Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 92544,
+  "<|im_start|>": 92545
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "chargoddard/internlm2-20b-llama",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 92544,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 92546
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.37.0.dev0"
+}

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bc2c68b0fd7d0162002f62ac5f60749fce95e85264959fe694990b1c96e019
+size 4836694681

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae744c1ce8eb81cab3515471e0d7d1c5abbebe771b23069e63059b8adbec0114
+size 4983026187

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae52df29ad9748e4335e4433130408230f7168cf6389f087b7de4ecbd827c24
+size 4957834531

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a337d0d58dd6ba992cbd3ee457cfbfe7b4ce40e4dc577d9d5575043a4c5b6cc1
+size 4882336561

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d4e2590d12a12a891281bb54c1c0c6f3dbdd744f67503e33106ce42964ffd4
+size 4983026187

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2469d89af9a34074c2efc6f5ee9fc579f7126083c6fac193383112b1ad5e0b
+size 4957834531

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11ef65c62eea46cb59bbf9c10276a72d5782d6d3cb166c7bd6950b902b60cbb
+size 4882336561

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e011ff5f43ba05f4730f2694f10b8fe3463b08d3b197e9ec08d316683b59382
+size 4102206145

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42d4df8e8c99ebf3afb5bd3c734f342a7fafc6885c2d978309a93d62e3f546d
+size 1137206186

pytorch_model.bin.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 39722348544
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00009-of-00009.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00009.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
+size 1477754

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": 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
+    },
+    "92544": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92545": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "internlm/internlm2-20b--tokenization_internlm.InternLMTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}