Upload folder using huggingface_hub

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -6,24 +7,41 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "eos_token_id": 0,
+  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
   "initializer_range": 0.041666666666666664,
   "intermediate_size": 1536,
   "is_llama_config": true,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 9,
   "num_hidden_layers": 30,
   "num_key_value_heads": 3,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "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_interleaved": false,
   "rope_scaling": null,
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.46.2",
   "use_cache": true,
   "vocab_size": 49152
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1f335333c19c19d7c1d69e2fdebe5dddbb36be022fe78a85e3fc760d737ddb0
-size 168578292
+oid sha256:4963a043140595ba61b95fdff1900bfd5065b198d5982ea64f6bd4f25e814000
+size 111880782