Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1 @@
+{"_name_or_path": "lodrick-the-lafted/Densefin-291-Mistral-22B", "architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 65536, "model_type": "mixtral", "num_attention_heads": 48, "num_hidden_layers": 56, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.40.2", "use_cache": false, "vocab_size": 32002}

densify.py

@@ -0,0 +1,79 @@
+import glob
+import json
+import torch
+from safetensors import safe_open
+from safetensors.torch import save_file
+
+def main():
+    print("densifying...")
+    files = glob.glob("model-*-of-*.safetensors")
+    densified = {}
+
+    for mf in sorted(files):
+        st = safe_open(mf, framework='pt')
+        print(f"processing {mf}")
+
+        for key in st.keys():
+            tensor = st.get_tensor(key)
+            nk = key.replace("block_sparse_moe.experts.0.w2.weight", "mlp.down_proj.weight")
+            nk = nk.replace("block_sparse_moe.experts.0.w1.weight", "mlp.gate_proj.weight")
+            nk = nk.replace("block_sparse_moe.experts.0.w3.weight", "mlp.up_proj.weight")
+
+            if "block_sparse_moe.gate.weight" not in key:
+                densified[nk] = tensor
+                print(f"+ {key} -> {nk}")
+            else:
+                print(f"- {key}")
+        save_file(densified, f"{mf}-x")
+        densified = {}
+
+    with open("config.json", "r") as read_conf_file:
+        conf = json.load(read_conf_file)
+    with open("config.json.old", "w") as conf_file:
+        json.dump(conf, conf_file)
+
+    if 'num_local_experts' in conf:
+        del conf['num_local_experts']
+    if 'num_experts_per_tok' in conf:
+        del conf['num_experts_per_tok']
+    if 'output_router_logits' in conf:
+        del conf['output_router_logits']
+    if 'router_aux_loss_coef' in conf:
+        del conf['router_aux_loss_coef']
+    if 'router_jitter_noise' in conf:
+        del conf['router_jitter_noise']
+
+    conf['architectures'] = ['MistralForCausalLM']
+    conf['model_type'] = 'mistral'
+    conf['_name_or_path'] = 'lodrick-the-lafted/Densefin-291-Mistral-22B'
+
+    with open("config.json", "w") as write_conf_file:
+        json.dump(conf, write_conf_file, indent=4)
+
+    with open("model.safetensors.index.json", "r") as index_file:
+        index = json.load(index_file)
+
+    new_index = {}
+    new_index['metadata'] = index['metadata']
+
+    wm = index['weight_map']
+    nwm = {}
+
+    for weight in wm.keys():
+        nk = weight.replace("block_sparse_moe.experts.0.w2.weight", "mlp.down_proj.weight")
+        nk = nk.replace("block_sparse_moe.experts.0.w1.weight", "mlp.gate_proj.weight")
+        nk = nk.replace("block_sparse_moe.experts.0.w3.weight", "mlp.up_proj.weight")
+        #print(f"{weight} -> {nk}")
+
+        if "block_sparse_moe.gate.weight" not in weight:
+            nwm[nk] = wm[weight]
+
+    new_index['weight_map'] = nwm
+ 
+    with open("model.safetensors.index.json.old", "w") as backup:
+        json.dump(index, backup, indent=4)
+    with open("model.safetensors.index.json", "w") as new_st_index:
+        json.dump(new_index, new_st_index, indent=4)
+
+if __name__ == "__main__":
+    main()

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c66ffb6cef89739bc962d0e8124f95d2d59f387d8f1635808e106079177ab9b
+size 4872886136

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3add7e98988cc95d96a6f3bbdb36fcf0737bab6fb73d60fb017d1e2cc8c1c31
+size 4983012128

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d08c1ed875acbd1915b9f50d12dca05b840001183ded47a9fe6b4af48deccd
+size 4957821304

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412463239353e7c0fb17392d99acb576d6a77cd5178a89261df80db2410d031d
+size 4882323712

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439a7c7ee9ccd4f68c64c4d22cfd8475c7d372a2ef2c63b02228dd0e73f23d11
+size 4983012160

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cad211ba13bb93a89e795f3be440ed10062dcaaeb6f5ec704061909ad0188a
+size 4957821304

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0d95a0e9f89b7d1c54c2abddc543892428df7c0b1a04f2f3b010a1132dac7e
+size 4882323712

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0ee9cdbedbde1e37ee9a33e9f4e90e8725e900f75c8c8d7d975cac17737d2c
+size 4983012160

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a36d2e23e1fb3bfdd5fb99bcc8107bca123137c21136abe9c27528e293f66d
+size 4973586416

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 44476428288}, "weight_map": {"lm_head.weight": "model-00009-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.40.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": false,
+  "eos_token": "<|im_end|>",
+  "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
+}