From b1807d4ffc78e568e03438d73c20d3644836bbc5 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 4 Oct 2026 13:49:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: Flexan/Blake-XTM-Arc-GGUF Source: Original Platform --- .gitattributes | 50 +++++++++++++++ Blake-XTM-Arc.IQ3_M.gguf | 3 + Blake-XTM-Arc.IQ3_S.gguf | 3 + Blake-XTM-Arc.IQ3_XS.gguf | 3 + Blake-XTM-Arc.IQ4_XS.gguf | 3 + Blake-XTM-Arc.Q2_K.gguf | 3 + Blake-XTM-Arc.Q3_K_L.gguf | 3 + Blake-XTM-Arc.Q3_K_M.gguf | 3 + Blake-XTM-Arc.Q3_K_S.gguf | 3 + Blake-XTM-Arc.Q4_K_M.gguf | 3 + Blake-XTM-Arc.Q4_K_S.gguf | 3 + Blake-XTM-Arc.Q5_K_M.gguf | 3 + Blake-XTM-Arc.Q5_K_S.gguf | 3 + Blake-XTM-Arc.Q6_K.gguf | 3 + Blake-XTM-Arc.Q8_0.gguf | 3 + Blake-XTM-Arc.f16.gguf | 3 + README.md | 127 ++++++++++++++++++++++++++++++++++++++ 17 files changed, 222 insertions(+) create mode 100644 .gitattributes create mode 100644 Blake-XTM-Arc.IQ3_M.gguf create mode 100644 Blake-XTM-Arc.IQ3_S.gguf create mode 100644 Blake-XTM-Arc.IQ3_XS.gguf create mode 100644 Blake-XTM-Arc.IQ4_XS.gguf create mode 100644 Blake-XTM-Arc.Q2_K.gguf create mode 100644 Blake-XTM-Arc.Q3_K_L.gguf create mode 100644 Blake-XTM-Arc.Q3_K_M.gguf create mode 100644 Blake-XTM-Arc.Q3_K_S.gguf create mode 100644 Blake-XTM-Arc.Q4_K_M.gguf create mode 100644 Blake-XTM-Arc.Q4_K_S.gguf create mode 100644 Blake-XTM-Arc.Q5_K_M.gguf create mode 100644 Blake-XTM-Arc.Q5_K_S.gguf create mode 100644 Blake-XTM-Arc.Q6_K.gguf create mode 100644 Blake-XTM-Arc.Q8_0.gguf create mode 100644 Blake-XTM-Arc.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ae9f810 --- /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.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.f16.gguf filter=lfs diff=lfs merge=lfs -text +Blake-XTM-Arc.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Blake-XTM-Arc.IQ3_M.gguf b/Blake-XTM-Arc.IQ3_M.gguf new file mode 100644 index 0000000..f865bae --- /dev/null +++ b/Blake-XTM-Arc.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e32ae089ddf2b3bd30e4585753172ca34e351d98094573faa7f3ff6e0c95aeb +size 3284891648 diff --git a/Blake-XTM-Arc.IQ3_S.gguf b/Blake-XTM-Arc.IQ3_S.gguf new file mode 100644 index 0000000..39f3173 --- /dev/null +++ b/Blake-XTM-Arc.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee5ca7a265fcb921ba35012448fbc7e38b2f89c447f145faa361e9229b0fd644 +size 3182393344 diff --git a/Blake-XTM-Arc.IQ3_XS.gguf b/Blake-XTM-Arc.IQ3_XS.gguf new file mode 100644 index 0000000..cf5b511 --- /dev/null +++ b/Blake-XTM-Arc.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7616138aaf14e4a370c590854e54d9779e05595f2786cdb4e3ae9a9efab16d77 +size 3018815488 diff --git a/Blake-XTM-Arc.IQ4_XS.gguf b/Blake-XTM-Arc.IQ4_XS.gguf new file mode 100644 index 0000000..7b912f5 --- /dev/null +++ b/Blake-XTM-Arc.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f419892235b4b6087b72bcec9568bb00a015801773a8cb2115f353285275f800 +size 3944388608 diff --git a/Blake-XTM-Arc.Q2_K.gguf b/Blake-XTM-Arc.Q2_K.gguf new file mode 100644 index 0000000..dea6010 --- /dev/null +++ b/Blake-XTM-Arc.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8959bffa6176ce1c6e1725e5c48d38845fea988d74e9ae18dc13bd6d3cd043e +size 2719242240 diff --git a/Blake-XTM-Arc.Q3_K_L.gguf b/Blake-XTM-Arc.Q3_K_L.gguf new file mode 100644 index 0000000..817f14a --- /dev/null +++ b/Blake-XTM-Arc.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10e3e2c3ffcc7e9f0fd7fbb3b0d0d3dd69ce9035973aedb2386d8df61f84e42 +size 3822024704 diff --git a/Blake-XTM-Arc.Q3_K_M.gguf b/Blake-XTM-Arc.Q3_K_M.gguf new file mode 100644 index 0000000..0a7d18d --- /dev/null +++ b/Blake-XTM-Arc.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7daa97d6d19357dd1bb380dcfa678f658252a4e81af27a47cff310a1a5bbc012 +size 3518986240 diff --git a/Blake-XTM-Arc.Q3_K_S.gguf b/Blake-XTM-Arc.Q3_K_S.gguf new file mode 100644 index 0000000..92ca95b --- /dev/null +++ b/Blake-XTM-Arc.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d24e0f354193eb4495e13f28f34dc032fb575c223a522e1ce9bb25f14034038a +size 3164567552 diff --git a/Blake-XTM-Arc.Q4_K_M.gguf b/Blake-XTM-Arc.Q4_K_M.gguf new file mode 100644 index 0000000..db6b003 --- /dev/null +++ b/Blake-XTM-Arc.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d76c5fed9710a90a78f089438dd623daf40ffedde7f3ab188f7e5148391e42ca +size 4368439296 diff --git a/Blake-XTM-Arc.Q4_K_S.gguf b/Blake-XTM-Arc.Q4_K_S.gguf new file mode 100644 index 0000000..b8296f9 --- /dev/null +++ b/Blake-XTM-Arc.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272d6abc42478cc637febe28444d2abdfef1b86b9034b369ea370bc4157a6cc1 +size 4140374016 diff --git a/Blake-XTM-Arc.Q5_K_M.gguf b/Blake-XTM-Arc.Q5_K_M.gguf new file mode 100644 index 0000000..0ed6bf8 --- /dev/null +++ b/Blake-XTM-Arc.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93054436b01a8389a5c40b6e540c881bf12b97f5d9892affaaf8f20799becb5a +size 5131409408 diff --git a/Blake-XTM-Arc.Q5_K_S.gguf b/Blake-XTM-Arc.Q5_K_S.gguf new file mode 100644 index 0000000..9e73e75 --- /dev/null +++ b/Blake-XTM-Arc.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc0a0648027000687b9b4173277e0e0e0cd4b31043d67715b5ffd9bc875c0512 +size 4997715968 diff --git a/Blake-XTM-Arc.Q6_K.gguf b/Blake-XTM-Arc.Q6_K.gguf new file mode 100644 index 0000000..90ed001 --- /dev/null +++ b/Blake-XTM-Arc.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2545a164afac01a66818be9bb3d1bcef472b1c00d857300187ddc29618c9ad85 +size 5942065152 diff --git a/Blake-XTM-Arc.Q8_0.gguf b/Blake-XTM-Arc.Q8_0.gguf new file mode 100644 index 0000000..2efa177 --- /dev/null +++ b/Blake-XTM-Arc.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade038e8593ffd30a5b35d892b97fb71606670451bfa5f751904a189ab30e321 +size 7695857664 diff --git a/Blake-XTM-Arc.f16.gguf b/Blake-XTM-Arc.f16.gguf new file mode 100644 index 0000000..575f113 --- /dev/null +++ b/Blake-XTM-Arc.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72c91bc972477c62f8684f38791be5be4ab5a4de53dc90bf0c6a3ed4d3ee40d +size 14484731904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..73cc31c --- /dev/null +++ b/README.md @@ -0,0 +1,127 @@ +--- +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: +- Flexan/Blake-XTM-Arc +pipeline_tag: text-generation +--- +# GGUF Files for Blake-XTM-Arc + +These are the GGUF files for [Flexan/Blake-XTM-Arc](https://huggingface.co/Flexan/Blake-XTM-Arc). + +| GGUF Link | Quantization | Description | +| ---- | ----- | ----------- | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q2_K.gguf) | Q2_K | Lowest quality | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.IQ3_XS.gguf) | IQ3_XS | Integer quant | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q3_K_S.gguf) | Q3_K_S | | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.IQ3_S.gguf) | IQ3_S | Integer quant, preferable over Q3_K_S | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.IQ3_M.gguf) | IQ3_M | Integer quant | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q3_K_M.gguf) | Q3_K_M | | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q3_K_L.gguf) | Q3_K_L | | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.IQ4_XS.gguf) | IQ4_XS | Integer quant | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q4_K_S.gguf) | Q4_K_S | Fast with good performance | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q4_K_M.gguf) | Q4_K_M | **Recommended:** Perfect mix of speed and performance | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q5_K_S.gguf) | Q5_K_S | | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q5_K_M.gguf) | Q5_K_M | | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q6_K.gguf) | Q6_K | Very good quality | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.Q8_0.gguf) | Q8_0 | Best quality | +| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-GGUF/resolve/main/Blake-XTM-Arc.f16.gguf) | f16 | Full precision, don't bother; use a quant | + +# Model Card for Blake-XTM Arc + +Blake-XTM Arc is a 7B large language model used for text generation. +It was trained to reason and optionally call provided tools. + +## Model Details + +### Model Description + +Blake-XTM Arc is a 7B 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 [CatNyanster-7B](https://huggingface.co/arlineka/CatNyanster-7b) as base model, which was fine-tuned on [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1). + +### Chat Format + +Blake-XTM Arc 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|> + ``` + +**Warning:** The model seems to bias towards thought process + response, even for short prompts like "Hello," which may cause it to overthink. + +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': []}}}] + + 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