ChatCompletionRequest
 
@@ -137,59 +55,10 @@ 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.tokenizer
-decoded = sp_tokenizer.decode(generated_ids[0])
-print(decoded)
+decoded = tokenizer.batch_decode(generated_ids)
+print(decoded[0])
 ```
 
-## Function calling with `transformers`
-
-To use this example, you'll need `transformers` version 4.42.0 or higher. Please see the 
-[function calling guide](https://huggingface.co/docs/transformers/main/chat_templating#advanced-tool-use--function-calling)
-in the `transformers` docs for more information.
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import 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](https://huggingface.co/docs/transformers/main/chat_templating#advanced-tool-use--function-calling), 
-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.
-
 # Instruct tokenizer
 The HuggingFace tokenizer included in this release should match our own. To compare: 
 `pip install mistral-common`
@@ -231,20 +100,7 @@ This tokenizer includes more special tokens, related to function calling :
 - [TOOL_CALLS]
 - [AVAILABLE_TOOLS]
 - [/AVAILABLE_TOOLS]
-- [TOOL_RESULTS]
+- [TOOL_RESULT]
 - [/TOOL_RESULTS]
 
-If you want to use this model with function calling, please be sure to apply it similarly to what is done in our [SentencePieceTokenizerV3](https://github.com/mistralai/mistral-common/blob/main/src/mistral_common/tokens/tokenizers/sentencepiece.py#L299).
-
-# The Mistral AI Team
-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
+If you want to use this model with function calling, please be sure to apply it similarly to what is done in our [SentencePieceTokenizerV3](github.com/mistralai/mistral-common/...).

config.json

@@ -9,7 +9,7 @@
   "hidden_size": 6144,
   "initializer_range": 0.02,
   "intermediate_size": 16384,
-  "max_position_embeddings": 65536,
+  "max_position_embeddings": 32768,
   "model_type": "mixtral",
   "num_attention_heads": 48,
   "num_experts_per_tok": 2,

special_tokens_map.json

@@ -1,23 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "b_inst": "[INST]",
+  "e_inst": "[/INST]"
 }

tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
-size 587404

tokenizer.model.v3

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
-size 587404