Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1 @@
+{%- if messages[0].role == 'system' %}{{ '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}{%- endif %}{%- for message in messages %}{%- if message.role == 'system' %}{%- elif message.role == 'user' %}{{ '<|im_start|>user\n' + message.content + '<|im_end|>\n' }}{%- elif message.role == 'assistant' %}{%- if message.content is defined and message.content %}{{ '<|im_start|>assistant\n' + message.content + '<|im_end|>\n' }}{%- endif %}{%- elif message.role == 'tool' %}{{ '<|im_start|>user\n<tool_response>\n' + message.content + '\n</tool_response><|im_end|>\n' }}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{%- if enable_thinking is defined and enable_thinking is true %}{{ '<think>\n' }}{%- endif %}{%- endif %}

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "5.5.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b322f0bd39f154bd2458bdffc4df43845867ca210385384d9fff85f1f197a0f9
+size 3866042378

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|endoftext|>",
+    "<think>",
+    "</think>",
+    "<tool_call>",
+    "</tool_call>",
+    "<tool_response>",
+    "</tool_response>",
+    "<tools>",
+    "</tools>"
+  ],
+  "is_local": true,
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}