Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: sarvamai/sarvam-1
+library_name: transformers
+model_name: sarvam_instruct
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for sarvam_instruct
+
+This model is a fine-tuned version of [sarvamai/sarvam-1](https://huggingface.co/sarvamai/sarvam-1).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Badribn/sarvam_instruct", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/badrinarayan-analytics-vidhya/openhathi_instruct_finetuning/runs/ajofpspr) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.48.3
+- Pytorch: 2.5.1
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "sarvamai/sarvam-1",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "embed_tokens",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bc0ab70105cc09d57a7bf8fbb9bac8ca0256c1b6a16eb67df21dd8dd330e3a
+size 610365024

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<pad>": 68097,
+  "<|im_end|>": 68096,
+  "<|im_start|>assistant": 68099,
+  "<|im_start|>system": 68100,
+  "<|im_start|>user": 68098
+}

runs/Mar11_05-24-17_215d55e723fe/events.out.tfevents.1741670744.215d55e723fe.1343.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9b5401e9c7abdb94742ef9e2ddf0877fe06d38377e2c34d77df2655f848391
+size 71717

special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>user",
+    "<|im_start|>assistant",
+    "<|im_start|>system",
+    "<|im_end|>",
+    "<s>",
+    "<pad>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd33409a577e8b416247587b0f5bd7a3eec245a1f18d4ec7793ff299ad3fbe2
+size 1935856

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098cd02c5f1b94c3e53ea7edd14aa01920e96a6f3d53efa4df79e52812e319ee
+size 5624