Upload MixtralForCausalLM

config.json

@@ -0,0 +1,106 @@
+{
+  "_name_or_path": "TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ",
+  "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": 2,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "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.0.w2",
+        "block_sparse_moe.experts.0.w3"
+      ],
+      [
+        "block_sparse_moe.experts.1.w1",
+        "block_sparse_moe.experts.1.w2",
+        "block_sparse_moe.experts.1.w3"
+      ],
+      [
+        "block_sparse_moe.experts.2.w1",
+        "block_sparse_moe.experts.2.w2",
+        "block_sparse_moe.experts.2.w3"
+      ],
+      [
+        "block_sparse_moe.experts.3.w1",
+        "block_sparse_moe.experts.3.w2",
+        "block_sparse_moe.experts.3.w3"
+      ],
+      [
+        "block_sparse_moe.experts.4.w1",
+        "block_sparse_moe.experts.4.w2",
+        "block_sparse_moe.experts.4.w3"
+      ],
+      [
+        "block_sparse_moe.experts.5.w1",
+        "block_sparse_moe.experts.5.w2",
+        "block_sparse_moe.experts.5.w3"
+      ],
+      [
+        "block_sparse_moe.experts.6.w1",
+        "block_sparse_moe.experts.6.w2",
+        "block_sparse_moe.experts.6.w3"
+      ],
+      [
+        "block_sparse_moe.experts.7.w1",
+        "block_sparse_moe.experts.7.w2",
+        "block_sparse_moe.experts.7.w3"
+      ]
+    ],
+    "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": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c47108bd055998f6f21f87ce572e2cb5a8e3f0f069825458b6d5a37fb4d2324
+size 4973490648

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa547a6e9fea7fd5d0c524412a2493db8d8d725585b3662699a49bc59c70e752
+size 4976328272

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78e5e9e9a775b305ab283051f7bc02f38339c50760c19827e8601fba0b62227
+size 4976323664

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5ca20003ac33f8e93e725d48ca023f2127f3c542eade8669d990e6dfa54bec
+size 4995156968

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884385c30ac1f9ef490e7dae2481d8e6cd92e4d5e1d3f89f97ef8106a94134f7
+size 3890241880