Quant for 8.0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -24,71 +24,13 @@ datasets:
 - CausalLM/Refined-Anime-Text
 - microsoft/orca-math-word-problems-200k
 - m-a-p/CodeFeedback-Filtered-Instruction
-quantized_by: bartowski
-pipeline_tag: text-generation
 ---
+## TBA
 
-## Exllama v2 Quantizations of 35b-beta-long
+Tokenizer is different from cohere - and chat template is ChatML - fully fine-tuned at 128K+
 
-Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.20">turboderp's ExLlamaV2 v0.0.20</a> for quantization.
+No loras, no quants, no tricks, 30M+ sft data.
 
-<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
+Pressure Testing from: https://github.com/LeonEricsson/llmcontext
 
-Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
-
-Conversion was done using the default calibration dataset.
-
-Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
-
-Original model: https://huggingface.co/CausalLM/35b-beta-long
-
-
-<a href="https://huggingface.co/bartowski/35b-beta-long-exl2/tree/8_0">8.0 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/35b-beta-long-exl2/tree/6_5">6.5 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/35b-beta-long-exl2/tree/5_0">5.0 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/35b-beta-long-exl2/tree/4_25">4.25 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/35b-beta-long-exl2/tree/3_5">3.5 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/35b-beta-long-exl2/tree/3_0">3.0 bits per weight</a>
-
-
-## Download instructions
-
-With git:
-
-```shell
-git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/35b-beta-long-exl2
-```
-
-With huggingface hub (credit to TheBloke for instructions):
-
-```shell
-pip3 install huggingface-hub
-```
-
-To download the `main` (only useful if you only care about measurement.json) branch to a folder called `35b-beta-long-exl2`:
-
-```shell
-mkdir 35b-beta-long-exl2
-huggingface-cli download bartowski/35b-beta-long-exl2 --local-dir 35b-beta-long-exl2 --local-dir-use-symlinks False
-```
-
-To download from a different branch, add the `--revision` parameter:
-
-Linux:
-
-```shell
-mkdir 35b-beta-long-exl2-6_5
-huggingface-cli download bartowski/35b-beta-long-exl2 --revision 6_5 --local-dir 35b-beta-long-exl2-6_5 --local-dir-use-symlinks False
-```
-
-Windows (which apparently doesn't like _ in folders sometimes?):
-
-```shell
-mkdir 35b-beta-long-exl2-6.5
-huggingface-cli download bartowski/35b-beta-long-exl2 --revision 6_5 --local-dir 35b-beta-long-exl2-6.5 --local-dir-use-symlinks False
-```
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63468a143ea42ee2cb49ddd1/2XbONpyTeMH1qWCtE9ziH.png)

config.json

@@ -0,0 +1,41 @@
+{
+    "_name_or_path": "35b",
+    "architectures": [
+        "CohereForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 5,
+    "eos_token_id": 6,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 22528,
+    "layer_norm_eps": 1e-05,
+    "logit_scale": 0.0625,
+    "max_position_embeddings": 8192,
+    "model_max_length": 128000,
+    "model_type": "cohere",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 64,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 8000000.0,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.38.2",
+    "use_cache": true,
+    "vocab_size": 256000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.20",
+        "bits": 8.0,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 6,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors.index.json

@@ -0,0 +1,329 @@
+{
+  "metadata": {
+    "total_size": 69961662464
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

output-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3611c06ad058782fd019586027e0cc657b4edda2cb543234dbfeb14db22a06
+size 8458345882

output-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1049dd8e870c58c8dcb18a235b2090a22f91882f99b851bc5717d53b4c5a6087
+size 8440603480

output-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ca60f2ecff841b186bc9f133a5b83c136a758cfb55ed37bf807135494baf77
+size 8440603656

output-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb82db5ad31130d3203ea3fd04e64940d8c36feb4de20882a7bee39f42ef0ca
+size 8578342624

output-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228c583640fe349426f9ff0cf44457cda76c16580d0e0047b4107da9423c220b
+size 5270076768

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec24d1fe80ac960489b2004b7399ea561799de2fae774bd5a9234c13e6a0726
+size 12777306

tokenizer_config.json

@@ -0,0 +1,314 @@
+{
+    "add_bos_token": true,
+    "add_eos_token": false,
+    "added_tokens_decoder": {
+      "0": {
+        "content": "<PAD>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "1": {
+        "content": "<UNK>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "2": {
+        "content": "<CLS>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "3": {
+        "content": "<SEP>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "4": {
+        "content": "<MASK_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "5": {
+        "content": "<s>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "6": {
+        "content": "</s>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "7": {
+        "content": "<EOP_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "255000": {
+        "content": "<|im_start|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255001": {
+        "content": "<|im_end|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255002": {
+        "content": "<|YES_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255003": {
+        "content": "<|NO_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255004": {
+        "content": "<|GOOD_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255005": {
+        "content": "<|BAD_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255006": {
+        "content": "<|USER_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255007": {
+        "content": "<|CHATBOT_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255008": {
+        "content": "<|SYSTEM_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255009": {
+        "content": "<|USER_0_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255010": {
+        "content": "<|USER_1_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255011": {
+        "content": "<|USER_2_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255012": {
+        "content": "<|USER_3_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255013": {
+        "content": "<|USER_4_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255014": {
+        "content": "<|USER_5_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255015": {
+        "content": "<|USER_6_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255016": {
+        "content": "<|USER_7_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255017": {
+        "content": "<|USER_8_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255018": {
+        "content": "<|USER_9_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255019": {
+        "content": "<|EXTRA_0_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255020": {
+        "content": "<|EXTRA_1_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255021": {
+        "content": "<|EXTRA_2_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255022": {
+        "content": "<|EXTRA_3_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255023": {
+        "content": "<|EXTRA_4_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255024": {
+        "content": "<|EXTRA_5_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255025": {
+        "content": "<|EXTRA_6_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255026": {
+        "content": "<|EXTRA_7_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255027": {
+        "content": "<|EXTRA_8_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255028": {
+        "content": "<|EXTRA_9_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      }
+    },
+    "bos_token": "<s>",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "</s>",
+    "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
+    "legacy": true,
+    "model_max_length": 1000000000000000019884624838656,
+    "pad_token": "<PAD>",
+    "sp_model_kwargs": {},
+    "spaces_between_special_tokens": false,
+    "tokenizer_class": "LlamaTokenizer",
+    "unk_token": null,
+    "use_default_system_prompt": false
+  }