Upload 5 files

config.json

@@ -0,0 +1,29 @@
+{
+  "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": true,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.1",
+  "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": "4.36.1"
+}

model_desc.json

@@ -0,0 +1 @@
+{"serving_type": "PytorchV2.0.0_TextGeneration_Mixtral_8x7B_Instruct_V0.1_SFT", "train_type": "sft", "generate_args": {"temperature": 0.95, "top_p": 0.7}}

prompt_template.json

@@ -0,0 +1 @@
+{"prompt_template": "AI_CHATBOT_TEMPLATE", "AI_CHATBOT_TEMPLATE": {"template": "{input}", "history_qa_template": "<s>[INST] {} [/INST] {}</s>", "latest_question_template": "<s>[INST] {} [/INST]", "input_variables": ["input"], "model_special_token": false, "with_round_index": false}}

pytorch_model-00001.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc9819ce60a5ce0b7dc6bf3a66148a196723813a0369718bb7e05cecfeb21570
+size 927074943