Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-license: other
+license: apache-2.0
 library_name: transformers
 base_model: nbeerbower/Mistral-Small-Drummer-22B
 datasets:
@@ -26,7 +26,8 @@ model-index:
       value: 63.31
       name: strict accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -41,7 +42,8 @@ model-index:
       value: 40.12
       name: normalized accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -56,7 +58,8 @@ model-index:
       value: 16.69
       name: exact match
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -71,7 +74,8 @@ model-index:
       value: 12.42
       name: acc_norm
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -86,7 +90,8 @@ model-index:
       value: 9.8
       name: acc_norm
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -103,7 +108,8 @@ model-index:
       value: 34.39
       name: accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Mistral-Small-Drummer-22B
       name: Open LLM Leaderboard
 ---
 
@@ -111,6 +117,28 @@ model-index:
 This model was converted to GGUF format from [`nbeerbower/Mistral-Small-Drummer-22B`](https://huggingface.co/nbeerbower/Mistral-Small-Drummer-22B) 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/nbeerbower/Mistral-Small-Drummer-22B) for more details on the model.
 
+---
+Model details:
+-
+mistralai/Mistral-Small-Instruct-2409 finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo.
+
+Method
+ORPO tuned with 2xA40 on RunPod for 1 epoch.
+
+learning_rate=4e-6,
+lr_scheduler_type="linear",
+beta=0.1,
+per_device_train_batch_size=4,
+per_device_eval_batch_size=4,
+gradient_accumulation_steps=8,
+optim="paged_adamw_8bit",
+num_train_epochs=1,
+
+Dataset was prepared using Mistral-Small Instruct format.
+
+Fine-tune Llama 3 with ORPO
+
+---
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)
 
@@ -149,4 +177,4 @@ Step 3: Run inference through the main binary.
 or 
 ```
 ./llama-server --hf-repo Triangle104/Mistral-Small-Drummer-22B-Q8_0-GGUF --hf-file mistral-small-drummer-22b-q8_0.gguf -c 2048
-```
+```