Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- unsloth
 ---
 
 # Model Card for Model ID

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "_name_or_path": "unsloth/tinyllama-chat-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
@@ -19,12 +19,28 @@
   "num_key_value_heads": 4,
   "pad_token_id": 2,
   "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_scaling": {
+    "factor": 2.0,
+    "type": "linear"
+  },
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.44.2",
+  "unsloth_version": "2024.10.7",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "max_length": 2048,
+  "max_length": 4096,
   "pad_token_id": 2,
   "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9e93a56efef2e4c9a01d31c9f3e1d5b7369b81843a426ecfd1889b10e4361d
-size 4400216536
+oid sha256:d0765cd247611d60e0f2eeab01dfc52be0aa38d5e3f7ad2234157c924cff6b23
+size 762453323