Instructions to use VMXVMX/llama2-project with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use VMXVMX/llama2-project with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/tmp/huggingface/hub/hf-llama-2-7b") model = PeftModel.from_pretrained(base_model, "VMXVMX/llama2-project") - Notebooks
- Google Colab
- Kaggle
'first'
Browse files- README.md +9 -0
- adapter_config.json +20 -0
- adapter_model.bin +3 -0
- added_tokens.json +3 -0
- config.json +26 -0
- generation_config.json +9 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +330 -0
- models--llama-2-7b.230914-071855.jsonl +11 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- test.csv +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +34 -0
- train.csv +0 -0
- trainer_state.json +86 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.4.0.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "/tmp/huggingface/hub/hf-llama-2-7b",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 8,
|
| 10 |
+
"lora_dropout": 0.0,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"q_proj",
|
| 17 |
+
"v_proj"
|
| 18 |
+
],
|
| 19 |
+
"task_type": "CAUSAL_LM"
|
| 20 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ca23df047b613b0bdf4d0b039cea3a7b9c097b2d7bb797c6870cc93f0cf9fac
|
| 3 |
+
size 16822989
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/tmp/huggingface/hub/hf-llama-2-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"num_key_value_heads": 32,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.31.0",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32001
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 32000,
|
| 6 |
+
"temperature": 0.9,
|
| 7 |
+
"top_p": 0.6,
|
| 8 |
+
"transformers_version": "4.31.0"
|
| 9 |
+
}
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7595afe9f59dc93d4db397cd53ea7ab532a6887e93f3bc938a1475ee269e005
|
| 3 |
+
size 1981888424
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae77f2cca400bd0f0cf5d068da858a7ae5bd11eac442718724c1dac1a7cb157d
|
| 3 |
+
size 1990286032
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2fc38dded5ee547a51d4010c244078ae1cbd457c201005f85e220039e2ed780
|
| 3 |
+
size 1990286072
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42a03ee26405dfa9b10d6d079312a75d68628ce38ad6f1493c19c078f8ed826e
|
| 3 |
+
size 1990286080
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82df13c2c480a33546e7eaceb28c2edf36ef6d4bc708a61c6df032031d476ba2
|
| 3 |
+
size 1933646360
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b2ba794aff3fc5f28d3f4abf5f363cb5e23d909f5229706f8587bc4461f1670
|
| 3 |
+
size 1933662968
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a437a929f8ddc64d7b8e507b5f9a0bda02342fc73af2ce5323d2342112526b4
|
| 3 |
+
size 1656836880
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13476855808
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00007-of-00007.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 268 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 269 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 270 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 271 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 272 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 273 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 274 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 275 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 279 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 280 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 281 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 282 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 283 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 284 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 285 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
| 287 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 288 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 289 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 290 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 291 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 292 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 293 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 294 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 295 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
| 297 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 298 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 299 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 300 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 301 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 302 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 303 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 304 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 305 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
| 307 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 308 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 309 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 310 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 311 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 312 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 313 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 314 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 315 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 318 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 319 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 320 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 321 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 322 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 323 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 324 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 325 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
|
| 327 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 328 |
+
"model.norm.weight": "model-00007-of-00007.safetensors"
|
| 329 |
+
}
|
| 330 |
+
}
|
models--llama-2-7b.230914-071855.jsonl
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"timestamp": 1694676536.8560767, "level": "info", "message": {"loss": 1.6945, "learning_rate": 0.00018568571761675893, "epoch": 0.96}}
|
| 2 |
+
{"timestamp": 1694676547.6095676, "level": "info", "message": {"eval_loss": 0.8912153244018555, "eval_runtime": 10.4021, "eval_samples_per_second": 4.711, "eval_steps_per_second": 4.711, "epoch": 0.96}}
|
| 3 |
+
{"timestamp": 1694676730.9974933, "level": "info", "message": {"loss": 0.5639, "learning_rate": 0.00013701381553399145, "epoch": 1.92}}
|
| 4 |
+
{"timestamp": 1694676741.7312047, "level": "info", "message": {"eval_loss": 0.39273881912231445, "eval_runtime": 10.4024, "eval_samples_per_second": 4.71, "eval_steps_per_second": 4.71, "epoch": 1.92}}
|
| 5 |
+
{"timestamp": 1694676924.8922534, "level": "info", "message": {"loss": 0.3821, "learning_rate": 7.324716614707793e-05, "epoch": 2.88}}
|
| 6 |
+
{"timestamp": 1694676935.6283114, "level": "info", "message": {"eval_loss": 0.3932119607925415, "eval_runtime": 10.394, "eval_samples_per_second": 4.714, "eval_steps_per_second": 4.714, "epoch": 2.88}}
|
| 7 |
+
{"timestamp": 1694677119.0242765, "level": "info", "message": {"loss": 0.3224, "learning_rate": 1.4314282383241096e-05, "epoch": 4.0}}
|
| 8 |
+
{"timestamp": 1694677129.83537, "level": "info", "message": {"eval_loss": 0.3916894495487213, "eval_runtime": 10.4021, "eval_samples_per_second": 4.711, "eval_steps_per_second": 4.711, "epoch": 4.0}}
|
| 9 |
+
{"timestamp": 1694677274.1792173, "level": "info", "message": {"loss": 0.3501, "learning_rate": 0.0, "epoch": 4.8}}
|
| 10 |
+
{"timestamp": 1694677284.8865535, "level": "info", "message": {"eval_loss": 0.3856528401374817, "eval_runtime": 10.3967, "eval_samples_per_second": 4.713, "eval_steps_per_second": 4.713, "epoch": 4.8}}
|
| 11 |
+
{"timestamp": 1694677285.4267673, "level": "info", "message": {"train_runtime": 933.9373, "train_samples_per_second": 2.141, "train_steps_per_second": 0.032, "total_flos": 4.0472554450944e+16, "train_loss": 0.6616616368293762, "epoch": 4.8}}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e94bc0209fc8dcd1092e3025819db339065cfceeb247ee8e89ffdeeca1ac6d3e
|
| 3 |
+
size 33661637
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f6cf74835c1af9f9e3dc4bcfbc0eae1e84048401ffb87d26ff318411e17c02d
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a83272f1b0ef670da99bb62dbce6094b7f78505c09c70be8b5ae8c3d1eba66d
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
test.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": false,
|
| 22 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"sp_model_kwargs": {},
|
| 25 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
train.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3856528401374817,
|
| 3 |
+
"best_model_checkpoint": "ckpt_output/checkpoint-30",
|
| 4 |
+
"epoch": 4.8,
|
| 5 |
+
"global_step": 30,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.96,
|
| 12 |
+
"learning_rate": 0.00018568571761675893,
|
| 13 |
+
"loss": 1.6945,
|
| 14 |
+
"step": 6
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.96,
|
| 18 |
+
"eval_loss": 0.8912153244018555,
|
| 19 |
+
"eval_runtime": 10.4021,
|
| 20 |
+
"eval_samples_per_second": 4.711,
|
| 21 |
+
"eval_steps_per_second": 4.711,
|
| 22 |
+
"step": 6
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.92,
|
| 26 |
+
"learning_rate": 0.00013701381553399145,
|
| 27 |
+
"loss": 0.5639,
|
| 28 |
+
"step": 12
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.92,
|
| 32 |
+
"eval_loss": 0.39273881912231445,
|
| 33 |
+
"eval_runtime": 10.4024,
|
| 34 |
+
"eval_samples_per_second": 4.71,
|
| 35 |
+
"eval_steps_per_second": 4.71,
|
| 36 |
+
"step": 12
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.88,
|
| 40 |
+
"learning_rate": 7.324716614707793e-05,
|
| 41 |
+
"loss": 0.3821,
|
| 42 |
+
"step": 18
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.88,
|
| 46 |
+
"eval_loss": 0.3932119607925415,
|
| 47 |
+
"eval_runtime": 10.394,
|
| 48 |
+
"eval_samples_per_second": 4.714,
|
| 49 |
+
"eval_steps_per_second": 4.714,
|
| 50 |
+
"step": 18
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 1.4314282383241096e-05,
|
| 55 |
+
"loss": 0.3224,
|
| 56 |
+
"step": 25
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 0.3916894495487213,
|
| 61 |
+
"eval_runtime": 10.4021,
|
| 62 |
+
"eval_samples_per_second": 4.711,
|
| 63 |
+
"eval_steps_per_second": 4.711,
|
| 64 |
+
"step": 25
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.8,
|
| 68 |
+
"learning_rate": 0.0,
|
| 69 |
+
"loss": 0.3501,
|
| 70 |
+
"step": 30
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 4.8,
|
| 74 |
+
"eval_loss": 0.3856528401374817,
|
| 75 |
+
"eval_runtime": 10.3967,
|
| 76 |
+
"eval_samples_per_second": 4.713,
|
| 77 |
+
"eval_steps_per_second": 4.713,
|
| 78 |
+
"step": 30
|
| 79 |
+
}
|
| 80 |
+
],
|
| 81 |
+
"max_steps": 30,
|
| 82 |
+
"num_train_epochs": 5,
|
| 83 |
+
"total_flos": 4.0472554450944e+16,
|
| 84 |
+
"trial_name": null,
|
| 85 |
+
"trial_params": null
|
| 86 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5160cf2710c5ddc9c05c133318815eb2f597c109cf066669e89ecfe2bc32ff21
|
| 3 |
+
size 3963
|