upload quantized model

config.json

@@ -0,0 +1,42 @@
+{
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": null,
+    "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,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "router_aux_loss_coef": 0.02,
+    "router_jitter_noise": 0.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.53.1",
+    "use_cache": true,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "ignore": [
+            "lm_head"
+        ],
+        "quant_algo": "W8A16",
+        "producer": {
+            "name": "modelopt",
+            "version": "0.33.0"
+        },
+        "quant_library": "modelopt"
+    }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.53.1"
+}

hf_quant_config.json

@@ -0,0 +1,13 @@
+{
+    "producer": {
+        "name": "modelopt",
+        "version": "0.33.0"
+    },
+    "quantization": {
+        "quant_algo": "W8A16",
+        "kv_cache_quant_algo": null,
+        "exclude_modules": [
+            "lm_head"
+        ]
+    }
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:176aa3665f47a8b5e6ae04c5b46c65752c3a60ab88788ff17b20a79a3d1fb25d
+size 4955095408

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9432d1fe99d25a442d8a0724a4a3a1f5368d79cb53a927f77654e6056aec4e1b
+size 4944781648

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf416c181043bf7fbca0380777e3c613152d995d74881d9be69e8e04669a558
+size 4986816160

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542c684e31043406917e1f93e13fa6c1b1fe98a21a0e78d4c63406eea0fae605
+size 4944740880

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271200e2055f476d149bc2feed24263c976ac906883403090deec938c4b1b4ba
+size 4944781848

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a4c2883f5603161b21dc64c2044dc8cfd52165099f2365b5a515ea8c329c3e
+size 4986816392

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a482f928a754bd363d01caa0382254f481be3fef072dfc024cd09aab9fc014
+size 4944740880

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c4b09834141570be165427dff7987ba84bcd975e88320bd8366420635ec4bd
+size 4986816392

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5626758919f77748fd69c2e518d32cf6146f34572ca8d05fe70e707eca388c
+size 4944781840

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d732d2a4ce8fec46d113fcc6f086113e7b447cc05694d8714e9420ec6b33fd
+size 2360936928

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": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}