Upload folder using huggingface_hub

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "/fsx/arthur/deepseek-r1",
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_head_dim": 192,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "modules_to_not_convert": null,
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370b2c57a0053d03a03ac8356a8bc082f8d1481919495fd260e263f99e53de2a
+size 4943762680

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698742e122e7c1436b74fabe539846283b90a64419e86f9958cc75c29898a294
+size 4220731256

model.safetensors.index.json

@@ -0,0 +1,70 @@
+{
+  "metadata": {
+    "total_size": 9164486304
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.kv_a_proj_with_mqa.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.kv_b_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_a_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_b_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.kv_a_proj_with_mqa.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.kv_b_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_a_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_b_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.kv_a_proj_with_mqa.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.kv_b_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_scale_inv": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_a_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_b_proj.weight_scale_inv": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}