Pot-l
/

mistral-7b-bnb-4bit-full-QA

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Pot-l commited on Apr 18

Commit

b4da351

•

1 Parent(s): f76ca6b

Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

config.json +2 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -17,8 +17,6 @@
   "num_key_value_heads": 8,
   "pad_token_id": 2,
   "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,
@@ -34,8 +32,9 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 32000
 }

   "num_key_value_heads": 8,
   "pad_token_id": 2,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
+  "unsloth_version": "2024.4",
   "use_cache": true,
   "vocab_size": 32000
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66849503dccdf144cccae533a6921137feee23eddc4c9882533fc9f62813a0e7
-size 4125687629

 version https://git-lfs.github.com/spec/v1
+oid sha256:ea0f3b83fa5d3ecb36a00e5957311ddda82f909abb425b2c3dbe87ea654e61e1
+size 4125687694