Update tiny models for DeepseekV2ForCausalLM

chat_template.jinja

@@ -0,0 +1,5 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '
+
+' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '
+
+' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}

config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "dtype": "float32",
+  "eos_token_id": 100001,
+  "first_k_dense_replace": 0,
+  "head_dim": 64,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_decoder": true,
+  "kv_lora_rank": 32,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 16,
+  "n_group": null,
+  "n_routed_experts": 8,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 100001,
+  "pretraining_tp": 1,
+  "q_lora_rank": 16,
+  "qk_head_dim": 128,
+  "qk_nope_head_dim": 64,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": null,
+  "topk_method": "greedy",
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 100002
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 100001,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492d6957141ca0d9c1f021a493813e974036aae2fc6364174381ca71182de37d
+size 25960464

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}