Update README.md

README.md

@@ -1,5 +1,7 @@
 ---
 base_model: JetBrains/Mellum-4b-base
+datasets:
+- Etherll/CodeFIM-Rust-Mellum
 tags:
 - text-generation-inference
 - transformers
@@ -7,17 +9,66 @@ tags:
 - llama
 - trl
 - sft
+- code
+- rust
+- fill-in-the-middle
+- fim
+- text-generation
+- llm
 license: apache-2.0
 language:
 - en
+library_name: transformers
+model-index:
+- name: Etherll/Mellum-4b-sft-rust
+  results: []
 ---
+# Etherll/Mellum-4b-sft-rust
 
-# Uploaded  model
+**Etherll/Mellum-4b-sft-rust** is a large language model (LLM) fine-tuned specifically for **Rust code Fill-in-the-Middle (FIM)** tasks. It is built upon `JetBrains/Mellum-4b-base` model.
 
-- **Developed by:** Etherll
-- **License:** apache-2.0
-- **Finetuned from model :** JetBrains/Mellum-4b-base
+This model has been fine-tuned on the `Etherll/CodeFIM-Rust-Mellum` dataset, which comprises approximately 57,000 Rust-specific FIM examples, to enhance its proficiency in completing Rust code snippets accurately and contextually.
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+A GGUF version for CPU inference is also available: [Etherll/Mellum-4b-sft-rust-GGUF](https://huggingface.co/Etherll/Mellum-4b-sft-rust-GGUF).
+
+## Model Description
+
+This model leverages the LLaMA-style architecture of `Mellum-4b-base` (4 billion parameters) and its extensive pre-training on over 4 trillion tokens. The fine-tuning process focused on adapting the model to the nuances of Rust syntax and common coding patterns for FIM tasks.
+
+**Key Features:**
+*   **Specialized for Rust:** Optimized for Fill-in-the-Middle tasks in Rust.
+*   **Based on Mellum-4b-base:** Benefits from JetBrains' robust base model.
+*   **Efficient:** Suitable for both cloud and local deployment.
+*   **IDE Integration Ready:** Designed for use in developer tooling, and works particularly well with [Continue.dev](https://www.continue.dev/) for an enhanced coding assistant experience.
+
+## Fine-tuning Data
+*   **Dataset:** `Etherll/CodeFIM-Rust-Mellum`
+*   **Size:** ~57,000 rows
+*   **Focus:** Rust code Fill-in-the-Middle
+
+## FIM Format
+
+This model is trained to recognize a specific format for Fill-in-the-Middle tasks. When providing input for FIM, please use the following structure:
+
+```
+<filename>{{{filename}}}
+<fim_suffix>{{{suffix_code}}}<fim_prefix>{{{prefix_code}}}<fim_middle>
+```
+
+## How to Use
+
+## With Continue.dev
+
+For the best integrated development experience, it's highly recommended to use this model with [Continue.dev](https://www.continue.dev/).
+
+Refer to the [Continue.dev documentation](https://www.continue.dev/docs/setup/overview) for instructions on how to add custom LLMs.
+
+### GGUF Version
+
+A GGUF version is available at [Etherll/Mellum-4b-sft-rust-GGUF](https://huggingface.co/Etherll/Mellum-4b-sft-rust-GGUF).
+This format is suitable for local inference on CPU (and GPU with appropriate llama.cpp/Ollama builds) using tools like:
+*   [llama.cpp](https://github.com/ggerganov/llama.cpp)
+*   [Ollama](https://ollama.ai/)
+*   [LM Studio](https://lmstudio.ai/)
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)