GPTQ model commit

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.2132024765014648,
+    "eval_logits/rejected": -1.2924575805664062,
+    "eval_logps/chosen": -396.52020263671875,
+    "eval_logps/rejected": -409.31964111328125,
+    "eval_loss": 0.4216844439506531,
+    "eval_rewards/accuracies": 0.8134920597076416,
+    "eval_rewards/chosen": -0.1933162659406662,
+    "eval_rewards/margins": 2.1035311222076416,
+    "eval_rewards/rejected": -2.296847343444824,
+    "eval_runtime": 398.9749,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.013,
+    "eval_steps_per_second": 0.158,
+    "train_loss": 0.4461688995361328,
+    "train_runtime": 44067.2139,
+    "train_samples": 58917,
+    "train_samples_per_second": 1.337,
+    "train_steps_per_second": 0.021
+}

config.json

@@ -0,0 +1,82 @@
+{
+    "_name_or_path": "/workspace/process/argilla_notux-8x7b-v1/source",
+    "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": 8,
+    "output_router_logits": false,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "router_aux_loss_coef": 0.02,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.37.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "bits": 4,
+        "group_size": -1,
+        "damp_percent": 0.1,
+        "desc_act": true,
+        "static_groups": false,
+        "sym": true,
+        "true_sequential": true,
+        "model_name_or_path": null,
+        "model_file_base_name": "model",
+        "quant_method": "gptq",
+        "modules_in_block_to_quantize": [
+            [
+                "self_attn.k_proj",
+                "self_attn.v_proj",
+                "self_attn.q_proj"
+            ],
+            [
+                "self_attn.o_proj"
+            ],
+            [
+                "block_sparse_moe.experts.0.w1",
+                "block_sparse_moe.experts.1.w1",
+                "block_sparse_moe.experts.2.w1",
+                "block_sparse_moe.experts.3.w1",
+                "block_sparse_moe.experts.4.w1",
+                "block_sparse_moe.experts.5.w1",
+                "block_sparse_moe.experts.6.w1",
+                "block_sparse_moe.experts.7.w1",
+                "block_sparse_moe.experts.0.w3",
+                "block_sparse_moe.experts.1.w3",
+                "block_sparse_moe.experts.2.w3",
+                "block_sparse_moe.experts.3.w3",
+                "block_sparse_moe.experts.4.w3",
+                "block_sparse_moe.experts.5.w3",
+                "block_sparse_moe.experts.6.w3",
+                "block_sparse_moe.experts.7.w3"
+            ],
+            [
+                "block_sparse_moe.experts.0.w2",
+                "block_sparse_moe.experts.1.w2",
+                "block_sparse_moe.experts.2.w2",
+                "block_sparse_moe.experts.3.w2",
+                "block_sparse_moe.experts.4.w2",
+                "block_sparse_moe.experts.5.w2",
+                "block_sparse_moe.experts.6.w2",
+                "block_sparse_moe.experts.7.w2"
+            ]
+        ]
+    }
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.2132024765014648,
+    "eval_logits/rejected": -1.2924575805664062,
+    "eval_logps/chosen": -396.52020263671875,
+    "eval_logps/rejected": -409.31964111328125,
+    "eval_loss": 0.4216844439506531,
+    "eval_rewards/accuracies": 0.8134920597076416,
+    "eval_rewards/chosen": -0.1933162659406662,
+    "eval_rewards/margins": 2.1035311222076416,
+    "eval_rewards/rejected": -2.296847343444824,
+    "eval_runtime": 398.9749,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.013,
+    "eval_steps_per_second": 0.158
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b9de3bb27324cfaca44960ad329655822964863ce0ab61d009e4cdee3a42af
+size 23811549344

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": -1,
+  "damp_percent": 0.1,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": "model"
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.4461688995361328,
+    "train_runtime": 44067.2139,
+    "train_samples": 58917,
+    "train_samples_per_second": 1.337,
+    "train_steps_per_second": 0.021
+}