Upload folder using huggingface_hub

README.md

@@ -0,0 +1,179 @@
+---
+license: apache-2.0
+language:
+- en
+- es
+- it
+- de
+- fr
+---
+
+# 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](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1).
+
+## Run the model 
+```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
+
+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).tokens
+model = 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.tokenizer
+decoded = sp_tokenizer.decode(generated_ids[0])
+print(decoded)
+```
+Alternatively, you can run this example with the Hugging Face tokenizer.
+To use this example, you'll need transformers version 4.39.0 or higher.
+```console
+pip install transformers==4.39.0
+```
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "mistralai/Mixtral-8x22B-Instruct-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+conversation=[
+    {"role": "user", "content": "What's the weather like in Paris?"},
+    {
+        "role": "tool_calls",
+        "content": [
+            {
+                "name": "get_current_weather",
+                "arguments": {"location": "Paris, France", "format": "celsius"},
+                
+            }
+        ]
+    },
+    {
+        "role": "tool_results",
+        "content": {"content": 22}
+    },
+    {"role": "assistant", "content": "The current temperature in Paris, France is 22 degrees Celsius."},
+    {"role": "user", "content": "What about San Francisco?"}
+]
+
+
+tools = [{"type": "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"]}}}]
+
+# render the tool use prompt as a string:
+tool_use_prompt = tokenizer.apply_chat_template(
+            conversation,
+            chat_template="tool_use",
+            tools=tools,
+            tokenize=False,
+            add_generation_prompt=True,
+
+)
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-Instruct-v0.1")
+
+inputs = tokenizer(tool_use_prompt, return_tensors="pt")
+
+outputs = model.generate(**inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+# Instruct tokenizer
+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 MistralTokenizer
+from 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
+```
+
+# Function calling and special tokens
+This tokenizer includes more special tokens, related to function calling : 
+- [TOOL_CALLS]
+- [AVAILABLE_TOOLS]
+- [/AVAILABLE_TOOLS]
+- [TOOL_RESULTS]
+- [/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

config.json

@@ -0,0 +1,40 @@
+{
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 65536,
+    "model_type": "mixtral",
+    "num_attention_heads": 48,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "router_aux_loss_coef": 0.001,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.38.0",
+    "use_cache": true,
+    "vocab_size": 32768,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.5",
+        "bits": 8.0,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

output-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35df79413790c84063f68cfa5d308d4d76a14b6b9d40866f1d9f88f2cac6e4aa
+size 8569422376

output-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a59002f8bbc1a32d478d2bddf5c15aab422f9a0732cd460266df00ade86e7b0
+size 8520306088

output-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e72c883944fbb2f20b88f7699ba6d3bbb1b8aead3dbe54c8e6d792c276a7a47
+size 8562563704

output-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f668e5b1d63435dbb138b04a7fb1317e98d7427a3b84f84b0e29d2bd6ac057ae
+size 8539616536

output-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce0eba57cd2928e7312162fb563fdaeb3077ae9736990024f879ffa74c7bedd
+size 8551200984

output-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e422fefdde9865403291f22f9222f9575ef7293026145e3a7967ef4eb90f977
+size 8548131656

output-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:badf4490ab6ffc16885f5ecf8b038ff028de19e596761d0f6fb3e7a50bfceddb
+size 8548467248

output-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd24c4b457c8b4e982b3886e63abcc483a23ea8349ac7585a79c5db1f144019
+size 8503684280

output-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b692779c594f007b5562f2497e4ec5fdb43826d3d6a7ddd324f017d1ec71b459
+size 8526934840

output-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855d44fa3814aa05b4ebbd0b05b7793b5fe2327399a2fbabc33b119b3a45031c
+size 8580903824

output-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c169515f15105616abc36b4ba80ed0e91f8babf557d4af948edcdc8506594f
+size 8560383464

output-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d27b249b49e3abc2389eba49f26446e975cb0fcc33e4acff938d1e9f0258651
+size 8570281616

output-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daebab7e7aac873f19a6c2f5cfe5b190c61087058cd16fd7a7656aa1bcdd8dd5
+size 8541151592

output-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:460e7812688035367c2602153652d83a8139be70cda581b19af0260c61495726
+size 8587397488

output-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1cf0e058e77db0fbc8babb888a26dc1263900863210ed1488f96e2d4c7fd3e
+size 281580456

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "b_inst": "[INST]",
+  "e_inst": "[/INST]"
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": [
+  {
+    "name": "default",
+    "template": "{{bos_token}}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ ' [INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
+  },
+  {
+    "name": "tool_use",
+    "template": "{{bos_token}}{% set user_messages = messages | selectattr('role', 'equalto', 'user') | list %}{% for message in messages %}{% if message['role'] == 'user' %}{% if message == user_messages[-1] %}{% if tools %}{{'[AVAILABLE_TOOLS]'+ tools|string + '[/AVAILABLE_TOOLS]'}}{% endif %}{{ '[INST]' + message['content'] + '[/INST]' }}{% else %}{{ '[INST]' + message['content'] + '[/INST]' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token}}{% elif message['role'] == 'tool_results' %}{{'[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]'}}{% elif message['role'] == 'tool_calls' %}{{'[TOOL_CALLS]' + message['content']|string + eos_token}}{% endif %}{% endfor %}"
+  }
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}