--- license: cc-by-sa-4.0 datasets: - PJMixers-Dev/dolphin-deepseek-1k-think-1k-response-filtered-ShareGPT - Jofthomas/hermes-function-calling-thinking-V1 language: - en base_model: - microsoft/phi-2 pipeline_tag: text-generation --- # GGUF Files for Blake-XTM-Arc-3B-V1 These are the GGUF files for [Flexan/Blake-XTM-Arc-3B-V1](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1). | GGUF Link | Quantization | Description | | ---- | ----- | ----------- | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q2_K.gguf) | Q2_K | Lowest quality | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.IQ3_XS.gguf) | IQ3_XS | Integer quant | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q3_K_S.gguf) | Q3_K_S | | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.IQ3_S.gguf) | IQ3_S | Integer quant, preferable over Q3_K_S | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.IQ3_M.gguf) | IQ3_M | Integer quant | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q3_K_M.gguf) | Q3_K_M | | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q3_K_L.gguf) | Q3_K_L | | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.IQ4_XS.gguf) | IQ4_XS | Integer quant | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q4_K_S.gguf) | Q4_K_S | Fast with good performance | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q4_K_M.gguf) | Q4_K_M | **Recommended:** Perfect mix of speed and performance | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q5_K_S.gguf) | Q5_K_S | | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q5_K_M.gguf) | Q5_K_M | | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q6_K.gguf) | Q6_K | Very good quality | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.Q8_0.gguf) | Q8_0 | Best quality | | [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-3B-V1-GGUF/resolve/main/Blake-XTM-Arc-3B-V1.f16.gguf) | f16 | Full precision, don't bother; use a quant | # Model Card for Blake-XTM Arc 3B (V1) Blake-XTM Arc 3B (V1) is a 3B large language model used for text generation. It was trained to reason and optionally call provided tools. ## Model Details ### Model Description Blake-XTM Arc 3B (V1) is a 3B parameter instruct LLM trained to think and optionally call a tool. It only supports using one tool per assistant message (no parallel tool calling). The model was LoRA fine-tuned with [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) as base model. ### Chat Format Blake-XTM Arc 3B (V1) uses the ChatML format, e.g.: ```text <|im_start|>system System message<|im_end|> <|im_start|>user User prompt<|im_end|> <|im_start|>assistant Assistant response<|im_end|> ``` ### Model Usage The assistant response can have the following three formats (the contents are examples and were not generated from the model): 1. Only response: ```text <|im_start|>assistant Hello! How may I assist you today?<|im_end|> ``` 2. Thought process and response: ```text <|im_start|>assistant <|think_start|>The user has greeted me with a simple message. I should think about how to respond to them. Since the user sent a simple greeting, I should reply with a greeting that matches their energy. Alright, I can reply with a message like 'Hello! How can I help you?'<|think_end|> Hello! How may I assist you today?<|im_end|> ``` 3. Thought process and tool call: ```text <|im_start|>assistant <|think_start|>The user has asked me to find all restaurants near Paris. Hmm... let me think this through thoroughly. I can see that I have a tool available called 'find_restaurants', which I might be able to use for this purpose. Alright, I think I should use the `find_restaurants` tool to find the restaurants near Paris. For the `city` parameter, I'll use 'Paris', and for the `country` parameter, I'll fill in `France`. Okay, I can go ahead and make the tool call now.<|think_end|> <|tool_start|>{'name': 'find_restaurants', 'arguments': {'city': 'Paris', 'country': 'France'}}<|tool_end|><|im_end|> ``` We recommend using the following system prompts for your situation: - Only thought process: ```text You are an advanced reasoning model. You think between <|think_start|>...<|think_end|> tags. You must think if the user's request involves math or logical thinking/reasoning. ``` - Thought process and tool calling: ```text You are an advanced reasoning model with tool-calling capabilities. You think between <|think_start|>...<|think_end|> tags. You must think if the user's request involves math, logical thinking/reasoning, or when you want to consider using a tool. # Tools You have access to the following tools: [{'type': 'function', 'function': {'name': 'convert_currency', 'description': 'Convert currency from one type to another', 'parameters': {'type': 'object', 'properties': {'amount': {'type': 'number', 'description': 'The amount to be converted'}, 'from_currency': {'type': 'string', 'description': 'The currency to convert from'}, 'to_currency': {'type': 'string', 'description': 'The currency to convert to'}}, 'required': ['amount', 'from_currency', 'to_currency']}}}, {'type': 'function', 'function': {'name': 'get_random_joke', 'description': 'Get a random joke', 'parameters': {'type': 'object', 'properties': {}, 'required': []}}}] <\/tools>Use the following pydantic model json schema for each tool call you will make: {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']} To call a tool, write a JSON object with the name and arguments inside <|tool_start|>...<|tool_end|>. ``` For responding with a tool response, you can send a message as the `tool` user: ``` <|im_start|>assistant <|think_start|>The user has asked me to find all restaurants near Paris. Hmm... let me think this through thoroughly. I can see that I have a tool available called 'find_restaurants', which I might be able to use for this purpose. Alright, I think I should use the `find_restaurants` tool to find the restaurants near Paris. For the `city` parameter, I'll use 'Paris', and for the `country` parameter, I'll fill in `France`. Okay, I can go ahead and make the tool call now.<|think_end|> <|tool_start|>{'name': 'find_restaurants', 'arguments': {'city': 'Paris', 'country': 'France'}}<|tool_end|><|im_end|> <|im_start|>tool {'restaurants': [{'name': 'A Restaurant Name', 'rating': 4.5}]}<|im_end|> ```