unsloth
/

llama-2-7b-chat-bnb-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

danielhanchen commited on Jan 31

Commit

a86cd15

•

1 Parent(s): 6745b72

Upload LlamaForCausalLM

Files changed (2) hide show

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

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -36,7 +36,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
   "transformers_version": "4.38.0.dev0",
   "use_cache": true,
   "vocab_size": 32000

   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
+    "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": "4.38.0.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:ccdae25751d6995831743603b8e5148da1ba16321ebe561ff6b37546c35e3e08
-size 3866042163

 version https://git-lfs.github.com/spec/v1
+oid sha256:5d1fb8211bf460e0d8b6d3a485f9eff3faa5a875f258c8f82ac690dfa591e6a1
+size 3866042099