commit 717ee6ea981d62c732120646baf46e74a5191141 Author: ModelHub XC Date: Mon Nov 2 09:23:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Flexan/Blake-XTM-Arc-3B-V1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88266db --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +Blake-XTM-Arc-3B-V1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc-3B-V1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Blake-XTM-Arc-3B-V1.IQ3_M.gguf b/Blake-XTM-Arc-3B-V1.IQ3_M.gguf new file mode 100644 index 0000000..07d2637 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f7d54b591dfa53ab429439cfe427224066bfec21f6c59a32211aa18363a047c +size 1320458880 diff --git a/Blake-XTM-Arc-3B-V1.IQ3_S.gguf b/Blake-XTM-Arc-3B-V1.IQ3_S.gguf new file mode 100644 index 0000000..667025b --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae6985c1c8cbbbd73ce0e01f88cefb749035700de36f02aab8c531a5c428386 +size 1250826880 diff --git a/Blake-XTM-Arc-3B-V1.IQ3_XS.gguf b/Blake-XTM-Arc-3B-V1.IQ3_XS.gguf new file mode 100644 index 0000000..5f6206c --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4d037e6c0c576b6303b06875eb8a6b467489f9d6c5793276b97687d55b6c5b +size 1201674880 diff --git a/Blake-XTM-Arc-3B-V1.IQ4_XS.gguf b/Blake-XTM-Arc-3B-V1.IQ4_XS.gguf new file mode 100644 index 0000000..fbdeb32 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb9bef26f4bf4615fb6e751c40a5fd36388d6a6c3304547812c7565e615d8a5 +size 1536113280 diff --git a/Blake-XTM-Arc-3B-V1.Q2_K.gguf b/Blake-XTM-Arc-3B-V1.Q2_K.gguf new file mode 100644 index 0000000..9c3d7ab --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6216a32b0d04d33ab20e307f653640a9b2618dc6015f55ad55a6a62b2609b7a +size 1109719680 diff --git a/Blake-XTM-Arc-3B-V1.Q3_K_L.gguf b/Blake-XTM-Arc-3B-V1.Q3_K_L.gguf new file mode 100644 index 0000000..2489f4a --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998541e6d875a3b35cdf8ba40c85da1a4d11e27d4a8a6473edb71f31f3436195 +size 1575230080 diff --git a/Blake-XTM-Arc-3B-V1.Q3_K_M.gguf b/Blake-XTM-Arc-3B-V1.Q3_K_M.gguf new file mode 100644 index 0000000..faa5881 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:559e37f05e151aaadf3a5ce71a9a5e88a19362d775ffd722f9dbe16e6fe150bf +size 1426135680 diff --git a/Blake-XTM-Arc-3B-V1.Q3_K_S.gguf b/Blake-XTM-Arc-3B-V1.Q3_K_S.gguf new file mode 100644 index 0000000..9de8219 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01a210914feaf4aa075b4155f848fc715a2b6bc7afea5826f69068313e1b733 +size 1250826880 diff --git a/Blake-XTM-Arc-3B-V1.Q4_K_M.gguf b/Blake-XTM-Arc-3B-V1.Q4_K_M.gguf new file mode 100644 index 0000000..cb97ce3 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:407e388bc2ddad3cf1a8b92ac49c1518828a060bebdcad7f9b1eea1e73ca0b40 +size 1737636480 diff --git a/Blake-XTM-Arc-3B-V1.Q4_K_S.gguf b/Blake-XTM-Arc-3B-V1.Q4_K_S.gguf new file mode 100644 index 0000000..b52f111 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5296bf2db2c555b943a6be22e58a8103cedf34e945d11b1e8c783081f37ab681 +size 1618852480 diff --git a/Blake-XTM-Arc-3B-V1.Q5_K_M.gguf b/Blake-XTM-Arc-3B-V1.Q5_K_M.gguf new file mode 100644 index 0000000..479edfd --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e01c76ff43d89e3a4bc769155521a19946e516b2efeeb857ace921fb337e071 +size 2003057280 diff --git a/Blake-XTM-Arc-3B-V1.Q5_K_S.gguf b/Blake-XTM-Arc-3B-V1.Q5_K_S.gguf new file mode 100644 index 0000000..096139a --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c79b008b6ebba8d80708727054ff45ba9b31daadfbfe13d0b11ec2159c71a94 +size 1933425280 diff --git a/Blake-XTM-Arc-3B-V1.Q6_K.gguf b/Blake-XTM-Arc-3B-V1.Q6_K.gguf new file mode 100644 index 0000000..6a8fc59 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef7700c4e7ccc77ff796f706c03d4fbe4e9f076cd6c8b72befeb98d8dd857194 +size 2285066880 diff --git a/Blake-XTM-Arc-3B-V1.Q8_0.gguf b/Blake-XTM-Arc-3B-V1.Q8_0.gguf new file mode 100644 index 0000000..c71b754 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68728f1f4c6f2b8c059b53881211625ca583b77f74fea9958271f5d54124d57e +size 2958039680 diff --git a/Blake-XTM-Arc-3B-V1.f16.gguf b/Blake-XTM-Arc-3B-V1.f16.gguf new file mode 100644 index 0000000..b80c7b4 --- /dev/null +++ b/Blake-XTM-Arc-3B-V1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ecdc974be7a62197a2167c31dda5610692dcc1f3ac5928a8d8d1f571b60720e +size 5563095680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..619d9ca --- /dev/null +++ b/README.md @@ -0,0 +1,128 @@ +--- +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. + +> [!WARNING] +> **Warning:** this model was finetuned on a **non-instruct** base model. This was an oversight, but it may impact model performance. + +## 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|> +``` \ No newline at end of file