Upload DeepseekV2ForCausalLM

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct--configuration_deepseek.DeepseekV2Config",
+    "AutoModel": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct--modeling_deepseek.DeepseekV2Model",
+    "AutoModelForCausalLM": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct--modeling_deepseek.DeepseekV2ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 1408,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 27,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "q_lora_rank": null,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 0.707,
+    "mscale_all_dim": 0.707,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "do_sample": true,
+  "eos_token_id": 100001,
+  "temperature": 0.3,
+  "top_p": 0.95,
+  "transformers_version": "4.42.3"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372d18cc4262712d90e686acae58484f76c32a9241b68729b4e6b286396d0b03
+size 4994763632

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf127ab17c084065ed9ad3d2de0c5718e24844c07c0ee50d7da1405bd43c68ba
+size 4995044944

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708a2d402d8b5e86b3bd0a0660f117db7128640d6d060c0272f2335f77bc71f0
+size 4996085000

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2b507316f1068c2cd789ce82fbc1eab2eef4fe5eae874dab408490d253c467
+size 4996085224

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925939e2bb55d61c9d81b2ab189ff3ae1c85f47c42ed0eb8a96fc129d5e67d81
+size 4996085224

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfa9122b57fa6d2048012aee82d90cb306b549fdfc71b5b49d0b0754edf8822
+size 4995045792

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfe9a7b4994de5b447ca852d98d56b19b7424d2c540eddebd34bb8e5dd00383
+size 1440515736