Upload folder using huggingface_hub

README.md

@@ -0,0 +1,24 @@
+---
+license: cc-by-nc-nd-4.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- Mistral
+- Pygmalion
+- llama-2
+- llama-2-7b
+---
+
+quant of [Delcos'](https://huggingface.co/Delcos) [MistralPy-7b](https://huggingface.co/Delcos/Mistral-Pygmalion-7b)
+
+```
+python3 convert.py \
+    -i /input/Delcos_Mistral-Pygmalion-7b/ \
+    -c /input/wikitext/0000.parquet \
+    -o /output/temp/ \
+    -cf /output/4bpw/ \
+    -b 4.0 \
+    -hb 6
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "PygmalionAI/pygmalion-2-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "badwordsids": "[[29961], [14352], [24630], [29962], [11759], [15974], [5519], [25473], [18899], [25901], [7110], [9341], [13531], [518], [9310], [2636], [3366], [21069], [11970], [23098], [16733], [21298], [18173], [10846], [3816], [28513], [15625], [23192], [28166], [10062], [1385], [11724], [3108], [15555], [10834], [10370], [14330], [1822], [12436], [5262], [17094], [10725], [17077], [11424], [4197], [24406], [13359], [17531], [24566], [23076], [4514], [13192], [19942], [16261], [7072], [6024], [1402], [1839], [2033], [13970], [850], [5913], [28895], [5387], [8308], [24927], [5691], [12940], [19997], [18959], [11287], [16862], [4638], [22322], [29861], [21251], [14704], [17548], [12452], [17288], [23160], [24960], [8219], [18024], [5539], [7464], [27865], [29588], [20068], [19660], [27706], [22896], [24264], [12258], [2314], [4400], [5586], [12622], [6796], [7226], [21939], [18456], [14178], [21540], [21945], [14664], [16215], [10338], [17361], [7503], [13769], [26073], [9601], [26909], [7961], [8999], [20840], [16272], [21545], [3199], [10514], [5159], [22689], [6525], [20526], [27077], [18017]]",
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.34.0"
+}

huggingface-metadata.txt

@@ -0,0 +1,12 @@
+url: https://huggingface.co/Delcos/Mistral-Pygmalion-7b
+branch: main
+download date: 2023-10-10 11:46:34
+sha256sum:
+    f6e292658c735121d3fdcf3b32a212221d2cb93697b5da355f3a47e45ae9cb07 pytorch_model-00001-of-00007.bin
+    5dd9c3687a3a413d8f361cf301b620eae7be2b1e386b93284f44080df081335f pytorch_model-00002-of-00007.bin
+    d08e9d7fb285a27a7a9f6101cfca61885e6393f69d7478e524336f69a11b5f2a pytorch_model-00003-of-00007.bin
+    66bc5d907dca1764e4adea18506799016b6aacaff9373f7e3d1a4b83c7d9debf pytorch_model-00004-of-00007.bin
+    5c85e5b8cda73eaa4a04374fb5b7119c5cbb16478381389cb65aa175932055a9 pytorch_model-00005-of-00007.bin
+    eaeb9b6a3e861cd941b75a290c2aa9fcd6947028358b5fc0bf60e0d6e0cbf979 pytorch_model-00006-of-00007.bin
+    5ff0b6530fd5a0743ad2dd149bfdfb566ccfc5ddef61e847c355a2f9851069fe pytorch_model-00007-of-00007.bin
+    9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+    "metadata": {
+        "total_size": 13476831232
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00007-of-00007.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.norm.weight": "model-00007-of-00007.safetensors"
+    }
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90f1084d5caa7904a44948e728900603cc9cafb562a1afdfd507b285ba26718
+size 3611119772

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}