初始化项目，由ModelHub XC社区提供模型

Model: SlimGroove/normistral-11b-translate-mlx
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,46 @@
+---
+license: apache-2.0
+language:
+- nb
+- nn
+- 'no'
+- en
+base_model: norallm/normistral-11b-translate
+library_name: mlx
+pipeline_tag: text-generation
+tags:
+- translation
+- norwegian
+- english
+- bokmaal
+- nynorsk
+- mlx
+---
+
+# SlimGroove/normistral-11b-translate-mlx
+
+This model [SlimGroove/normistral-11b-translate-mlx](https://huggingface.co/SlimGroove/normistral-11b-translate-mlx) was
+converted to MLX format from [norallm/normistral-11b-translate](https://huggingface.co/norallm/normistral-11b-translate)
+using mlx-lm version **0.29.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("SlimGroove/normistral-11b-translate-mlx")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,12 @@
+{%- set ns = namespace(last_user_msg="", system="engelsk") -%}
+{%- for message in messages -%}
+  {%- if message.role == "user" -%}
+    {%- set ns.last_user_msg = message.content -%}
+  {%- elif message.role == "system" -%}
+    {%- set ns.system = message.content -%}
+  {%- endif -%}
+{%- endfor -%}
+<s><source>{% if ns.last_user_msg[:1] == " " %}{{ ns.last_user_msg }}{% else %} {{ ns.last_user_msg }}{% endif %}</source>
+
+## {{ ns.system }}:
+<target>

config.json

@@ -0,0 +1,28 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "mask_token_id": 4,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "pad_token_id": 3,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.3",
+    "use_cache": true,
+    "vocab_size": 51200
+}

convert_to_safetensors.py

@@ -0,0 +1,68 @@
+import argparse
+import random
+from statistics import mean, stdev
+from typing import List
+import torch
+import torchmetrics
+from datasets import load_dataset
+from tqdm import tqdm
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model_name_or_path",
+        type=str,
+        default=".",
+        help="Path to the pre-trained model",
+    )
+    args = parser.parse_args()
+
+    return args
+
+
+def load_model(model_path: str):
+    # Load the pre-trained model and tokenizer
+    tokenizer = AutoTokenizer.from_pretrained(model_path, torch_dtype=torch.bfloat16)
+    model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.bfloat16).cuda().eval()
+
+    eos_token_ids = [
+        token_id
+        for token_id in range(tokenizer.vocab_size)
+        if "\n" in tokenizer.decode([token_id])
+    ]
+
+    if hasattr(model.config, "n_positions"):
+        max_length = model.config.n_positions
+    elif hasattr(model.config, "max_position_embeddings"):
+        max_length = model.config.max_position_embeddings
+    elif hasattr(model.config, "max_length"):
+        max_length = model.config.max_length
+    elif hasattr(model.config, "n_ctx"):
+        max_length = model.config.n_ctx
+    else:
+        max_length = 32768  # Default value
+
+    return {
+        "name": model_path.split("/")[-1],
+        "tokenizer": tokenizer,
+        "model": model,
+        "eos_token_ids": eos_token_ids,
+        "max_length": max_length,
+    }
+
+
+def main():
+    args = parse_args()
+
+    model = load_model(args.model_name_or_path)
+    
+    model["model"].save_pretrained(
+        args.model_name_or_path,
+        max_shard_size="5GB"
+    )
+
+
+if __name__ == "__main__":
+    main()

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587d6df9c1e67d120c64be8db24987aefc5b77cbb87124ce66dfe407273e9abc
+size 5284996009

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a0477de9ee43f4abd530380fed3178ad240ddbe799895aceea266a7690a551
+size 5306009740

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07e6fb7ee218692f3713aeb3eaec569a4833a02f28695ffa14a784f5ef41b63
+size 5306009758

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adcf132fd80f6ad18d3a96645aa4cba9f52e243305c7ff9a9bf1c1a79fbec0c3
+size 5347952444

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4a5518aaf2e82169cb50a14bec3bdb966025176398ee4e40ecf643cc88b18a
+size 1614860509

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+    "metadata": {
+        "total_size": 22859786240,
+        "total_parameters": 11429893120
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00005-of-00005.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.norm.weight": "model-00005-of-00005.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,179 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "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
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<source>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</source>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<target>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<special_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<special_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<special_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<special_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<special_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<special_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<special_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<special_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51200": {
+      "content": "<instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51201": {
+      "content": "</instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51202": {
+      "content": "<system_prompt>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51203": {
+      "content": "</system_prompt>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "bos_token_id": 1,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<pad>",
+  "pad_token_id": 3,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>",
+  "unk_token_id": 0
+}