diff --git a/README.md b/README.md
index 3140730..5c9bdd6 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,48 @@
-# vicuna-7b-v1.5_a13650666788876288723125
+---
+inference: false
+license: llama2
+---
-vicuna-7b-v1.5
\ No newline at end of file
+# Vicuna Model Card
+
+## Model Details
+
+Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
+
+- **Developed by:** [LMSYS](https://lmsys.org/)
+- **Model type:** An auto-regressive language model based on the transformer architecture
+- **License:** Llama 2 Community License Agreement
+- **Finetuned from model:** [Llama 2](https://arxiv.org/abs/2307.09288)
+
+### Model Sources
+
+- **Repository:** https://github.com/lm-sys/FastChat
+- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
+- **Paper:** https://arxiv.org/abs/2306.05685
+- **Demo:** https://chat.lmsys.org/
+
+## Uses
+
+The primary use of Vicuna is research on large language models and chatbots.
+The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
+
+## How to Get Started with the Model
+
+- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
+- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api
+
+## Training Details
+
+Vicuna v1.5 is fine-tuned from Llama 2 with supervised instruction fine-tuning.
+The training data is around 125K conversations collected from ShareGPT.com.
+See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
+
+## Evaluation
+
+![Evaluation Results](https://github.com/lm-sys/lm-sys.github.io/blob/main/public/images/webdata/vicuna_v1.5_eval.png?raw=true)
+
+Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).
+
+## Difference between different versions of Vicuna
+
+See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..8f8fd12
--- /dev/null
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+ "_name_or_path": "vicuna-7b-v1.5",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 11008,
+ "max_position_embeddings": 4096,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 32,
+ "pad_token_id": 0,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.31.0",
+ "use_cache": true,
+ "vocab_size": 32000
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..bbeeda1
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..57dbab3
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "max_length": 4096,
+ "pad_token_id": 0,
+ "temperature": 0.9,
+ "top_p": 0.6,
+ "transformers_version": "4.31.0"
+}
diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin
new file mode 100644
index 0000000..b79c622
--- /dev/null
+++ b/pytorch_model-00001-of-00002.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4133d2fcc5f31286881ea50806d95b721d016b533036a99dedce3f8fe88520e6
+size 9976634558
diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin
new file mode 100644
index 0000000..e563335
--- /dev/null
+++ b/pytorch_model-00002-of-00002.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d261d3c35e92d3070d1e61ed821ebfca812a847d2a880757d82728acf005c5ac
+size 3500315539
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000..db7264b
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,330 @@
+{
+ "metadata": {
+ "total_size": 13476839424
+ },
+ "weight_map": {
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+ }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..14761dc
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "",
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..6c00c74
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..508754b
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,35 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "legacy": false,
+ "model_max_length": 4096,
+ "pad_token": null,
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}