sarvam1-sft/checkpoint-4272

sarvam1-sft/checkpoint-4272/chat_template.jinja

@@ -0,0 +1,22 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}
+{% for message in loop_messages %}
+{% if message['role'] not in ['user', 'assistant', 'tool_calls'] %}
+{{ raise_exception('Invalid role: ' + message['role'] + '. Must be user, assistant, or tool_calls.') }}
+{% endif %}
+{% if loop.index0 == 0 and system_message != false %}
+{% set content = '<<SYS>>
+' + system_message + '
+<</SYS>>
+
+' + message['content'] %}
+{% else %}
+{% set content = message['content'] %}
+{% endif %}
+{% if message['role'] == 'user' %}
+{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}
+{% elif message['role'] == 'assistant' %}
+{{ ' ' + content.strip() + ' ' + eos_token }}
+{% elif message['role'] == 'tool_calls' %}
+{{ ' [TOOL_CALLS] ' + content.strip() + ' [/TOOL_CALLS] ' }}
+{% endif %}
+{% endfor %}

sarvam1-sft/checkpoint-4272/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.17.0",
+  "use_cache": false,
+  "vocab_size": 68098
+}

sarvam1-sft/checkpoint-4272/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "max_length": 8192,
+  "pad_token_id": 2,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_p": 0.95,
+  "transformers_version": "5.17.0"
+}

sarvam1-sft/checkpoint-4272/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98f78b644e2a323520b5a919c160a2ca17455fa748be744439341311599af27
+size 10100413160

sarvam1-sft/checkpoint-4272/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec8fd1c6b2b9fa721405fa18b0d18e21f092b4589a24b21a51c4733f8c8cd2b
+size 20200994231

sarvam1-sft/checkpoint-4272/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea11996454b5587fcf33ae0ab5cf14b2031bf5f53f8c2ed5a48e87de31e29c84
+size 14645

sarvam1-sft/checkpoint-4272/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a37d50d48d001254bfa87996d0e082b9170e1a515ea4461975353c3bc0ac3b
+size 1465

sarvam1-sft/checkpoint-4272/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

sarvam1-sft/checkpoint-4272/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d170d90aca06ba4b4181d119bcc3b7e050c8521b88c82dde31b983e49f075d06
+size 5841