Upload NemotronHForCausalLM

config.json

@@ -12,7 +12,7 @@
   "expand": 2,
   "head_dim": 128,
   "hidden_dropout": 0.0,
-  "hidden_size": 8,
+  "hidden_size": 16,
   "initializer_range": 0.02,
   "intermediate_size": 32,
   "layer_norm_epsilon": 1e-05,
@@ -20,7 +20,7 @@
     "mamba",
     "attention"
   ],
-  "mamba_head_dim": 2,
+  "mamba_head_dim": 8,
   "mamba_hidden_act": "silu",
   "mamba_num_heads": 4,
   "mamba_proj_bias": false,
@@ -52,7 +52,7 @@
   "residual_in_fp32": false,
   "routed_scaling_factor": 1.0,
   "sliding_window": null,
-  "ssm_state_size": 8,
+  "ssm_state_size": 16,
   "tie_word_embeddings": false,
   "time_step_floor": 0.0001,
   "time_step_limit": [
@@ -64,7 +64,7 @@
   "time_step_max": 0.1,
   "time_step_min": 0.001,
   "topk_group": 1,
-  "transformers_version": "5.3.0.dev0",
+  "transformers_version": "5.3.0",
   "use_bias": false,
   "use_cache": true,
   "use_conv_bias": true,

generation_config.json

@@ -1,13 +1,10 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "do_sample": true,
-  "eos_token_id": [
-    2,
-    11
-  ],
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
   "pad_token_id": 0,
-  "temperature": 1.0,
-  "top_p": 1.0,
-  "transformers_version": "5.3.0.dev0"
+  "transformers_version": "5.3.0",
+  "use_cache": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760883f4d4754b5613061c8383e6ccdf7803180914562e26e5e5959f70e748b6
-size 4221632
+oid sha256:52e48197fa8403975baa3f2426192973fbc4859097b09a8c849eaa92f23e655c
+size 8444544