commit 9c423daddafd7383c16fd8b6fd6c79d48c74cc61 Author: ModelHub XC Date: Fri Aug 7 16:33:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Llama-Deepsync-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5141058 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.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 +Llama-Deepsync-3B.F16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Deepsync-3B.F16.gguf b/Llama-Deepsync-3B.F16.gguf new file mode 100644 index 0000000..692ae3c --- /dev/null +++ b/Llama-Deepsync-3B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db5e9bf29b57c83a8fecb4c962a59de5e44602506c5af4253f57dbfe5c0e0bce +size 6433688352 diff --git a/Llama-Deepsync-3B.Q4_K_M.gguf b/Llama-Deepsync-3B.Q4_K_M.gguf new file mode 100644 index 0000000..1f70c42 --- /dev/null +++ b/Llama-Deepsync-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f11c4d9b10a732845d8e64dc9badfcbb7d94053bc5fe11f89bb8e99ed557f711 +size 2019377952 diff --git a/Llama-Deepsync-3B.Q5_K_M.gguf b/Llama-Deepsync-3B.Q5_K_M.gguf new file mode 100644 index 0000000..23d3388 --- /dev/null +++ b/Llama-Deepsync-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c76661a6e6811dae23ecabc994aa62418ee26e752f437a7c0b4d42625d4106 +size 2322154272 diff --git a/Llama-Deepsync-3B.Q8_0.gguf b/Llama-Deepsync-3B.Q8_0.gguf new file mode 100644 index 0000000..4c5b260 --- /dev/null +++ b/Llama-Deepsync-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20814bfb2beb7c599d6a8646ef200d496cb0d4b82184c6cbdf8f23d38a9f3b6c +size 3421899552 diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..33712ce --- /dev/null +++ b/Modelfile @@ -0,0 +1,57 @@ + +FROM /content/prithivMLmods/Llama-Deepsync-3B-GGUF/Llama-Deepsync-3B.F16.gguf +TEMPLATE """{{ if .Messages }} +{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> +{{- if .System }} + +{{ .System }} +{{- end }} +{{- if .Tools }} + +You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original use question. +{{- end }} +{{- end }}<|eot_id|> +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 }} +{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|> +{{- if and $.Tools $last }} + +Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt. + +Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables. + +{{ $.Tools }} +{{- end }} + +{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }} +{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|> +{{- if .ToolCalls }} + +{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }} +{{- else }} + +{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }} +{{- end }} +{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|> + +{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }} +{{- end }} +{{- end }} +{{- else }} +{{- if .System }}<|start_header_id|>system<|end_header_id|> + +{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> + +{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}""" +PARAMETER stop "<|start_header_id|>" +PARAMETER stop "<|end_header_id|>" +PARAMETER stop "<|eot_id|>" +PARAMETER stop "<|eom_id|>" +PARAMETER temperature 1.5 +PARAMETER min_p 0.1 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..aef2039 --- /dev/null +++ b/README.md @@ -0,0 +1,108 @@ +--- +license: creativeml-openrail-m +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +base_model: +- prithivMLmods/Llama-Deepsync-3B +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +- Llama +- CoT +- Code +- Math +- Deepsync +- 3b +--- +
+    .___                                                ___________.    
+  __| _/____   ____ ______  _________.__. ____   ____   \_____  \_ |__  
+ / __ |/ __ \_/ __ \\____ \/  ___<   |  |/    \_/ ___\    _(__  <| __ \ 
+/ /_/ \  ___/\  ___/|  |_> >___ \ \___  |   |  \  \___   /       \ \_\ \
+\____ |\___  >\___  >   __/____  >/ ____|___|  /\___  > /______  /___  /
+     \/    \/     \/|__|       \/ \/         \/     \/         \/    \/ 
+
+ +The **Llama-Deepsync-3B-GGUF** is a fine-tuned version of the **Llama-3.2-3B-Instruct** base model, designed for text generation tasks that require deep reasoning, logical structuring, and problem-solving. This model leverages its optimized architecture to provide accurate and contextually relevant outputs for complex queries, making it ideal for applications in education, programming, and creative writing. + +With its robust natural language processing capabilities, **Llama-Deepsync-3B** excels in generating step-by-step solutions, creative content, and logical analyses. Its architecture integrates advanced understanding of both structured and unstructured data, ensuring precise text generation aligned with user inputs. + +- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains. +- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots. +- **Long-context Support** up to 128K tokens and can generate up to 8K tokens. +- **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. + +# **Model Architecture** + +Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. + +# **Use with transformers** + +Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function. + +Make sure to update your transformers installation via `pip install --upgrade transformers`. + +```python +import torch +from transformers import pipeline + +model_id = "prithivMLmods/Llama-Deepsync-3B" +pipe = pipeline( + "text-generation", + model=model_id, + torch_dtype=torch.bfloat16, + device_map="auto", +) +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": "Who are you?"}, +] +outputs = pipe( + messages, + max_new_tokens=256, +) +print(outputs[0]["generated_text"][-1]) +``` + +Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes) + +# **Run with Ollama [Ollama Run]** + +Ollama makes running machine learning models simple and efficient. Follow these steps to set up and run your GGUF models quickly. + +## Quick Start: Step-by-Step Guide + +| Step | Description | Command / Instructions | +|------|-------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------| +| 1 | **Install Ollama 🦙** | Download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your system. | +| 2 | **Create Your Model File** | - Create a file named after your model, e.g., `metallama`. | +| | | - Add the following line to specify the base model: | +| | | ```bash | +| | | FROM Llama-3.2-1B.F16.gguf | +| | | ``` | +| | | - Ensure the base model file is in the same directory. | +| 3 | **Create and Patch the Model** | Run the following commands to create and verify your model: | +| | | ```bash | +| | | ollama create metallama -f ./metallama | +| | | ollama list | +| | | ``` | +| 4 | **Run the Model** | Use the following command to start your model: | +| | | ```bash | +| | | ollama run metallama | +| | | ``` | +| 5 | **Interact with the Model** | Once the model is running, interact with it: | +| | | ```plaintext | +| | | >>> Tell me about Space X. | +| | | Space X, the private aerospace company founded by Elon Musk, is revolutionizing space exploration... | +| | | ``` | + +## Conclusion +With Ollama, running and interacting with models is seamless. Start experimenting today! \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file