First commit

README.md

@@ -0,0 +1,56 @@
+---
+license: cc-by-nc-4.0
+---
+
+Re:MythoMax-Mistral (ReMM-Mistral) is a recreation trial of the original [MythoMax-L2-B13](https://huggingface.co/Gryphe/MythoMax-L2-13b) with updated models and data of Mistral.
+
+This merge use Gradient merging method to merge ReML-Mistral v2.2 and Huginn.
+
+Explaination :
+```shell
+- ReML-Mistral-v2.2: (Chronos-Beluga v2/Hermes/Airboros 2.2.1 + LoRA)
+=> The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
+=> jondurbin/airoboros-l2-13b-2.2 by jondurbin/airoboros-l2-13b-2.2.1
+=> NousResearch/Nous-Hermes-Llama2-13b
+
+=> Applying Undi95/llama2-to-mistral-diff at 1.0 at the end
+
+With that :
+- ReMM-Mistral: (ReML-Mistral-v2.2/Huginn)
+=> ReMM by the one above
+=> The-Face-Of-Goonery/Huginn-13b-FP16
+```
+
+<!-- description start -->
+## Description
+
+This repo contains fp16 files of ReMM-Mistral, a recreation of the original MythoMax, but updated and merged with Gradient method and Mistral data.
+<!-- description end -->
+<!-- description start -->
+## Models used
+
+
+- [The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16=)
+- [jondurbin/airoboros-l2-13b-2.2.1](https://huggingface.co/jondurbin/airoboros-l2-13b-2.2.1)
+- [NousResearch/Nous-Hermes-Llama2-13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)
+- [The-Face-Of-Goonery/Huginn-13b-FP16](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16)
+- [Undi95/ReML-Mistral-v2.2-13B](https://huggingface.co/Undi95/ReML-Mistral-v2.2-13B) (Private recreation trial of an updated Mythologic-L2-13B with Mistral data)
+- [Undi95/llama2-to-mistral-diff](https://huggingface.co/Undi95/llama2-to-mistral-diff)
+
+<!-- description end -->
+<!-- prompt-template start -->
+## Prompt template: Alpaca
+
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+{prompt}
+
+### Response:
+
+```
+
+A big thanks to [KoboldAI](https://github.com/KoboldAI/KoboldAI-Client) dev' Henky for giving me a machine powerfull enough to do some of my work!
+
+If you want to support me, you can [here](https://ko-fi.com/undiai).

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "./Undi95_ReMM-Mistral-13B-part1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "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.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model-00001-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7327574bec97682cd1c96e7db2fa198e18a95b8821bb12b4d306419d336e15a2
+size 2089337041

pytorch_model-00002-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1de0c76df4857ec375147ae8f416b1fc10e3b6d044f17684438b816e134132
+size 2044815083

pytorch_model-00003-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29eae38fb735d1f1a17bf72a5692898556ec71abdb6d9b875ee57d04153b566d
+size 2060523307

pytorch_model-00004-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14984b7e3b8665fdf487e96a2b1fe5dd09d1a38a2f0cd41d20e7825f71fe1601
+size 1955665095

pytorch_model-00005-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfcf8d38899722f2de6a8bc555ef0d55b5773f4302e90d145fee2e210fbfa54e
+size 2044794055

pytorch_model-00006-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65de41ffb268ae65fad2d708d13252294f2629e663172527bc26b04ffbd58a9
+size 2044794055

pytorch_model-00007-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb4a2b4e310887d59062f20adc7e77de4d1ed65e9d460e780bd90fda66fbf09
+size 2044815147

pytorch_model-00008-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0f6bd3ea4f89e5826cbfc20c9977ce7c6d76b0cdf19fb4a2b7ed4b0e26730f
+size 2060523307

pytorch_model-00009-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e80c727db159b9d3eaced578a208caca35e4e80b73d45382d63310a3b6fbde
+size 1955665095

pytorch_model-00010-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbad5c7be1b42b7adfe41e3ffbf57029e0633ae638696a32904e270635267b7
+size 2044794055

pytorch_model-00011-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4784e34d16809f3505cc5a75e800e9a224da315f1fbc1bdc5032e42f78e910a0
+size 2044794055

pytorch_model-00012-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ae338ebe6e61e4d65b8727e5eec9a360b1e5ce24978c69b26d3d177ee56a3b
+size 2044815147

pytorch_model-00013-of-00013.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9626f81f15919faa567b23d730e51d86f019b24ecde7133e2745ecc26e36df84
+size 1596514999

pytorch_model.bin.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031728640
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00013-of-00013.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
+    "model.norm.weight": "pytorch_model-00013-of-00013.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "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": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}