Upload 8 files

README.md

@@ -1,3 +1,85 @@
 ---
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+  - mistral
+  - instruct
+  - bggpt
+  - insait
+language:
+- bg
+- en
+library_name: transformers
+pipeline_tag: text-generation
 license: apache-2.0
 ---
+# INSAIT-Institute/BgGPT-7B-Instruct-v0.2
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/637e1f8cf7e01589cc17bf7e/p6d0YFHjWCQ3S12jWqO1m.png)
+
+Meet BgGPT-7B, a Bulgarian language model trained from mistralai/Mistral-7B-v0.1. BgGPT is distributed under Apache 2.0 license.
+
+This model was created by [`INSAIT Institute`](https://insait.ai/), part of Sofia University, in Sofia, Bulgaria.
+
+This is an improved version of the model - v0.2.
+
+## Model description
+
+The model is continously pretrained to gain its Bulgarian language and culture capabilities using multiple datasets, including Bulgarian web crawl data, a range of specialized Bulgarian datasets sourced by INSAIT Institute, and machine translations of popular English datasets. 
+This Bulgarian data was augmented with English datasets to retain English and logical reasoning skills.
+
+The model's tokenizer has been extended to allow for a more efficient encoding of Bulgarian words written in Cyrillic. 
+This not only increases throughput of Cyrillic text but also performance. 
+
+## Instruction format
+
+In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. 
+The very first instruction should begin with a begin of sequence token `<s>`. Following instructions should not. 
+The assistant generation will be ended by the end-of-sequence token.
+
+E.g.
+```
+text = "<s>[INST] Кога е основан Софийският университет? [/INST]"
+"Софийският университет „Св. Климент Охридски“ е създаден на 1 октомври 1888 г.</s> "
+"[INST] Кой го е основал? [/INST]"
+```
+
+This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
+
+## Benchmarks
+
+The model comes with a set of Benchmarks that are translations of the corresponding English-benchmarks. These are provided at [`https://github.com/insait-institute/lm-evaluation-harness-bg`](https://github.com/insait-institute/lm-evaluation-harness-bg)
+
+As this is an improved version over version 0.1 of the same model, we include benchmark comparisons.
+
+## Summary
+- **Finetuned from:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+- **Model type:** Causal decoder-only transformer language model
+- **Language:** Bulgarian and English
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html)
+- **Contact:** [bggpt@insait.ai](mailto:bggpt@insait.ai)
+
+## Use in 🤗Transformers
+First install direct dependencies:
+```
+pip install transformers torch accelerate
+```
+If you want faster inference using flash-attention2, you need to install these dependencies:
+```bash
+pip install packaging ninja
+pip install flash-attn
+```
+Then load the model in transformers:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+model = AutoModelForCausalLM.from_pretrained(
+    model="INSAIT-Institute/BgGPT-7B-Instruct-v0.2",
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+    use_flash_attn_2=True # optional
+)
+```
+
+## Use with GGML / llama.cpp
+
+The model in GGUF format [INSAIT-Institute/BgGPT-7B-Instruct-v0.2-GGUF](https://huggingface.co/INSAIT-Institute/BgGPT-7B-Instruct-v0.2-GGUF)

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 38000
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91ae46bfc3ada28db79a533a39e7c21ae03f0c050935afb613cca8875d166d7
+size 9992133696

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9d6851686ea6cf8c8510f47455336f34098098a725e040cac58611330a9cd2
+size 4589668352

model.safetensors.index.json

@@ -0,0 +1,297 @@
+{
+   "metadata" : {
+   },
+   "weight_map" : {
+      "lm_head.weight" : "model-00002-of-00002.safetensors",
+      "model.embed_tokens.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.0.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.1.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.10.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.11.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.12.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.13.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.14.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.15.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.16.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.17.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.18.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.19.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.2.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.20.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.21.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.22.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.22.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.22.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.22.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.22.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.22.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.22.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.22.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.22.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.23.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.23.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.23.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.23.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.23.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.23.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.23.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.23.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.23.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.24.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.25.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.26.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.27.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.28.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.29.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.3.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.3.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.3.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.3.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.3.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.3.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.3.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.3.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.3.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.30.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.30.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.30.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.30.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.30.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.30.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.30.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.30.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.30.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.input_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.mlp.down_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.mlp.gate_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.mlp.up_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.post_attention_layernorm.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.self_attn.k_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.self_attn.o_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.self_attn.q_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.31.self_attn.v_proj.weight" : "model-00002-of-00002.safetensors",
+      "model.layers.4.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.4.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.4.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.4.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.4.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.4.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.4.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.4.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.4.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.5.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.6.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.7.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.8.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.input_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.mlp.down_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.mlp.gate_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.mlp.up_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.post_attention_layernorm.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.self_attn.k_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.self_attn.o_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.self_attn.q_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.layers.9.self_attn.v_proj.weight" : "model-00001-of-00002.safetensors",
+      "model.norm.weight" : "model-00002-of-00002.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": "<unk>",
+    "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 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}