Yi30 commited on 28 days ago

Commit

69b9ad1

verified ·

1 Parent(s): 4cf5f9d

Upload folder using huggingface_hub

Files changed (21) hide show

config.json CHANGED Viewed

@@ -1,4 +1,5 @@
 {
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -29,8 +30,9 @@
           "actorder": null,
           "block_structure": null,
           "dynamic": "local",
-          "group_size": 16,
-          "num_bits": 4,
           "observer": "minmax",
           "observer_kwargs": {},
           "strategy": "tensor_group",
@@ -45,8 +47,9 @@
           "actorder": null,
           "block_structure": null,
           "dynamic": false,
-          "group_size": 16,
-          "num_bits": 4,
           "observer": "minmax",
           "observer_kwargs": {},
           "strategy": "tensor_group",
@@ -55,7 +58,7 @@
         }
       }
     },
-    "format": "nvfp4-pack-quantized",
     "global_compression_ratio": null,
     "ignore": [
       "lm_head"
@@ -75,7 +78,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
   "use_cache": true,
   "vocab_size": 128256
 }

 {
+  "_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
           "actorder": null,
           "block_structure": null,
           "dynamic": "local",
+          "group_size": 32,
+          "is_mx": true,
+          "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
           "strategy": "tensor_group",
           "actorder": null,
           "block_structure": null,
           "dynamic": false,
+          "group_size": 32,
+          "is_mx": true,
+          "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
           "strategy": "tensor_group",
         }
       }
     },
+    "format": "float-quantized",
     "global_compression_ratio": null,
     "ignore": [
       "lm_head"
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json CHANGED Viewed

@@ -8,5 +8,5 @@
   ],
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.51.3"
 }

   ],
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.47.0"
 }

model-00001-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:722948ea9e8a88f08776bbfc3071cc09fd69f9bc48bc766d30f0ed4788633697
+size 4904295040

model-00002-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:81d98efb24d5f10e797647d55fa525990d2cc7ab367cc08846014eb340236dcc
+size 4896499344

model-00003-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:16f9f7315ee6213342231265cecd0974a5427032180afef7f2eddfc9e50e0036
+size 4810025600

model-00004-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:606a7df04f36ef8892d6536bede20ee27c741b57663ae7abeaa58e96c2e57036
+size 4896499432

model-00005-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:d06ab1527b00f0c586884d1f2185870e3d1a1f4d5c2d52ad06a71e2c835897b4
+size 4810025624

model-00006-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:218e5f8b88c7244c5699b1e8bea026f05c5abf52050d9ff78a132876769669c7
+size 4896499432

model-00007-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:078b787fc329db684b704f518da01056157ab6b49a42b5f90adb0e44e690be5c
+size 4810025624

model-00008-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:f87188ca957c20c044347369f38dc9c526dc204be6ea62b4a79a974ddbf7a94b
+size 4896499432

model-00009-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab12e5941d789d5689eee77ebeaf7db2c8f99d0d13133ecacc6ba7e5f1d5754
+size 4810025624

model-00010-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:79e1ec3b3fc217327102d0a58b9bf338d90f72b9eda43069486570105706e952
+size 4896499432

model-00011-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:1f01a3aab1f1a75c19b1546a1d472ff0a3e1886764a5e28305b1124d1303d937
+size 4810025624

model-00012-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7b3916e3ce3dbcf8af8d492a37fece0b51d6383216fa0321092ce17f7b812e
+size 4896499432

model-00013-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:05f4e116b0fc0b1be4ff84243ef5b00ada77a08efb0748bf160d0971b5f487f0
+size 4810025624

model-00014-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd50d7bf866fe74c5d6287cff0557aecdd277e5e4fe370c5d74a65a0620f726
+size 4896499432

model-00015-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4622d9300ef1d594899cecb63478ce56a8baed45a7fe0ef1952a02ef2569d09
+size 4654327584

model-00016-of-00016.safetensors ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0436c98c9b4f78e61f6769e588e0853179b970e2a084ae2886e2daebf1ce13d
+size 2101346432

model.safetensors.index.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

recipe.yaml CHANGED Viewed

@@ -3,4 +3,4 @@ default_stage:
     QuantizationModifier:
       targets: [Linear]
       ignore: [lm_head]
-      scheme: NVFP4

     QuantizationModifier:
       targets: [Linear]
       ignore: [lm_head]
+      scheme: MXFP8

tokenizer_config.json CHANGED Viewed

@@ -2060,5 +2060,5 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "tokenizer_class": "PreTrainedTokenizer"
 }

   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }