first commit
Browse files- config.json +24 -0
- quant_config.json +11 -0
- quantized_weights.pt +3 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LLaMAForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 1,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"max_sequence_length": 2048,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"pad_token_id": -1,
|
| 18 |
+
"rms_norm_eps": 1e-06,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float16",
|
| 21 |
+
"transformers_version": "4.28.0",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 32000
|
| 24 |
+
}
|
quant_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "c4",
|
| 3 |
+
"bits": 4,
|
| 4 |
+
"nsamples": 128,
|
| 5 |
+
"groupsize": 64,
|
| 6 |
+
"act_order": true,
|
| 7 |
+
"percdamp": 0.01,
|
| 8 |
+
"seed": 0,
|
| 9 |
+
"nearest": false,
|
| 10 |
+
"save": "/tmp/llama-out-test"
|
| 11 |
+
}
|
quantized_weights.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d2d5c6bd83723f210cc499e02cabec7a30d0e17c976e04334e9195a2a52ec4f
|
| 3 |
+
size 4020707137
|