Nuovo training DPO con Mistral-7B-Instruct-v0.2, modelli aggiornati

README.md

@@ -1,22 +1 @@
----
-base_model: meta-llama/Llama-2-7b-hf
-tags:
-- LoRA
-- bittensor
-- gradients
-license: apache-2.0
----
-
-# Submission for task `dpo_test_finale_007`
-
-Fine-tuned using LoRA on dynamic dataset.
-
-- Task ID: `dpo_test_finale_007`
-- Repo: `dpo_test_finale_007`
-- SHA256: 5fa30211ee0266cbc3c9828a45679020d334b290c39d60fd8666fbe8c510af75
-- Timestamp: 2025-07-30T17:24:34.233691
-## URLs per validator
-
-- [Adapter Model](https://huggingface.co/raniero/dpo_test_finale_007/resolve/main/adapter_model.safetensors)
-- [Adapter Config](https://huggingface.co/raniero/dpo_test_finale_007/raw/main/adapter_config.json)
-- [README](https://huggingface.co/raniero/dpo_test_finale_007/raw/main/README.md)
+Modello addestrato con DPOTask

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "peft_type": "LORA",
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "revision": null,
   "task_type": "CAUSAL_LM",
   "inference_mode": false,
@@ -17,5 +17,10 @@
   "modules_to_save": null,
   "init_lora_weights": true,
   "layers_to_transform": null,
-  "layers_pattern": null
-}
+  "layers_pattern": null,
+  "rank_pattern": {},
+  "alpha_pattern": {},
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "loftq_config": {}
+}

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa30211ee0266cbc3c9828a45679020d334b290c39d60fd8666fbe8c510af75
+oid sha256:160e8454f5c4745fe0d9954328e167444c9193b788f1f1042ada27485b551a07
 size 13648400