Upload DeepSeek-V3 Mini 50M trained model

README.md

@@ -0,0 +1,35 @@
+# DeepSeek-V3 Mini 50M Parameters
+
+A compact version of DeepSeek-V3 Mini with exactly **58,283,136 parameters** (reduced from ~181M).
+
+## Model Specifications
+
+- **Parameters**: 58,283,136
+- **Hidden Size**: 448 
+- **Layers**: 6 
+- **Attention Heads**: 8 
+- **Intermediate Size**: 1200 
+- **Memory (FP16)**: ~111.2 MB
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("./deepseek_v3_mini_50m")
+tokenizer = AutoTokenizer.from_pretrained("./deepseek_v3_mini_50m")
+
+# Quick test
+inputs = tokenizer("The future of AI is", return_tensors="pt")
+outputs = model.generate(**inputs, max_length=50)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Reductions Applied
+
+- Hidden Size: 448 
+- Layers: 6 
+- Attention Heads: 8 
+- Intermediate Size: 1200 
+- KV LoRA Rank: 96
+

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{ message['content'] }}{% endfor %}

config.json

@@ -0,0 +1,85 @@
+{
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "architectures": null,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": 50256,
+  "pad_token_id": 50255,
+  "eos_token_id": 50256,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "task_specific_params": null,
+  "problem_type": null,
+  "_name_or_path": "",
+  "transformers_version": "4.52.4",
+  "vocab_size": 50257,
+  "hidden_size": 448,
+  "num_hidden_layers": 6,
+  "num_attention_heads": 8,
+  "intermediate_size": 1200,
+  "max_position_embeddings": 2048,
+  "kv_lora_rank": 96,
+  "qk_nope_head_dim": 48,
+  "qk_rope_head_dim": 16,
+  "v_head_dim": 64,
+  "n_predicted_tokens": 2,
+  "use_mtp": true,
+  "layer_norm_eps": 1e-06,
+  "dropout_prob": 0.1,
+  "rope_theta": 10000.0,
+  "use_cache": true,
+  "hidden_act": "silu",
+  "qk_head_dim": 64,
+  "head_dim": 56,
+  "model_type": "deepseek_v3_mini_50m",
+  "original_param_count": 58283136,
+  "weights_properly_tied": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4daaf5af62832cc8ac1fb54295eab74a43836482fdf7587c5c73a94a37f7e38e
+size 116572832

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "Ġgazed",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "Ġgazed",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}