Upload LlamaForCausalLM

README.md

@@ -1,3 +1,6 @@
+---
+{}
+---
 Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of `meta-llama/Llama-2-7b-hf`.
 
 For this quantization, we used 1 codebook of 16 bits.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "BlackSamorez/Llama-2-70b-AQLM-2Bit-8x8-hf",
+  "_name_or_path": "/extra_disk_1/dkuznedelev/aqlm/Llama-2-70b-hf-2x8",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -20,7 +20,168 @@
   "quantization_config": {
     "in_group_size": 8,
     "linear_weights_not_to_quantize": [
+      "model.layers.0.input_layernorm.weight",
+      "model.layers.0.post_attention_layernorm.weight",
+      "model.layers.1.input_layernorm.weight",
+      "model.layers.1.post_attention_layernorm.weight",
+      "model.layers.2.input_layernorm.weight",
+      "model.layers.2.post_attention_layernorm.weight",
+      "model.layers.3.input_layernorm.weight",
+      "model.layers.3.post_attention_layernorm.weight",
+      "model.layers.4.input_layernorm.weight",
+      "model.layers.4.post_attention_layernorm.weight",
+      "model.layers.5.input_layernorm.weight",
+      "model.layers.5.post_attention_layernorm.weight",
+      "model.layers.6.input_layernorm.weight",
+      "model.layers.6.post_attention_layernorm.weight",
+      "model.layers.7.input_layernorm.weight",
+      "model.layers.7.post_attention_layernorm.weight",
+      "model.layers.8.input_layernorm.weight",
+      "model.layers.8.post_attention_layernorm.weight",
+      "model.layers.9.input_layernorm.weight",
+      "model.layers.9.post_attention_layernorm.weight",
+      "model.layers.10.input_layernorm.weight",
+      "model.layers.10.post_attention_layernorm.weight",
+      "model.layers.11.input_layernorm.weight",
+      "model.layers.11.post_attention_layernorm.weight",
+      "model.layers.12.input_layernorm.weight",
+      "model.layers.12.post_attention_layernorm.weight",
+      "model.layers.13.input_layernorm.weight",
+      "model.layers.13.post_attention_layernorm.weight",
+      "model.layers.14.input_layernorm.weight",
+      "model.layers.14.post_attention_layernorm.weight",
+      "model.layers.15.input_layernorm.weight",
+      "model.layers.15.post_attention_layernorm.weight",
+      "model.layers.16.input_layernorm.weight",
+      "model.layers.16.post_attention_layernorm.weight",
+      "model.layers.17.input_layernorm.weight",
+      "model.layers.17.post_attention_layernorm.weight",
+      "model.layers.18.input_layernorm.weight",
+      "model.layers.18.post_attention_layernorm.weight",
+      "model.layers.19.input_layernorm.weight",
+      "model.layers.19.post_attention_layernorm.weight",
+      "model.layers.20.input_layernorm.weight",
+      "model.layers.20.post_attention_layernorm.weight",
+      "model.layers.21.input_layernorm.weight",
+      "model.layers.21.post_attention_layernorm.weight",
+      "model.layers.22.input_layernorm.weight",
+      "model.layers.22.post_attention_layernorm.weight",
+      "model.layers.23.input_layernorm.weight",
+      "model.layers.23.post_attention_layernorm.weight",
+      "model.layers.24.input_layernorm.weight",
+      "model.layers.24.post_attention_layernorm.weight",
+      "model.layers.25.input_layernorm.weight",
+      "model.layers.25.post_attention_layernorm.weight",
+      "model.layers.26.input_layernorm.weight",
+      "model.layers.26.post_attention_layernorm.weight",
+      "model.layers.27.input_layernorm.weight",
+      "model.layers.27.post_attention_layernorm.weight",
+      "model.layers.28.input_layernorm.weight",
+      "model.layers.28.post_attention_layernorm.weight",
+      "model.layers.29.input_layernorm.weight",
+      "model.layers.29.post_attention_layernorm.weight",
+      "model.layers.30.input_layernorm.weight",
+      "model.layers.30.post_attention_layernorm.weight",
+      "model.layers.31.input_layernorm.weight",
+      "model.layers.31.post_attention_layernorm.weight",
+      "model.layers.32.input_layernorm.weight",
+      "model.layers.32.post_attention_layernorm.weight",
+      "model.layers.33.input_layernorm.weight",
+      "model.layers.33.post_attention_layernorm.weight",
+      "model.layers.34.input_layernorm.weight",
+      "model.layers.34.post_attention_layernorm.weight",
+      "model.layers.35.input_layernorm.weight",
+      "model.layers.35.post_attention_layernorm.weight",
+      "model.layers.36.input_layernorm.weight",
+      "model.layers.36.post_attention_layernorm.weight",
+      "model.layers.37.input_layernorm.weight",
+      "model.layers.37.post_attention_layernorm.weight",
+      "model.layers.38.input_layernorm.weight",
+      "model.layers.38.post_attention_layernorm.weight",
+      "model.layers.39.input_layernorm.weight",
+      "model.layers.39.post_attention_layernorm.weight",
+      "model.layers.40.input_layernorm.weight",
+      "model.layers.40.post_attention_layernorm.weight",
+      "model.layers.41.input_layernorm.weight",
+      "model.layers.41.post_attention_layernorm.weight",
+      "model.layers.42.input_layernorm.weight",
+      "model.layers.42.post_attention_layernorm.weight",
+      "model.layers.43.input_layernorm.weight",
+      "model.layers.43.post_attention_layernorm.weight",
+      "model.layers.44.input_layernorm.weight",
+      "model.layers.44.post_attention_layernorm.weight",
+      "model.layers.45.input_layernorm.weight",
+      "model.layers.45.post_attention_layernorm.weight",
+      "model.layers.46.input_layernorm.weight",
+      "model.layers.46.post_attention_layernorm.weight",
+      "model.layers.47.input_layernorm.weight",
+      "model.layers.47.post_attention_layernorm.weight",
+      "model.layers.48.input_layernorm.weight",
+      "model.layers.48.post_attention_layernorm.weight",
+      "model.layers.49.input_layernorm.weight",
+      "model.layers.49.post_attention_layernorm.weight",
+      "model.layers.50.input_layernorm.weight",
+      "model.layers.50.post_attention_layernorm.weight",
+      "model.layers.51.input_layernorm.weight",
+      "model.layers.51.post_attention_layernorm.weight",
+      "model.layers.52.input_layernorm.weight",
+      "model.layers.52.post_attention_layernorm.weight",
+      "model.layers.53.input_layernorm.weight",
+      "model.layers.53.post_attention_layernorm.weight",
+      "model.layers.54.input_layernorm.weight",
+      "model.layers.54.post_attention_layernorm.weight",
+      "model.layers.55.input_layernorm.weight",
+      "model.layers.55.post_attention_layernorm.weight",
+      "model.layers.56.input_layernorm.weight",
+      "model.layers.56.post_attention_layernorm.weight",
+      "model.layers.57.input_layernorm.weight",
+      "model.layers.57.post_attention_layernorm.weight",
+      "model.layers.58.input_layernorm.weight",
+      "model.layers.58.post_attention_layernorm.weight",
+      "model.layers.59.input_layernorm.weight",
+      "model.layers.59.post_attention_layernorm.weight",
+      "model.layers.60.input_layernorm.weight",
+      "model.layers.60.post_attention_layernorm.weight",
+      "model.layers.61.input_layernorm.weight",
+      "model.layers.61.post_attention_layernorm.weight",
+      "model.layers.62.input_layernorm.weight",
+      "model.layers.62.post_attention_layernorm.weight",
+      "model.layers.63.input_layernorm.weight",
+      "model.layers.63.post_attention_layernorm.weight",
+      "model.layers.64.input_layernorm.weight",
+      "model.layers.64.post_attention_layernorm.weight",
+      "model.layers.65.input_layernorm.weight",
+      "model.layers.65.post_attention_layernorm.weight",
+      "model.layers.66.input_layernorm.weight",
+      "model.layers.66.post_attention_layernorm.weight",
+      "model.layers.67.input_layernorm.weight",
+      "model.layers.67.post_attention_layernorm.weight",
+      "model.layers.68.input_layernorm.weight",
+      "model.layers.68.post_attention_layernorm.weight",
+      "model.layers.69.input_layernorm.weight",
+      "model.layers.69.post_attention_layernorm.weight",
+      "model.layers.70.input_layernorm.weight",
+      "model.layers.70.post_attention_layernorm.weight",
+      "model.layers.71.input_layernorm.weight",
+      "model.layers.71.post_attention_layernorm.weight",
+      "model.layers.72.input_layernorm.weight",
+      "model.layers.72.post_attention_layernorm.weight",
+      "model.layers.73.input_layernorm.weight",
+      "model.layers.73.post_attention_layernorm.weight",
+      "model.layers.74.input_layernorm.weight",
+      "model.layers.74.post_attention_layernorm.weight",
+      "model.layers.75.input_layernorm.weight",
+      "model.layers.75.post_attention_layernorm.weight",
+      "model.layers.76.input_layernorm.weight",
+      "model.layers.76.post_attention_layernorm.weight",
+      "model.layers.77.input_layernorm.weight",
+      "model.layers.77.post_attention_layernorm.weight",
+      "model.layers.78.input_layernorm.weight",
+      "model.layers.78.post_attention_layernorm.weight",
+      "model.layers.79.input_layernorm.weight",
+      "model.layers.79.post_attention_layernorm.weight",
       "model.embed_tokens.weight",
+      "model.norm.weight",
       "lm_head.weight"
     ],
     "nbits_per_codebook": 8,
@@ -33,7 +194,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.38.0",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.37.0"
+  "transformers_version": "4.38.2"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb3c9d31e8883babe636d1b08a66b3df815ad5a1aa3b0538a4d800aedcfc79b
+oid sha256:3e26928fd1ff5b7840bea5eb341d89e49e38cfa968b87f2d0d55e7b0fd202664
 size 4963092360

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e878615c34c2c6bf2f1377d71ba3bed5cacce24042b9de2678abb018ffaa15e9
+oid sha256:0f6d8f38c8625c5bc14538c37e52b36fd3564009492c6665f03495cc32d3c792
 size 4984691288

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140a8ff43a4b1769c20bcd93cecf6e815e0a0e57c709813c03b9a7ccb5932579
+oid sha256:301a24700933075175a212e4edfc1b234e6c02095a6587d7ae243cd30295683f
 size 4963732872

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:452d90ad3edd8773d2b717ef47bd7d0ba9fbfaa23a03bb750f8c8ab3f543fb40
+oid sha256:997ea3a8e98e77fc9ddbb7ef9929f24e9e551fa1528fda780c1b8e3cf6b507d4
 size 3270689184