unsloth
/

llama-2-7b-bnb-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

danielhanchen commited on Dec 25, 2023

Commit

42794f9

•

1 Parent(s): 3e3776d

Upload LlamaForCausalLM

Files changed (2) hide show

config.json +2 -2
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -19,7 +19,7 @@
   "pad_token_id": 2,
   "pretraining_tp": 1,
   "quantization_config": {
-    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -34,7 +34,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
   "transformers_version": "4.37.0.dev0",
   "use_cache": true,
   "vocab_size": 32000

   "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,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.37.0.dev0",
   "use_cache": true,
   "vocab_size": 32000

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da29c3783607df13fc1d74e008573d9d5175e20fc08e905e8e3c6ae200f893c
-size 3866042386

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd12aa5433caa8df441f5c9a0ca376bc33d185d18fbb6ccdfbf55fbcbf15d542
+size 3866042098