End of training

README.md

@@ -2,9 +2,22 @@
 license: mit
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- jan-hq/distilabel_dpo_pairs_binarized
+- argilla/OpenHermes2.5-dpo-binarized-alpha
+- jan-hq/capybara_dpo_binarized
+- jan-hq/bagel_dpo_binarized
+- jan-hq/ultrafeedback_preferences_cleaned_binarized
+- jan-hq/openmath_instruct_dpo_binarized
+- jan-hq/distil_math_dpo_binarized
+- jan-hq/evol_codealpaca_dpo_binarized
 base_model: TomGrc/FusionNet_7Bx2_MoE_v0.1
 model-index:
 - name: stealth-finance-v2-dpo-adapter
@@ -16,7 +29,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stealth-finance-v2-dpo-adapter
 
-This model is a fine-tuned version of [TomGrc/FusionNet_7Bx2_MoE_v0.1](https://huggingface.co/TomGrc/FusionNet_7Bx2_MoE_v0.1) on the None dataset.
+This model is a fine-tuned version of [TomGrc/FusionNet_7Bx2_MoE_v0.1](https://huggingface.co/TomGrc/FusionNet_7Bx2_MoE_v0.1) on the jan-hq/distilabel_dpo_pairs_binarized, the argilla/OpenHermes2.5-dpo-binarized-alpha, the jan-hq/capybara_dpo_binarized, the jan-hq/bagel_dpo_binarized, the jan-hq/ultrafeedback_preferences_cleaned_binarized, the jan-hq/openmath_instruct_dpo_binarized, the jan-hq/distil_math_dpo_binarized and the jan-hq/evol_codealpaca_dpo_binarized datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.1290
 - Rewards/chosen: -0.1799

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "TomGrc/FusionNet_7Bx2_MoE_v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}