GPTQ model commit

config.json

@@ -0,0 +1,92 @@
+{
+    "_name_or_path": "/workspace/process/dillfrescott_sonya-medium-x8-moe/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": 8192,
+    "model_type": "mixtral",
+    "num_attention_heads": 32,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "quantization_config": {
+        "batch_size": 1,
+        "bits": 8,
+        "block_name_to_quantize": null,
+        "cache_block_outputs": true,
+        "damp_percent": 0.1,
+        "desc_act": true,
+        "exllama_config": {
+            "version": 1
+        },
+        "group_size": -1,
+        "max_input_length": null,
+        "model_seqlen": null,
+        "module_name_preceding_first_block": null,
+        "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"
+            ]
+        ],
+        "pad_token_id": null,
+        "quant_method": "gptq",
+        "sym": true,
+        "tokenizer": null,
+        "true_sequential": true,
+        "use_cuda_fp16": false,
+        "use_exllama": true
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "router_aux_loss_coef": 0.001,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.37.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae15ebb832a772e131cfe1607c5d94a89f12822e3b5634654722671ec6be3b3
+size 48974696016

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff7845730dde035f21940597ef5ce96ebaeb0b41f27cdd570508754caa03799
+size 21316520536

quantize_config.json

@@ -0,0 +1,8 @@
+{
+    "bits": 8,
+    "group_size": -1,
+    "damp_percent": 0.1,
+    "desc_act": true,
+    "sym": true,
+    "true_sequential": true
+}

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}