Upload DeepSeek pretrained multilingual model (90k steps)

README.md

@@ -0,0 +1,77 @@
+---
+language: 
+- en
+- te  
+- sa
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- multilingual
+- pretrained
+- deepseek
+- base-model
+license: apache-2.0
+model_type: deepseek
+---
+
+# asrith05/deepseek_pretrain_90k
+
+This is a pretrained multilingual model based on DeepSeek architecture, trained on English, Telugu, and Sanskrit data.
+
+## Model Details
+- **Base Architecture**: DeepSeek
+- **Languages**: English, Telugu, Sanskrit  
+- **Training Stage**: Pretraining (90k steps)
+- **Model Type**: Base model (not fine-tuned)
+- **Size**: ~1253MB
+
+## Description
+
+This model represents the pretrained base version before any task-specific fine-tuning. It has been trained on a diverse multilingual corpus and can be used as a foundation for various downstream tasks.
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_name = "asrith05/deepseek_pretrain_90k"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Example usage
+prompt = "The quick brown fox"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=50, temperature=0.7)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Training Details
+
+- **Training Steps**: 90,000
+- **Architecture**: DeepSeek-based transformer
+- **Context Length**: 2048 tokens
+- **Vocabulary**: Multilingual (English/Telugu/Sanskrit)
+
+## Intended Use
+
+This model is intended as a base model for:
+- Fine-tuning on specific tasks
+- Research in multilingual NLP
+- Building specialized applications
+
+## Limitations
+
+- This is a base model and may require fine-tuning for specific tasks
+- Generated content should be reviewed for accuracy and appropriateness
+- May reflect biases present in training data
+
+## Training Data
+
+The model was trained on a curated multilingual corpus including:
+- English text from various sources
+- Telugu language content
+- Sanskrit texts and literature
+
+## License
+
+This model is released under the Apache 2.0 License.

config.json

@@ -0,0 +1,44 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "first_k_dense_replace": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 4096,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "n_group": 8,
+  "n_routed_experts": 0,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 12,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 12,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_head_dim": 192,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_interleave": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "routed_scaling_factor": 2.5,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "v_head_dim": 128,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "transformers_version": "4.51.3",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45de2ca2d782d95ca5a22c0f398e6febc3e565a5f9237dddb7f00a1b8cabd238
+size 436535952

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d910dbc5dadbff30e2de1dd3fd292d41c5b83b1682b8dfc6bb2980a1f7ead11
+size 873103610

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf4d700cdd7ef81bf005d2842e2f669e1810471cfce670ab79872c6ee698af7
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7420e5809b6f02bb50f1ec4f1387ea70e02322cdb51ae3c0e3e3967eb0e7fc99
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5755e18bdcf3818890c58896161c3db1bc077c16a686b5e001d3c19630a5a0ef
+size 1064

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>"
+}

tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<en>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<te>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<sa>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5617fa164ef7140269d9c8d1432d43a7a3cd19108325fd0c61103fc9da846e
+size 5368