Upload folder using huggingface_hub

vllm_bitblas/config.json

@@ -0,0 +1 @@
+{"vocab_size": 128256, "max_position_embeddings": 131072, "hidden_size": 8192, "intermediate_size": 28672, "num_hidden_layers": 80, "num_attention_heads": 64, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000.0, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": [128001, 128008, 128009], "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct", "transformers_version": "4.44.0", "model_type": "llama"}

vllm_bitblas/model-00001-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:242089b2ae7aa016e9cd5225f65f4756dbaa68d22e76f3ccee65e9692cf7a999
+size 2756485432

vllm_bitblas/model-00002-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9439520bcbb6e2e5e6c85b6c021346b6a80dbae55da5ee8b7d208d7ce7265900
+size 1003259488

vllm_bitblas/model-00003-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea685cdf0f235cc279e1bff48190b99ad81c317dc20f9bc3a91e410758be8d4c
+size 1058350688

vllm_bitblas/model-00004-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c172f6f2e6aae6c19100806e818f8b7c8beb3aabd1d6e505e4bb4caab183bbd8
+size 1047073048

vllm_bitblas/model-00005-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752b712e782a786dc04c4113b92441b91c1e3634d4e66892ecda901d435fb99a
+size 1003267600

vllm_bitblas/model-00006-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d60a376a64362c3220e72a4fd26d2c2a24fc03dcf1acb1a325e350d0f82f43f
+size 1150060208

vllm_bitblas/model-00007-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d29e351302137d2c09ecd62b603df778279a553f432b2b3f373bb95e1208171
+size 1186760408

vllm_bitblas/model-00008-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea58783808db260b014b4e8b1c8513e745ee6fc59cd4661de8761d4eaa656b5
+size 1168451296

vllm_bitblas/model-00009-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c831507aed4834af1c184c6e0bff16834eb1ce056fa75f83034caef11b80ca42
+size 1267274096

vllm_bitblas/model-00010-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9396b60c941b25586abe049d3f7435dee87985e4b3cef4e6fb8a23c21e4d7b7f
+size 1076667920

vllm_bitblas/model-00011-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43e2c75fe9f985b4651eea8386174453447419b568f5d047c6c46fc06b051e3
+size 1076659944

vllm_bitblas/model-00012-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98391f199fd863e9bba3bd970ef56e1fb721b69de1fb7d54982b5880e71a98b0
+size 1186760408

vllm_bitblas/model-00013-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff6ab57710700bffd2902b01152a2c7eb69d2379521a25f27f3e02865f41a13
+size 1168451296

vllm_bitblas/model-00014-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6c1244bc0a4aa7491d1d0b34b393cb0fee31bea2ffc6dad275810e12a28dd3
+size 1047073168

vllm_bitblas/model-00015-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ec33007c2630df2c41b303b2621b96d6a9d67ca6524a5b82e49894b5f89713
+size 1003267600

vllm_bitblas/model-00016-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada1110be07b7870f7b131dbc3f73ff024fd6ecfdeeaa64dc8ac8f9bf0ad7a0d
+size 1003259624

vllm_bitblas/model-00017-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a096463bfbea767351d1a3b5f33c16ba2f3d196893570bf3dd50a2fa6d6a4fb7
+size 1003259616

vllm_bitblas/model-00018-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3baa46f52212d0bfb1f1c1389d388cb3fb6ad0f087251c66f033f6b8d6e72b75
+size 1058350808

vllm_bitblas/model-00019-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d789c4cb72ae1b3fa4c7e481590465d2da42c45cbd0987d4f39dfc22e045c17
+size 1047073168

vllm_bitblas/model-00020-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a36b3f618856843da0a31a479a65c8e47f111e41a01db978cfe74d07125fb94
+size 1003267600

vllm_bitblas/model-00021-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ec83dce4856bd1d83e67b0ff9d6c5b3ecae46c0a2956d690ca18c5d4ec0756
+size 1113360112

vllm_bitblas/model-00022-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848507f0ef2c8bd717b6d4b2e34f7eb143bd1375b8a47a366de994c5a3b7f9d8
+size 1113360104

vllm_bitblas/model-00023-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ba3398f2664544bfd56b3e1c038cd1c66ed76eb5314c1ea3ffb585efbff76f
+size 1058350808

vllm_bitblas/model-00024-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248f0129535c481f64534a514e874634ce82d9565f0c00253ec90967b3752533
+size 1047073168

vllm_bitblas/model-00025-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f337100553e4e24cf9821fdcc15528e30c60a4acef2b04135da1e80a54254d23
+size 1076667920

vllm_bitblas/model-00026-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d306d75abd885c249d6daef8cdd189cf91d17ede9dedf5914c11ee8df1ba78b0
+size 1076659944

vllm_bitblas/model-00027-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea0103bf58f789e21cf56425cea7214ace6f2ca0e9926d39fc2c45b32150eeb
+size 1076659920

vllm_bitblas/model-00028-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfcaf800880b531f21184e884a165e3ddad9621871cce18389e0c825995aa23
+size 1058350808

vllm_bitblas/model-00029-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3f1c4af0a4b0dbc050bfcd43de8964a74946b5dc3014982264a689ae018b1f
+size 1157190112

vllm_bitblas/model-00030-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c845d7ccba30e2e0eb8ab20aa313d5ed45dca6634e214a62ed323b70462fa828
+size 2101346432

vllm_bitblas/quantize_config.json

@@ -0,0 +1 @@
+{"group_size": {"gate_up_proj": 32, "qkv_proj": 128, "o_proj": 128, "down_proj": 32}, "nbits": {"gate_up_proj": 2, "qkv_proj": 4, "o_proj": 4, "down_proj": 2}, "lora_rank": 64, "skipped_dora_layers": [], "block_influence_layers": ["layers.0", "layers.13", "layers.15", "layers.17", "layers.19", "layers.21", "layers.23", "layers.26", "layers.29", "layers.31", "layers.33", "layers.56", "layers.59", "layers.68", "layers.71", "layers.79"], "groupsize_4bit": 128}