Upload MixtralForCausalLM

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "/fsx/alvaro.bartolome/Mixtral-8x7B-Instruct-v0.1-AWQ-INT4",
+  "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,
+  "quantization_config": {
+    "backend": "autoawq",
+    "bits": 4,
+    "do_fuse": false,
+    "exllama_config": null,
+    "fuse_max_seq_len": null,
+    "group_size": 128,
+    "modules_to_fuse": null,
+    "modules_to_not_convert": [
+      "gate"
+    ],
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "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": "float16",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.42.4"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bbbb3f904268ec47898be2e4e121c2f319487b1e6bc42b7235e5442c28d2de5
+size 4991356832

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14eaf2f4ab6e580430c6c3f39fbb19719a65aa2e8172d5607c1a078a4c41736
+size 4981921768

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b113937d4bcd0462ebc510eced2f2b6cf2c623bfea7b3c7281e7b68ab8dc672
+size 4973289064

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e966180a0ca240d7a327eb782ec0a63a73c0f569ffed3201f77f6690043b2f
+size 4973289080

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f30925aad4f05a7536d3fbb4ee0af1f04d065167ca55c5f3a43ba63feb06de9
+size 4734098376