Training in progress, step 2000

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "neeleshg23/jamba-1.9b-5",
+  "architectures": [
+    "JambaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_layer_offset": 4,
+  "attn_layer_period": 8,
+  "bos_token_id": 1,
+  "d_model": 1024,
+  "eos_token_id": 2,
+  "expert_layer_offset": 1,
+  "expert_layer_period": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 256,
+  "mamba_expand": 2,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 2048,
+  "model_type": "jamba",
+  "num_attention_heads": 16,
+  "num_experts": 4,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 3,
+  "num_key_value_heads": 8,
+  "num_logits_to_keep": 1,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "use_mamba_kernels": true,
+  "vocab_size": 128256
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9f29554eaca2086ea34757e311ec3ce839758643c292e9af51698239c8668c
+size 3796550480

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfbba53b6dd8bf0c0cab2230ebd883b62d8b6779f3d8786a05f4642cc7c5592a
+size 5240