Upload folder using huggingface_hub

config.json

@@ -0,0 +1,43 @@
+{
+    "_name_or_path": "/home/alpha/Models/Raw/internlm_internlm2_5-7b-chat-1m",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attn_implementation": "eager",
+    "bias": false,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 262144,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "pad_token_id": 2,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "factor": 2.5,
+        "type": "dynamic"
+    },
+    "rope_theta": 50000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.42.3",
+    "use_cache": true,
+    "vocab_size": 92544,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.5",
+        "bits": 6.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

convert_weights_internlm.py

@@ -0,0 +1,101 @@
+#!/usr/bin/env python3
+# 1/17/2024
+# Charles O. Goddard
+# https://huggingface.co/chargoddard/internlm2-7b-llama/raw/main/convert_weights.py
+"""Convert internlm2 weights to Llama format."""
+
+import json
+import os
+import einops
+import tqdm
+from mergekit.io import LazyTensorLoader, TensorWriter
+from mergekit.common import ModelReference
+from transformers import LlamaTokenizer
+
+MODEL_IN = "raw weights"
+OUT_PATH = "llamafied weights"
+
+model_ref = ModelReference.parse(MODEL_IN)
+cfg = model_ref.config(trust_remote_code=True)
+head_dim = cfg.hidden_size // cfg.num_attention_heads
+num_key_value_groups = cfg.num_attention_heads // cfg.num_key_value_heads
+loader = LazyTensorLoader(model_ref.tensor_index(), lazy_unpickle=True)
+writer = TensorWriter(OUT_PATH)
+
+SIMPLE_REPLACEMENTS = {
+    "feed_forward.w1": "mlp.gate_proj",
+    "feed_forward.w2": "mlp.down_proj",
+    "feed_forward.w3": "mlp.up_proj",
+    "attention.wo": "self_attn.o_proj",
+    "ffn_norm": "post_attention_layernorm",
+    "attention_norm": "input_layernorm",
+    "tok_embeddings": "embed_tokens",
+    "output.weight": "lm_head.weight",
+}
+
+for tensor_name in tqdm.tqdm(loader.index.tensor_paths):
+    tensor = loader.get_tensor(tensor_name)
+    if "attention.wqkv" in tensor_name:
+        # make me think about tensor shapes will you >:(
+
+        # ((cfg.num_attention_heads + 2 * cfg.num_key_value_heads) * head_dim, cfg.hidden_size) x (batch_sz, sq_len, cfg.hidden_size)
+        # -> (batch_sz, sq_len, (cfg.num_attention_heads + 2 * cfg.num_key_value_heads) * head_dim)
+        # qkv_states = rearrange(
+        #     qkv_states,
+        #     "b q (h gs d) -> b q h gs d",
+        #     gs=2 + self.num_key_value_groups,
+        #     d=self.head_dim,
+        # )
+        # ->(batch_sz, sq_len, h, 2 + self.num_key_value_groups, head_dim)
+        qkv_vecs = einops.rearrange(
+            tensor, "(h gs d) z -> h gs d z", gs=2 + num_key_value_groups, d=head_dim
+        )
+        q_proj = (
+            qkv_vecs[:, :num_key_value_groups, ...]
+            .reshape(-1, cfg.hidden_size)
+            .contiguous()
+        )
+        k_proj = qkv_vecs[:, -2, ...].reshape(-1, cfg.hidden_size).contiguous()
+        v_proj = qkv_vecs[:, -1, ...].reshape(-1, cfg.hidden_size).contiguous()
+        assert k_proj.shape == v_proj.shape
+
+        writer.save_tensor(
+            tensor_name.replace("attention.wqkv", "self_attn.q_proj"),
+            q_proj,
+            clone=True,
+        )
+        writer.save_tensor(
+            tensor_name.replace("attention.wqkv", "self_attn.k_proj"),
+            k_proj,
+            clone=True,
+        )
+        writer.save_tensor(
+            tensor_name.replace("attention.wqkv", "self_attn.v_proj"),
+            v_proj,
+            clone=True,
+        )
+        continue
+
+    out_name = tensor_name
+    for pattern, sub in SIMPLE_REPLACEMENTS.items():
+        if pattern in out_name:
+            out_name = out_name.replace(pattern, sub)
+    writer.save_tensor(out_name, tensor)
+writer.finalize()
+
+cfg_dict = json.loads(cfg.to_json_string())
+del cfg_dict["auto_map"]
+cfg_dict["architectures"] = ["LlamaForCausalLM"]
+cfg_dict["model_type"] = "llama"
+if "rope_scaling" in cfg_dict and cfg_dict["rope_scaling"]["factor"] == 1.0:
+    del cfg_dict["rope_scaling"]
+with open(os.path.join(OUT_PATH, "config.json"), "w", encoding="utf-8") as fp:
+    json.dump(cfg_dict, fp, indent=2)
+
+# InternLMTokenizer differences:
+# 1. clean_up_tokenization() hardcoded to always be called
+# 2. might prepend a space to some tokens that LlamaTokenizer doesn't if they're the first token
+# 1 is easy to fix, 2... is not important
+tok = LlamaTokenizer.from_pretrained(MODEL_IN, trust_remote_code=False, legacy=True)
+tok.clean_up_tokenization_spaces = True
+tok.save_pretrained(OUT_PATH)

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 15475417088}, "weight_map": {"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00003-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5782458335220c3e954300f04cb207d4e823883e185a64c1b392499450e3f0
+size 4262967508

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf111584d5280196e32028bd45565cec3be2b151b53e527348b81029b2af714
+size 2026454576

special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|action_start|>",
+    "<|action_end|>",
+    "<|interpreter|>",
+    "<|plugin|>"
+  ],
+  "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": "</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 +1,106 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    },
+    "92538": {
+      "content": "<|plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92539": {
+      "content": "<|interpreter|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92540": {
+      "content": "<|action_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92541": {
+      "content": "<|action_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92542": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92543": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|action_start|>",
+    "<|action_end|>",
+    "<|interpreter|>",
+    "<|plugin|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_internlm2.InternLM2Tokenizer",
+      "tokenization_internlm2_fast.InternLM2TokenizerFast"
+    ]
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "decode_with_prefix_space": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}