Upload MambaForCausalLM

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "tiiuae/falcon-mamba-7b-instruct",
+  "architectures": [
+    "MambaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "conv_kernel": 4,
+  "eos_token_id": 11,
+  "expand": 16,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.1,
+  "intermediate_size": 8192,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mamba",
+  "num_hidden_layers": 64,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "state_size": 16,
+  "tie_word_embeddings": false,
+  "time_step_floor": 0.0001,
+  "time_step_init_scheme": "random",
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 256,
+  "time_step_scale": 1.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.0.dev0",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "use_mambapy": false,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    11,
+    10
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.45.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac36cdd7e1f774cd33304ae6f416817ffe44c329f3f135ec4b77ea444b2ec8c
+size 4891294152