Upload LlamaForCausalLM
Browse files- config.json +45 -0
- generation_config.json +8 -0
- pytorch_model-00001-of-00007.bin +3 -0
- pytorch_model-00002-of-00007.bin +3 -0
- pytorch_model-00003-of-00007.bin +3 -0
- pytorch_model-00004-of-00007.bin +3 -0
- pytorch_model-00005-of-00007.bin +3 -0
- pytorch_model-00006-of-00007.bin +3 -0
- pytorch_model-00007-of-00007.bin +3 -0
- pytorch_model.bin.index.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 123964,
|
| 8 |
+
"dtype": "float16",
|
| 9 |
+
"eos_token_id": 123972,
|
| 10 |
+
"head_dim": 160,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 5120,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 27392,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 40,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 124415,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"quantization_config": {
|
| 24 |
+
"_load_in_4bit": true,
|
| 25 |
+
"_load_in_8bit": false,
|
| 26 |
+
"bnb_4bit_compute_dtype": "float16",
|
| 27 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 28 |
+
"bnb_4bit_quant_type": "nf4",
|
| 29 |
+
"bnb_4bit_use_double_quant": false,
|
| 30 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 31 |
+
"llm_int8_has_fp16_weight": false,
|
| 32 |
+
"llm_int8_skip_modules": null,
|
| 33 |
+
"llm_int8_threshold": 6.0,
|
| 34 |
+
"load_in_4bit": true,
|
| 35 |
+
"load_in_8bit": false,
|
| 36 |
+
"quant_method": "bitsandbytes"
|
| 37 |
+
},
|
| 38 |
+
"rms_norm_eps": 1e-05,
|
| 39 |
+
"rope_scaling": null,
|
| 40 |
+
"rope_theta": 1000000.0,
|
| 41 |
+
"tie_word_embeddings": false,
|
| 42 |
+
"transformers_version": "4.57.3",
|
| 43 |
+
"use_cache": true,
|
| 44 |
+
"vocab_size": 124416
|
| 45 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 123964,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 123972,
|
| 5 |
+
"temperature": 0.6,
|
| 6 |
+
"top_p": 0.9,
|
| 7 |
+
"transformers_version": "4.57.3"
|
| 8 |
+
}
|
pytorch_model-00001-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ddcc366ae077a9665fd7b75b76a06301e48d03beddaafcad86a6889f8853953
|
| 3 |
+
size 1936907411
|
pytorch_model-00002-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e979ad15ff8f30dd851bca9eb038646ff41119dd6224f66ae60fb7fd867c351c
|
| 3 |
+
size 1993831519
|
pytorch_model-00003-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8de88e61b6545826656e23897a29021c76129b642a9cf154f75a2d1bb60e5d6
|
| 3 |
+
size 1993852933
|
pytorch_model-00004-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31a4b31f94ecac27fe99a8f0e9bfac965620fc1395458f2d5e9448393f1c03ed
|
| 3 |
+
size 1951811523
|
pytorch_model-00005-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:362c6bd24802ad36e3279c8abb0cf771dd17cd1f0e8fc5e9819a0c2e3ffb8e6d
|
| 3 |
+
size 1993831775
|
pytorch_model-00006-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff84ce1c6160771a80362ad674d8676504e068987ddcff997e4713e1e7029c54
|
| 3 |
+
size 1993831775
|
pytorch_model-00007-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9db2a4981dbbefee350f76a5023d1497699da8102d091cb96ffd57c59340e03b
|
| 3 |
+
size 1626506125
|
pytorch_model.bin.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|