model upload

config.json

@@ -1,10 +1,43 @@
 {
+  "_name_or_path": "defog/llama-3-sqlcoder-8b",
   "architectures": [
-    "defog/llama-3-sqlcoder-8b"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
-  "task": "question-answering",
-  "language": "th",
-  "max_sequence_length": 2048,
-  "do_sample": true
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128255,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "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-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 128256
 }

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 8192,
+  "pad_token_id": 128255,
+  "temperature": 0,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd7683612ac389879e3596c35d75cf87c1ecc4363382fdd6c3109ac37efdc64
+size 4652072873

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641f16503b3e12f0573fc5db67a60cfbf9675842247bc78cb8a23a40f342bf7f
+size 1050673280