Upload folder using huggingface_hub

Browse files

Files changed (16) hide show

.gitattributes +1 -0
README.md +613 -0
config.json +39 -0
config.yaml +208 -0
generation_config.json +7 -0
measurement.json +0 -0
model.safetensors.index.json +649 -0
output-00001-of-00005.safetensors +3 -0
output-00002-of-00005.safetensors +3 -0
output-00003-of-00005.safetensors +3 -0
output-00004-of-00005.safetensors +3 -0
output-00005-of-00005.safetensors +3 -0
place-your-models-here.txt +0 -0
special_tokens_map.json +23 -0
tokenizer.json +3 -0
tokenizer_config.json +330 -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

README.md ADDED Viewed

	@@ -0,0 +1,613 @@

+---
+inference: false
+license: cc-by-nc-4.0
+library_name: transformers
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ja
+- ko
+- zh
+- ar
+extra_gated_prompt: "By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license)  and acknowledge that the information you provide will be collected, used, and shared in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy)."
+extra_gated_fields:
+ Name: text
+ Affiliation: text
+ Country:
+    type: select
+    options:
+      - Aruba
+      - Afghanistan
+      - Angola
+      - Anguilla
+      - Åland Islands
+      - Albania
+      - Andorra
+      - United Arab Emirates
+      - Argentina
+      - Armenia
+      - American Samoa
+      - Antarctica
+      - French Southern Territories
+      - Antigua and Barbuda
+      - Australia
+      - Austria
+      - Azerbaijan
+      - Burundi
+      - Belgium
+      - Benin
+      - Bonaire Sint Eustatius and Saba
+      - Burkina Faso
+      - Bangladesh
+      - Bulgaria
+      - Bahrain
+      - Bahamas
+      - Bosnia and Herzegovina
+      - Saint Barthélemy
+      - Belarus
+      - Belize
+      - Bermuda
+      - Plurinational State of Bolivia
+      - Brazil
+      - Barbados
+      - Brunei-Darussalam
+      - Bhutan
+      - Bouvet-Island
+      - Botswana
+      - Central African Republic
+      - Canada
+      - Cocos (Keeling) Islands
+      - Switzerland
+      - Chile
+      - China
+      - Côte-dIvoire
+      - Cameroon
+      - Democratic Republic of the Congo
+      - Cook Islands
+      - Colombia
+      - Comoros
+      - Cabo Verde
+      - Costa Rica
+      - Cuba
+      - Curaçao
+      - Christmas Island
+      - Cayman Islands
+      - Cyprus
+      - Czechia
+      - Germany
+      - Djibouti
+      - Dominica
+      - Denmark
+      - Dominican Republic
+      - Algeria
+      - Ecuador
+      - Egypt
+      - Eritrea
+      - Western Sahara
+      - Spain
+      - Estonia
+      - Ethiopia
+      - Finland
+      - Fiji
+      - Falkland Islands (Malvinas)
+      - France
+      - Faroe Islands
+      - Federated States of Micronesia
+      - Gabon
+      - United Kingdom
+      - Georgia
+      - Guernsey
+      - Ghana
+      - Gibraltar
+      - Guinea
+      - Guadeloupe
+      - Gambia
+      - Guinea Bissau
+      - Equatorial Guinea
+      - Greece
+      - Grenada
+      - Greenland
+      - Guatemala
+      - French Guiana
+      - Guam
+      - Guyana
+      - Hong Kong
+      - Heard Island and McDonald Islands
+      - Honduras
+      - Croatia
+      - Haiti
+      - Hungary
+      - Indonesia
+      - Isle of Man
+      - India
+      - British Indian Ocean Territory
+      - Ireland
+      - Islamic Republic of Iran
+      - Iraq
+      - Iceland
+      - Israel
+      - Italy
+      - Jamaica
+      - Jersey
+      - Jordan
+      - Japan
+      - Kazakhstan
+      - Kenya
+      - Kyrgyzstan
+      - Cambodia
+      - Kiribati
+      - Saint-Kitts-and-Nevis
+      - South Korea
+      - Kuwait
+      - Lao-Peoples-Democratic-Republic
+      - Lebanon
+      - Liberia
+      - Libya
+      - Saint-Lucia
+      - Liechtenstein
+      - Sri Lanka
+      - Lesotho
+      - Lithuania
+      - Luxembourg
+      - Latvia
+      - Macao
+      - Saint Martin (French-part)
+      - Morocco
+      - Monaco
+      - Republic of Moldova
+      - Madagascar
+      - Maldives
+      - Mexico
+      - Marshall Islands
+      - North Macedonia
+      - Mali
+      - Malta
+      - Myanmar
+      - Montenegro
+      - Mongolia
+      - Northern Mariana Islands
+      - Mozambique
+      - Mauritania
+      - Montserrat
+      - Martinique
+      - Mauritius
+      - Malawi
+      - Malaysia
+      - Mayotte
+      - Namibia
+      - New Caledonia
+      - Niger
+      - Norfolk Island
+      - Nigeria
+      - Nicaragua
+      - Niue
+      - Netherlands
+      - Norway
+      - Nepal
+      - Nauru
+      - New Zealand
+      - Oman
+      - Pakistan
+      - Panama
+      - Pitcairn
+      - Peru
+      - Philippines
+      - Palau
+      - Papua New Guinea
+      - Poland
+      - Puerto Rico
+      - North Korea
+      - Portugal
+      - Paraguay
+      - State of Palestine
+      - French Polynesia
+      - Qatar
+      - Réunion
+      - Romania
+      - Russia
+      - Rwanda
+      - Saudi Arabia
+      - Sudan
+      - Senegal
+      - Singapore
+      - South Georgia and the South Sandwich Islands
+      - Saint Helena Ascension and Tristan da Cunha
+      - Svalbard and Jan Mayen
+      - Solomon Islands
+      - Sierra Leone
+      - El Salvador
+      - San Marino
+      - Somalia
+      - Saint Pierre and Miquelon
+      - Serbia
+      - South Sudan
+      - Sao Tome and Principe
+      - Suriname
+      - Slovakia
+      - Slovenia
+      - Sweden
+      - Eswatini
+      - Sint Maarten (Dutch-part)
+      - Seychelles
+      - Syrian Arab Republic
+      - Turks and Caicos Islands
+      - Chad
+      - Togo
+      - Thailand
+      - Tajikistan
+      - Tokelau
+      - Turkmenistan
+      - Timor Leste
+      - Tonga
+      - Trinidad and Tobago
+      - Tunisia
+      - Turkey
+      - Tuvalu
+      - Taiwan
+      - United Republic of Tanzania
+      - Uganda
+      - Ukraine
+      - United States Minor Outlying Islands
+      - Uruguay
+      - United-States
+      - Uzbekistan
+      - Holy See (Vatican City State)
+      - Saint Vincent and the Grenadines
+      - Bolivarian Republic of Venezuela
+      - Virgin Islands British
+      - Virgin Islands U.S.
+      - VietNam
+      - Vanuatu
+      - Wallis and Futuna
+      - Samoa
+      - Yemen
+      - South Africa
+      - Zambia
+      - Zimbabwe
+ Receive email updates on C4AI and Cohere research, events, products and services?:
+   type: select
+   options:
+     - Yes
+     - No
+ I agree to use this model for non-commercial use ONLY: checkbox
+---
+# Model Card for C4AI Command R+ 08-2024
+## Model Summary
+C4AI Command R+ 08-2024 is an open weights research release of a 104B billion parameter model with highly advanced capabilities, this includes Retrieval Augmented Generation (RAG) and tool use to automate sophisticated tasks. The tool use in this model generation enables multi-step tool use which allows the model to combine multiple tools over multiple steps to accomplish difficult tasks. C4AI Command R+ 08-2024 is a multilingual model trained on 23 languages and evaluated in 10 languages. Command R+ 08-2024 is optimized for a variety of use cases including reasoning, summarization, and question answering.
+C4AI Command R+ 08-2024 is part of a family of open weight releases from Cohere For AI and Cohere. Our smaller companion model is [C4AI Command R 08-2024](https://huggingface.co/CohereForAI/c4ai-command-r-08-2024).
+- Point of Contact: Cohere For AI: [cohere.for.ai](https://cohere.for.ai/)
+- License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy)
+- Model: c4ai-command-r-plus-08-2024
+- Model Size: 104 billion parameters
+- Context length: 128K
+**Try C4AI Command R+**
+You can try out C4AI Command R+ before downloading the weights in our hosted [Hugging Face Space](https://huggingface.co/spaces/CohereForAI/c4ai-command?model=command-r-plus-08-2024).
+**Usage**
+Please use `transformers` version 4.39.1 or higher
+```python
+# pip install 'transformers>=4.39.1'
+from transformers import AutoTokenizer, AutoModelForCausalLM
+model_id = "CohereForAI/c4ai-command-r-plus-08-2024"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+# Format message with the command-r-plus-08-2024 chat template
+messages = [{"role": "user", "content": "Hello, how are you?"}]
+input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+gen_tokens = model.generate(
+    input_ids,
+    max_new_tokens=100,
+    do_sample=True,
+    temperature=0.3,
+    )
+gen_text = tokenizer.decode(gen_tokens[0])
+print(gen_text)
+```
+## Model Details
+**Input**: Models input text only.
+**Output**: Models generate text only.
+**Model Architecture**: This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety. We use grouped query attention (GQA) to improve inference speed.
+**Languages covered**: The model has been trained on 23 languages (English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, Simplified Chinese, Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, and Persian) and evaluated on 10 languages (English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, Simplified Chinese).
+**Context length**: Command R+ 08-2024 supports a context length of 128K.
+### Tool use & Agent capabilities:
+Command R+ 08-2024 has been specifically trained with conversational tool use capabilities. These have been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template will likely reduce performance, but we encourage experimentation.
+Command R+ 08-2024’s tool use functionality takes a conversation as input (with an optional user-system preamble), along with a list of available tools. The model will then generate a json-formatted list of actions to execute on a subset of those tools. Command R+ 08-2024 may use one of its supplied tools more than once.
+The model has been trained to recognise a special `directly_answer` tool, which it uses to indicate that it doesn’t want to use any of its other tools. The ability to abstain from calling a specific tool can be useful in a range of situations, such as greeting a user, or asking clarifying questions. We recommend including the `directly_answer` tool, but it can be removed or renamed if required.
+Comprehensive documentation for working with Command R+ 08-2024's tool use prompt template can be found [here](https://docs.cohere.com/docs/prompting-command-r).
+Command R+ 08-2024 also supports Hugging Face's [tool use API](https://huggingface.co/docs/transformers/main/en/chat_templating#advanced-tool-use--function-calling).
+The code snippets below show minimal working examples on how to render a prompt.
+<details>
+<summary><b>Usage: Rendering Tool Use Prompts [CLICK TO EXPAND]</b> </summary>
+```python
+from transformers import AutoTokenizer
+model_id = "CohereForAI/c4ai-command-r-plus-08-2024"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+# define conversation input:
+conversation = [
+    {"role": "user", "content": "Whats the biggest penguin in the world?"}
+]
+# Define tools available for the model to use:
+tools = [
+  {
+    "name": "internet_search",
+    "description": "Returns a list of relevant document snippets for a textual query retrieved from the internet",
+    "parameter_definitions": {
+      "query": {
+        "description": "Query to search the internet with",
+        "type": 'str',
+        "required": True
+      }
+    }
+  },
+  {
+    'name': "directly_answer",
+    "description": "Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history",
+    'parameter_definitions': {}
+  }
+]
+# render the tool use prompt as a string:
+tool_use_prompt = tokenizer.apply_tool_use_template(
+    conversation,
+    tools=tools,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+print(tool_use_prompt)
+```
+</details>
+<details>
+<summary><b>Usage: Rendering prompts with the Tool Use API [CLICK TO EXPAND]</b> </summary>
+```python
+from transformers import AutoTokenizer
+model_id = "CohereForAI/c4ai-command-r-plus-08-2024"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+# define conversation input:
+conversation = [
+    {"role": "user", "content": "Whats the biggest penguin in the world?"}
+]
+# Define tools available for the model to use
+# Type hints and docstrings from Python functions are automatically extracted
+def internet_search(query: str):
+    """
+    Returns a list of relevant document snippets for a textual query retrieved from the internet
+    Args:
+        query: Query to search the internet with
+    """
+    pass
+def directly_answer():
+    """
+    Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history
+    """
+    pass
+tools = [internet_search, directly_answer]
+# render the tool use prompt as a string:
+tool_use_prompt = tokenizer.apply_chat_template(
+    conversation,
+    tools=tools,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+print(tool_use_prompt)
+```
+</details>
+<details>
+<summary><b>Example Rendered Tool Use Prompt [CLICK TO EXPAND]</b></summary>
+````
+<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble
+The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
+# System Preamble
+## Basic Rules
+You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.
+# User Preamble
+## Task and Context
+You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.
+## Style Guide
+Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.
+## Available Tools
+Here is a list of tools that you have available to you:
+```python
+def internet_search(query: str) -> List[Dict]:
+    """Returns a list of relevant document snippets for a textual query retrieved from the internet
+    Args:
+        query (str): Query to search the internet with
+    """
+    pass
+```
+```python
+def directly_answer() -> List[Dict]:
+    """Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history
+    """
+    pass
+```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Whats the biggest penguin in the world?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write 'Action:' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user's last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:
+```json
+[
+    {
+        "tool_name": title of the tool in the specification,
+        "parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters
+    }
+]```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+````
+</details>
+<details>
+<summary><b>Example Rendered Tool Use Completion [CLICK TO EXPAND]</b></summary>
+````
+Action: ```json
+[
+      {
+          "tool_name": "internet_search",
+          "parameters": {
+              "query": "biggest penguin in the world"
+          }
+      }
+]
+```
+````
+</details>
+### Grounded Generation and RAG Capabilities:
+Command R+ 08-2024 has been specifically trained with grounded generation capabilities. This means that it can generate responses based on a list of supplied document snippets, and it will include grounding spans (citations) in its response indicating the source of the information. This can be used to enable behaviors such as grounded summarization and the final step of Retrieval Augmented Generation (RAG). This behavior has been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template may reduce performance, but we encourage experimentation.
+Command R+ 08-2024’s grounded generation behavior takes a conversation as input (with an optional user-supplied system preamble, indicating task, context and desired output style), along with a list of retrieved document snippets. The document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured.
+By default, Command R+ 08-2024 will generate grounded responses by first predicting which documents are relevant, then predicting which ones it will cite, then generating an answer. Finally, it will then insert grounding spans into the answer. See below for an example. This is referred to as `accurate` grounded generation.
+The model is trained with a number of other answering modes, which can be selected by prompt changes. A `fast` citation mode is supported in the tokenizer, which will directly generate an answer with grounding spans in it, without first writing the answer out in full. This sacrifices some grounding accuracy in favor of generating fewer tokens.
+Comprehensive documentation for working with Command R+ 08-2024's grounded generation prompt template can be found [here](https://docs.cohere.com/docs/prompting-command-r).
+The code snippet below shows a minimal working example on how to render a prompt.
+<details>
+<summary> <b>Usage: Rendering Grounded Generation prompts [CLICK TO EXPAND]</b> </summary>
+````python
+from transformers import AutoTokenizer
+model_id = "CohereForAI/c4ai-command-r-plus-08-2024"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+# define conversation input:
+conversation = [
+    {"role": "user", "content": "Whats the biggest penguin in the world?"}
+]
+# define documents to ground on:
+documents = [
+    { "title": "Tall penguins", "text": "Emperor penguins are the tallest growing up to 122 cm in height." },
+    { "title": "Penguin habitats", "text": "Emperor penguins only live in Antarctica."}
+]
+# render the tool use prompt as a string:
+grounded_generation_prompt = tokenizer.apply_grounded_generation_template(
+    conversation,
+    documents=documents,
+    citation_mode="accurate", # or "fast"
+    tokenize=False,
+    add_generation_prompt=True,
+)
+print(grounded_generation_prompt)
+````
+</details>
+<details>
+<summary><b>Example Rendered Grounded Generation Prompt [CLICK TO EXPAND]</b></summary>
+````
+<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble
+The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
+# System Preamble
+## Basic Rules
+You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.
+# User Preamble
+## Task and Context
+You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.
+## Style Guide
+Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Whats the biggest penguin in the world?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><results>
+Document: 0
+title: Tall penguins
+text: Emperor penguins are the tallest growing up to 122 cm in height.
+Document: 1
+title: Penguin habitats
+text: Emperor penguins only live in Antarctica.
+</results><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Carefully perform the following instructions, in order, starting each with a new line.
+Firstly, Decide which of the retrieved documents are relevant to the user's last input by writing 'Relevant Documents:' followed by comma-separated list of document numbers. If none are relevant, you should instead write 'None'.
+Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user's last input by writing 'Cited Documents:' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write 'None'.
+Thirdly, Write 'Answer:' followed by a response to the user's last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.
+Finally, Write 'Grounded answer:' followed by a response to the user's last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+````
+</details>
+<details>
+<summary><b>Example Rendered Grounded Generation Completion [CLICK TO EXPAND]</b></summary>
+````
+Relevant Documents: 0,1
+Cited Documents: 0,1
+Answer: The Emperor Penguin is the tallest or biggest penguin in the world. It is a bird that lives only in Antarctica and grows to a height of around 122 centimetres.
+Grounded answer: The <co: 0>Emperor Penguin</co: 0> is the <co: 0>tallest</co: 0> or biggest penguin in the world. It is a bird that <co: 1>lives only in Antarctica</co: 1> and <co: 0>grows to a height of around 122 centimetres.</co: 0>
+````
+</details>
+### Code Capabilities:
+Command R+ 08-2024 has been optimized to interact with your code, by requesting code snippets, code explanations, or code rewrites. It might not perform well out-of-the-box for pure code completion. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions.
+### Model Card Contact
+For errors or additional questions about details in this model card, contact [info@for.ai](mailto:info@for.ai).
+### Terms of Use:
+We hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 104 billion parameter model to researchers all over the world. This model is governed by a [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license) License with an acceptable use addendum, and also requires adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy).
+### Try Chat:
+You can try Command R+ 08-2024 chat in the playground [here](https://dashboard.cohere.com/playground/chat). You can also use it in our dedicated Hugging Face Space [here](https://huggingface.co/spaces/CohereForAI/c4ai-command?model=command-r-plus-08-2024).

config.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+    "_name_or_path": "models/command2_100B_v20.1.0_muzsk7yh_pref_multi/",
+    "architectures": [
+        "CohereForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 5,
+    "eos_token_id": 255001,
+    "hidden_act": "silu",
+    "hidden_size": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 33792,
+    "layer_norm_eps": 1e-05,
+    "logit_scale": 0.8333333333333334,
+    "max_position_embeddings": 131072,
+    "model_type": "cohere",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "rope_theta": 8000000,
+    "torch_dtype": "float16",
+    "transformers_version": "4.44.0",
+    "use_cache": true,
+    "use_qk_norm": true,
+    "vocab_size": 256000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.9",
+        "bits": 2.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

config.yaml ADDED Viewed

	@@ -0,0 +1,208 @@

+.*(llama|alpac|vicuna|guanaco|koala|llava|wizardlm|metharme|pygmalion-7b|pygmalion-2|mythalion|wizard-mega|openbuddy|vigogne|h2ogpt-research|manticore):
+  model_type: 'llama'
+.*(opt-|opt_|opt1|opt3|optfor|galactica|galpaca|pygmalion-350m):
+  model_type: 'opt'
+.*(gpt-j|gptj|gpt4all-j|malion-6b|pygway|pygmalion-6b|dolly-v1):
+  model_type: 'gptj'
+.*(gpt-neox|koalpaca-polyglot|polyglot.*koalpaca|polyglot-ko|polyglot_ko|pythia|stablelm|incite|dolly-v2|polycoder|h2ogpt-oig|h2ogpt-oasst1|h2ogpt-gm):
+  model_type: 'gptneox'
+.*bloom:
+  model_type: 'bloom'
+.*gpt2:
+  model_type: 'gpt2'
+.*falcon:
+  model_type: 'falcon'
+.*mpt:
+  model_type: 'mpt'
+.*(starcoder|starchat):
+  model_type: 'starcoder'
+.*dolly-v2:
+  model_type: 'dollyv2'
+.*replit:
+  model_type: 'replit'
+.*(oasst|openassistant-|stablelm-7b-sft-v7-epoch-3):
+  instruction_template: 'Open Assistant'
+  skip_special_tokens: false
+(?!.*galactica)(?!.*reward).*openassistant:
+  instruction_template: 'Open Assistant'
+  skip_special_tokens: false
+.*galactica:
+  skip_special_tokens: false
+.*dolly-v[0-9]-[0-9]*b:
+  instruction_template: 'Alpaca'
+  skip_special_tokens: false
+.*alpaca-native-4bit:
+  instruction_template: 'Alpaca'
+  custom_stopping_strings: '"### End"'
+.*llava:
+  instruction_template: 'LLaVA'
+  custom_stopping_strings: '"\n###"'
+.*llava.*1.5:
+  instruction_template: 'Vicuna-v1.1'
+.*wizard.*mega:
+  instruction_template: 'Wizard-Mega'
+  custom_stopping_strings: '"</s>"'
+.*starchat-beta:
+  instruction_template: 'Starchat-Beta'
+  custom_stopping_strings: '"<|end|>"'
+(?!.*v0)(?!.*1.1)(?!.*1_1)(?!.*stable)(?!.*chinese).*vicuna:
+  instruction_template: 'Vicuna-v0'
+.*vicuna.*v0:
+  instruction_template: 'Vicuna-v0'
+.*vicuna.*(1.1|1_1|1.3|1_3):
+  instruction_template: 'Vicuna-v1.1'
+.*vicuna.*(1.5|1_5):
+  instruction_template: 'Vicuna-v1.1'
+.*stable.*vicuna:
+  instruction_template: 'StableVicuna'
+(?!.*chat).*chinese-vicuna:
+  instruction_template: 'Alpaca'
+.*chinese-vicuna.*chat:
+  instruction_template: 'Chinese-Vicuna-Chat'
+.*alpaca:
+  instruction_template: 'Alpaca'
+.*koala:
+  instruction_template: 'Koala'
+.*chatglm:
+  instruction_template: 'ChatGLM'
+.*(metharme|pygmalion|mythalion):
+  instruction_template: 'Metharme'
+.*raven:
+  instruction_template: 'RWKV-Raven'
+.*moss-moon.*sft:
+  instruction_template: 'MOSS'
+.*stablelm-tuned:
+  instruction_template: 'StableLM'
+.*galactica.*finetuned:
+  instruction_template: 'Galactica Finetuned'
+.*galactica.*-v2:
+  instruction_template: 'Galactica v2'
+(?!.*finetuned)(?!.*-v2).*galactica:
+  instruction_template: 'Galactica'
+.*guanaco:
+  instruction_template: 'Guanaco non-chat'
+.*baize:
+  instruction_template: 'Baize'
+.*mpt-.*instruct:
+  instruction_template: 'Alpaca'
+.*mpt-.*chat:
+  instruction_template: 'ChatML'
+(?!.*-flan-)(?!.*-t5-).*lamini-:
+  instruction_template: 'Alpaca'
+.*incite.*chat:
+  instruction_template: 'INCITE-Chat'
+.*incite.*instruct:
+  instruction_template: 'INCITE-Instruct'
+.*ziya-:
+  instruction_template: 'Ziya'
+.*koalpaca:
+  instruction_template: 'KoAlpaca'
+.*openbuddy:
+  instruction_template: 'OpenBuddy'
+(?!.*chat).*vigogne:
+  instruction_template: 'Vigogne-Instruct'
+.*vigogne.*chat:
+  instruction_template: 'Vigogne-Chat'
+.*(llama-deus|supercot|llama-natural-instructions|open-llama-0.3t-7b-instruct-dolly-hhrlhf|open-llama-0.3t-7b-open-instruct):
+  instruction_template: 'Alpaca'
+.*bactrian:
+  instruction_template: 'Bactrian'
+.*(h2ogpt-oig-|h2ogpt-oasst1-|h2ogpt-research-oasst1-):
+  instruction_template: 'INCITE-Chat'
+.*h2ogpt-gm-:
+  instruction_template: 'H2O-prompt_answer'
+.*manticore:
+  instruction_template: 'Manticore Chat'
+.*bluemoonrp-(30|13)b:
+  instruction_template: 'Bluemoon'
+.*Nous-Hermes-13b:
+  instruction_template: 'Alpaca'
+.*airoboros:
+  instruction_template: 'Vicuna-v1.1'
+.*airoboros.*1.2:
+  instruction_template: 'Airoboros-v1.2'
+.*alpa(cino|sta):
+  instruction_template: 'Alpaca'
+.*hippogriff:
+  instruction_template: 'Hippogriff'
+.*lazarus:
+  instruction_template: 'Alpaca'
+.*guanaco-.*(7|13|33|65)b:
+  instruction_template: 'Vicuna-v0'
+.*hypermantis:
+  instruction_template: 'Alpaca'
+.*open-llama-.*-open-instruct:
+  instruction_template: 'Alpaca'
+.*starcoder-gpteacher-code-instruct:
+  instruction_template: 'Alpaca'
+.*tulu:
+  instruction_template: 'Tulu'
+.*chronos:
+  instruction_template: 'Alpaca'
+.*samantha:
+  instruction_template: 'Samantha'
+.*wizardcoder:
+  instruction_template: 'Alpaca'
+.*minotaur:
+  instruction_template: 'Manticore Chat'
+.*orca_mini:
+  instruction_template: 'Orca Mini'
+.*(platypus|gplatty|superplatty):
+  instruction_template: 'Alpaca'
+.*(openorca-platypus2):
+  instruction_template: 'OpenOrca-Platypus2'
+  custom_stopping_strings: '"### Instruction:", "### Response:"'
+.*longchat:
+  instruction_template: 'Vicuna-v1.1'
+.*vicuna-33b:
+  instruction_template: 'Vicuna-v1.1'
+.*redmond-hermes-coder:
+  instruction_template: 'Alpaca'
+.*wizardcoder-15b:
+  instruction_template: 'Alpaca'
+.*wizardlm:
+  instruction_template: 'Vicuna-v1.1'
+.*godzilla:
+  instruction_template: 'Alpaca'
+.*llama(-?)(2|v2).*chat:
+  instruction_template: 'Llama-v2'
+.*newhope:
+  instruction_template: 'NewHope'
+.*stablebeluga2:
+  instruction_template: 'StableBeluga2'
+.*openchat:
+  instruction_template: 'OpenChat'
+.*codellama.*instruct:
+  instruction_template: 'Llama-v2'
+.*(mistral|mixtral).*instruct:
+  instruction_template: 'Mistral'
+.*mistral.*openorca:
+  instruction_template: 'ChatML'
+.*(WizardCoder-Python-34B-V1.0|Phind-CodeLlama-34B-v2|CodeBooga-34B-v0.1):
+  instruction_template: 'Alpaca'
+.*orca-2-(13|7)b:
+  instruction_template: 'ChatML'
+.*openhermes.*mistral:
+  instruction_template: 'ChatML'
+.*Yi-34B-Chat:
+  instruction_template: 'ChatML'
+(dolphin).*:
+  instruction_template: 'ChatML'
+.*synthia:
+  instruction_template: 'Synthia'
+.*(hercules|hyperion):
+  instruction_template: 'ChatML'
+.*command-r:
+  instruction_template: 'Command-R'
+.*xwin-lm-70b-v0.1:
+  instruction_template: 'Vicuna-v1.1'
+.*platypus-yi-34b:
+  instruction_template: 'Vicuna-v1.1'
+.*CausalLM-RP-34B:
+  instruction_template: 'ChatML'
+34b-beta:
+  instruction_template: 'ChatML'
+.*airoboros-3_1-yi-34b-200k:
+  instruction_template: 'Llama-v2'
+.*chatqa:
+  instruction_template: 'NVIDIA-ChatQA'

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.0"
+}

measurement.json ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,649 @@

+{
+  "metadata": {
+    "total_size": 207621349376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00044.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00044.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00044.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00044.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00009-of-00044.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00008-of-00044.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00008-of-00044.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00044.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00010-of-00044.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00009-of-00044.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00009-of-00044.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00011-of-00044.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00010-of-00044.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00010-of-00044.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00044.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00044.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00012-of-00044.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00011-of-00044.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00011-of-00044.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00013-of-00044.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00012-of-00044.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00012-of-00044.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00044.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00044.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00014-of-00044.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00013-of-00044.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00013-of-00044.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00015-of-00044.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00014-of-00044.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00014-of-00044.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00044.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00044.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00015-of-00044.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00016-of-00044.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00015-of-00044.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00015-of-00044.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00017-of-00044.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00016-of-00044.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00016-of-00044.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00044.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00017-of-00044.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00018-of-00044.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00017-of-00044.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00017-of-00044.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00019-of-00044.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00018-of-00044.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00018-of-00044.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00044.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00044.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00020-of-00044.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00019-of-00044.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00019-of-00044.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00021-of-00044.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00020-of-00044.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00020-of-00044.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00044.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00044.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00044.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00044.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00044.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00022-of-00044.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00021-of-00044.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00021-of-00044.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00023-of-00044.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00022-of-00044.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00022-of-00044.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00044.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00044.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00024-of-00044.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00023-of-00044.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00023-of-00044.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00025-of-00044.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00024-of-00044.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00024-of-00044.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00044.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00044.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00026-of-00044.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00025-of-00044.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00025-of-00044.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00027-of-00044.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00026-of-00044.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00026-of-00044.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00044.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00044.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00028-of-00044.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00027-of-00044.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00027-of-00044.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00005-of-00044.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00004-of-00044.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00004-of-00044.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00044.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00029-of-00044.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00028-of-00044.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00028-of-00044.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00028-of-00044.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00029-of-00044.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00030-of-00044.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00029-of-00044.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00029-of-00044.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00031-of-00044.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00030-of-00044.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00030-of-00044.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00030-of-00044.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00031-of-00044.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00032-of-00044.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00031-of-00044.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00031-of-00044.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00033-of-00044.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00032-of-00044.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00032-of-00044.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00032-of-00044.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00033-of-00044.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00034-of-00044.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00033-of-00044.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00033-of-00044.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00035-of-00044.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00034-of-00044.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00034-of-00044.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00034-of-00044.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00044.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00035-of-00044.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00036-of-00044.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00035-of-00044.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00035-of-00044.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00037-of-00044.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00036-of-00044.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00036-of-00044.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00036-of-00044.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00037-of-00044.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00038-of-00044.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00037-of-00044.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00037-of-00044.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00039-of-00044.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00038-of-00044.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00038-of-00044.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00038-of-00044.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00039-of-00044.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00040-of-00044.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00039-of-00044.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00039-of-00044.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00041-of-00044.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00040-of-00044.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00040-of-00044.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00040-of-00044.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00041-of-00044.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00006-of-00044.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00005-of-00044.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00005-of-00044.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00042-of-00044.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.60.self_attn.k_norm.weight": "model-00041-of-00044.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.60.self_attn.q_norm.weight": "model-00041-of-00044.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00043-of-00044.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.61.self_attn.k_norm.weight": "model-00042-of-00044.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.61.self_attn.q_norm.weight": "model-00042-of-00044.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00042-of-00044.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.self_attn.k_norm.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.self_attn.q_norm.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00043-of-00044.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00044-of-00044.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00044-of-00044.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00044-of-00044.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00044-of-00044.safetensors",
+    "model.layers.63.self_attn.k_norm.weight": "model-00043-of-00044.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00044-of-00044.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00044-of-00044.safetensors",
+    "model.layers.63.self_attn.q_norm.weight": "model-00043-of-00044.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00044-of-00044.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00044-of-00044.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00007-of-00044.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00006-of-00044.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00006-of-00044.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00044.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00044.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00008-of-00044.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00007-of-00044.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00007-of-00044.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00044.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00044.safetensors",
+    "model.norm.weight": "model-00044-of-00044.safetensors"
+  }
+}

output-00001-of-00005.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4c6a32e077c2df7f5ce4a657c54e0aa9233aa016aed7ee68cf1491669fdc03
+size 8579219212

output-00002-of-00005.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ebaa118318c6c0445605620bfeb33df71f94c6732a6533050f8f7afc24730a7f
+size 8532909708

output-00003-of-00005.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8bee3b42cfa78b98a682f4ea5e5aa0f8bab24210f7c1c0bd791feafb4072e3
+size 8498671002

output-00004-of-00005.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b0e530a18c0f159aa5ef34ba5d33764880099bdcb586c9043dc96d676430a1
+size 8524537128

output-00005-of-00005.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:35ca721906a2733ca21892d7468ea049a6862a35d1e6b2e2c9ca283afeeba577
+size 7093655058

place-your-models-here.txt ADDED Viewed

File without changes

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,23 @@

+{
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c69a7ea6c0927dfac8c349186ebcf0466a4723c21cbdb2e850cf559f0bee92b8
+size 12777433

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,330 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|EXTRA_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|EXTRA_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|EXTRA_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|EXTRA_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|EXTRA_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|EXTRA_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|EXTRA_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|EXTRA_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|EXTRA_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<BOS_TOKEN>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are a large language model called Command R+ built by the company Cohere. You act as a brilliant, sophisticated, AI-assistant chatbot trained to assist human users by providing thorough responses.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{'\n\n## Available Tools\nHere is a list of tools that you have available to you:\n\n'}}{% for tool in tools %}{% if loop.index0 != 0 %}{{ '\n\n'}}{% endif %}{{'```python\ndef ' + tool.name + '('}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ ', '}}{% endif %}{{param_name}}: {% if not param_fields.required %}{{'Optional[' + param_fields.type + '] = None'}}{% else %}{{ param_fields.type }}{% endif %}{% endfor %}{{ ') -> List[Dict]:\n    \"\"\"'}}{{ tool.description }}{% if tool.parameter_definitions|length != 0 %}{{ '\n\n    Args:\n        '}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ '\n        ' }}{% endif %}{{ param_name + ' ('}}{% if not param_fields.required %}{{'Optional[' + param_fields.type + ']'}}{% else %}{{ param_fields.type }}{% endif %}{{ '): ' + param_fields.description }}{% endfor %}{% endif %}{{ '\n    \"\"\"\n    pass\n```' }}{% endfor %}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \\'Action:\\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:\n```json\n[\n    {\n        \"tool_name\": title of the tool in the specification,\n        \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n    }\n]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    },
+    {
+      "name": "rag",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '<results>' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{value}}\n{% endfor %}{% endfor %}{{ '</results>'}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Carefully perform the following instructions, in order, starting each with a new line.\n' }}{{ 'Firstly, Decide which of the retrieved documents are relevant to the user\\'s last input by writing \\'Relevant Documents:\\' followed by comma-separated list of document numbers. If none are relevant, you should instead write \\'None\\'.\n' }}{{ 'Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user\\'s last input by writing \\'Cited Documents:\\' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write \\'None\\'.\n' }}{% if citation_mode=='accurate' %}{{ 'Thirdly, Write \\'Answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.\n' }}{% endif %}{{ 'Finally, Write \\'Grounded answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    }
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}