Upload LlamaForCausalLM
Browse files- README.md +6 -6
- config.json +29 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
README.md
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- autotrain
|
| 4 |
- text-generation-inference
|
| 5 |
- text-generation
|
| 6 |
- peft
|
| 7 |
-
library_name: transformers
|
| 8 |
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 9 |
-
widget:
|
| 10 |
-
- messages:
|
| 11 |
-
- role: user
|
| 12 |
-
content: What is your favorite condiment?
|
| 13 |
-
license: other
|
| 14 |
datasets:
|
| 15 |
- meirm/cia_poumpouras
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# Model Trained Using AutoTrain
|
|
|
|
| 1 |
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: transformers
|
| 4 |
tags:
|
| 5 |
- autotrain
|
| 6 |
- text-generation-inference
|
| 7 |
- text-generation
|
| 8 |
- peft
|
|
|
|
| 9 |
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
datasets:
|
| 11 |
- meirm/cia_poumpouras
|
| 12 |
+
widget:
|
| 13 |
+
- messages:
|
| 14 |
+
- role: user
|
| 15 |
+
content: What is your favorite condiment?
|
| 16 |
---
|
| 17 |
|
| 18 |
# Model Trained Using AutoTrain
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float16",
|
| 26 |
+
"transformers_version": "4.41.0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.0"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:043c6daa171cd0ead829a2817266dbfe25f583626cae0f784f512fdc19ffcce5
|
| 3 |
+
size 2200119664
|