Update README.md

README.md

@@ -7,52 +7,37 @@ tags:
 - transformers
 - unsloth
 - mistral
-- trl
-- llama-cpp
-- gguf-my-repo
-base_model: sydonayrex/Barely-Regal-10.7B
+- gguf
+base_model: sydonayrex/AI-M3-10.7Bv2
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
-# sydonayrex/Barely-Regal-10.7B-Q6_K-GGUF
-This model was converted to GGUF format from [`sydonayrex/Barely-Regal-10.7B`](https://huggingface.co/sydonayrex/Barely-Regal-10.7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
-Refer to the [original model card](https://huggingface.co/sydonayrex/Barely-Regal-10.7B) for more details on the model.
-
-## Use with llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
-
-```bash
-brew install llama.cpp
-
-```
-Invoke the llama.cpp server or the CLI.
-
-### CLI:
-```bash
-llama --hf-repo sydonayrex/Barely-Regal-10.7B-Q6_K-GGUF --hf-file barely-regal-10.7b-q6_k.gguf -p "The meaning to life and the universe is"
-```
-
-### Server:
-```bash
-llama-server --hf-repo sydonayrex/Barely-Regal-10.7B-Q6_K-GGUF --hf-file barely-regal-10.7b-q6_k.gguf -c 2048
-```
-
-Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
-
-Step 1: Clone llama.cpp from GitHub.
-```
-git clone https://github.com/ggerganov/llama.cpp
-```
-
-Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
-```
-cd llama.cpp && LLAMA_CURL=1 make
-```
-
-Step 3: Run inference through the main binary.
-```
-./main --hf-repo sydonayrex/Barely-Regal-10.7B-Q6_K-GGUF --hf-file barely-regal-10.7b-q6_k.gguf -p "The meaning to life and the universe is"
-```
-or 
-```
-./server --hf-repo sydonayrex/Barely-Regal-10.7B-Q6_K-GGUF --hf-file barely-regal-10.7b-q6_k.gguf -c 2048
-```
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63603f4a3605bd411c196eef/cU9HbxD9OYFlpSxj6k6Es.jpeg)
+
+The name of the model is not a ding against the models performance, more of a commentary of our current ISP infrastructure within the U.S. and the fact that many of our ISPs have not moved into the era of AI yet. They still are primarily monopolies, they put forth arbitrary caps on data transfer, and they do not invest in improving services for customers in moderate to low density population areas. Some of us hit those arbitrary data caps just trying to upload and download models.
+
+The base of this model is Mistral Instruct 0.3 that has been supersized using task arithmetic to combine layers, when folding it in on itself. This new model I call Artificial Innovation - Mistral 3, which will show as AI-M3-10.7B as the base model on hub. In just my basic testing, this seems to have worked better than simple passthrough merging of layers, as the LLM has had less issues.
+
+In addition to the layer merging, the model has been further fine tuned using SFT using Unsloth to act as a base for further training and experimentation with DPO or ORPO (current DPO project in the process of being trained using Axolotl.)
+
+If you find the LLM is acting as if it has had a stroke, see if you have flash attn turned off and enable it is so. This seemed to correct any issues I had when running the model in LM Studio.
+
+GGUFs are available here:
+
+Q4_K_M and Q8: https://huggingface.co/sydonayrex/Barely-Regal-10.7B-Q6_K-GGUF
+
+Q5_K_M: https://huggingface.co/sydonayrex/Barely-Regal-10.7B-Q5_K_M-GGUF
+
+Q6_K: https://huggingface.co/sydonayrex/Barely-Regal-10.7B-Q6_K-GGUF
+
+# Uploaded  model
+
+- **Developed by:** sydonayrex
+- **License:** apache-2.0
+- **Finetuned from model :** sydonayrex/AI-M3-10.7Bv2
+
+This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)