Upload MixtralForCausalLM

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "TheBloke/Mixtral-8x7B-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": 0,
+  "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,
+    "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,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0",
+  "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": "4.36.0"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e88d8d6c5e3552c78e453235568a6e5f282ca7c8f2a91b6071769c77939e503
+size 1974135120

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60dcc80b677c8c1757bad5169a71af78e00ad42a4cabc95b10c15b83c5e8e99a
+size 1977005424

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f627ecefbc8d8e2f4d69a706fd0d6485f43b40468028e9c0d828387d7d23aff9
+size 1985306712

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cfee1a67b054c1315fa8d512c73ac26a71cd315d9522e674dac4bb6d6beaf5e
+size 1977000368

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e78ba09c412dfe11ef9593012bf056895f80a2a760cd01fbfbd888be8a7673
+size 1977000704

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b7a908d026e9156db4f274579baf886ae8b184377b3ce47013580d8ceac8f4
+size 1985307088

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8396e3b6a7ecedcbc32eeec12d7e21b7d3619a036bfa75c61f0e3dd34965f480
+size 1977005800

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c7acefd34768894a131ef393df9bc9d3d22725e0a662f62f945f51beec28da
+size 1977000688

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbd3161a9878385b488b4d50f5480f04e0fe27533e25202a311033148324e6f
+size 1977000704

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa82f130e7ca6f27a472feac22526e318a1815b2bf90fdb3dfb0f9c7f239aa4e
+size 1985307088

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45929a231c38c7ff6283c0041f619671f2aee19fe56c46cf4a7166744ae46397
+size 1977005808

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f32646e51abd846079c81b1360d06e094c7aef58e375953e01125b44e72ffc
+size 1779283888

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4961bad525a4915196cf836de572294aff797a7737317314732eaa276e9f694c
+size 262144128