Commit
•
c8004e2
1
Parent(s):
7f5a336
Upload LlamaForCausalLM
Browse files- README.md +201 -0
- config.json +43 -0
- generation_config.json +12 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- trl
|
5 |
+
- sft
|
6 |
+
---
|
7 |
+
|
8 |
+
# Model Card for Model ID
|
9 |
+
|
10 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
11 |
+
|
12 |
+
|
13 |
+
|
14 |
+
## Model Details
|
15 |
+
|
16 |
+
### Model Description
|
17 |
+
|
18 |
+
<!-- Provide a longer summary of what this model is. -->
|
19 |
+
|
20 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
21 |
+
|
22 |
+
- **Developed by:** [More Information Needed]
|
23 |
+
- **Funded by [optional]:** [More Information Needed]
|
24 |
+
- **Shared by [optional]:** [More Information Needed]
|
25 |
+
- **Model type:** [More Information Needed]
|
26 |
+
- **Language(s) (NLP):** [More Information Needed]
|
27 |
+
- **License:** [More Information Needed]
|
28 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
29 |
+
|
30 |
+
### Model Sources [optional]
|
31 |
+
|
32 |
+
<!-- Provide the basic links for the model. -->
|
33 |
+
|
34 |
+
- **Repository:** [More Information Needed]
|
35 |
+
- **Paper [optional]:** [More Information Needed]
|
36 |
+
- **Demo [optional]:** [More Information Needed]
|
37 |
+
|
38 |
+
## Uses
|
39 |
+
|
40 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
41 |
+
|
42 |
+
### Direct Use
|
43 |
+
|
44 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
45 |
+
|
46 |
+
[More Information Needed]
|
47 |
+
|
48 |
+
### Downstream Use [optional]
|
49 |
+
|
50 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
51 |
+
|
52 |
+
[More Information Needed]
|
53 |
+
|
54 |
+
### Out-of-Scope Use
|
55 |
+
|
56 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
57 |
+
|
58 |
+
[More Information Needed]
|
59 |
+
|
60 |
+
## Bias, Risks, and Limitations
|
61 |
+
|
62 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
63 |
+
|
64 |
+
[More Information Needed]
|
65 |
+
|
66 |
+
### Recommendations
|
67 |
+
|
68 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
69 |
+
|
70 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
71 |
+
|
72 |
+
## How to Get Started with the Model
|
73 |
+
|
74 |
+
Use the code below to get started with the model.
|
75 |
+
|
76 |
+
[More Information Needed]
|
77 |
+
|
78 |
+
## Training Details
|
79 |
+
|
80 |
+
### Training Data
|
81 |
+
|
82 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
83 |
+
|
84 |
+
[More Information Needed]
|
85 |
+
|
86 |
+
### Training Procedure
|
87 |
+
|
88 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
89 |
+
|
90 |
+
#### Preprocessing [optional]
|
91 |
+
|
92 |
+
[More Information Needed]
|
93 |
+
|
94 |
+
|
95 |
+
#### Training Hyperparameters
|
96 |
+
|
97 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
98 |
+
|
99 |
+
#### Speeds, Sizes, Times [optional]
|
100 |
+
|
101 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
102 |
+
|
103 |
+
[More Information Needed]
|
104 |
+
|
105 |
+
## Evaluation
|
106 |
+
|
107 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
108 |
+
|
109 |
+
### Testing Data, Factors & Metrics
|
110 |
+
|
111 |
+
#### Testing Data
|
112 |
+
|
113 |
+
<!-- This should link to a Dataset Card if possible. -->
|
114 |
+
|
115 |
+
[More Information Needed]
|
116 |
+
|
117 |
+
#### Factors
|
118 |
+
|
119 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
120 |
+
|
121 |
+
[More Information Needed]
|
122 |
+
|
123 |
+
#### Metrics
|
124 |
+
|
125 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
126 |
+
|
127 |
+
[More Information Needed]
|
128 |
+
|
129 |
+
### Results
|
130 |
+
|
131 |
+
[More Information Needed]
|
132 |
+
|
133 |
+
#### Summary
|
134 |
+
|
135 |
+
|
136 |
+
|
137 |
+
## Model Examination [optional]
|
138 |
+
|
139 |
+
<!-- Relevant interpretability work for the model goes here -->
|
140 |
+
|
141 |
+
[More Information Needed]
|
142 |
+
|
143 |
+
## Environmental Impact
|
144 |
+
|
145 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
146 |
+
|
147 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
148 |
+
|
149 |
+
- **Hardware Type:** [More Information Needed]
|
150 |
+
- **Hours used:** [More Information Needed]
|
151 |
+
- **Cloud Provider:** [More Information Needed]
|
152 |
+
- **Compute Region:** [More Information Needed]
|
153 |
+
- **Carbon Emitted:** [More Information Needed]
|
154 |
+
|
155 |
+
## Technical Specifications [optional]
|
156 |
+
|
157 |
+
### Model Architecture and Objective
|
158 |
+
|
159 |
+
[More Information Needed]
|
160 |
+
|
161 |
+
### Compute Infrastructure
|
162 |
+
|
163 |
+
[More Information Needed]
|
164 |
+
|
165 |
+
#### Hardware
|
166 |
+
|
167 |
+
[More Information Needed]
|
168 |
+
|
169 |
+
#### Software
|
170 |
+
|
171 |
+
[More Information Needed]
|
172 |
+
|
173 |
+
## Citation [optional]
|
174 |
+
|
175 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
176 |
+
|
177 |
+
**BibTeX:**
|
178 |
+
|
179 |
+
[More Information Needed]
|
180 |
+
|
181 |
+
**APA:**
|
182 |
+
|
183 |
+
[More Information Needed]
|
184 |
+
|
185 |
+
## Glossary [optional]
|
186 |
+
|
187 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
188 |
+
|
189 |
+
[More Information Needed]
|
190 |
+
|
191 |
+
## More Information [optional]
|
192 |
+
|
193 |
+
[More Information Needed]
|
194 |
+
|
195 |
+
## Model Card Authors [optional]
|
196 |
+
|
197 |
+
[More Information Needed]
|
198 |
+
|
199 |
+
## Model Card Contact
|
200 |
+
|
201 |
+
[More Information Needed]
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128001,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"quantization_config": {
|
21 |
+
"_load_in_4bit": true,
|
22 |
+
"_load_in_8bit": false,
|
23 |
+
"bnb_4bit_compute_dtype": "float16",
|
24 |
+
"bnb_4bit_quant_storage": "uint8",
|
25 |
+
"bnb_4bit_quant_type": "nf4",
|
26 |
+
"bnb_4bit_use_double_quant": true,
|
27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
28 |
+
"llm_int8_has_fp16_weight": false,
|
29 |
+
"llm_int8_skip_modules": null,
|
30 |
+
"llm_int8_threshold": 6.0,
|
31 |
+
"load_in_4bit": true,
|
32 |
+
"load_in_8bit": false,
|
33 |
+
"quant_method": "bitsandbytes"
|
34 |
+
},
|
35 |
+
"rms_norm_eps": 1e-05,
|
36 |
+
"rope_scaling": null,
|
37 |
+
"rope_theta": 500000.0,
|
38 |
+
"tie_word_embeddings": false,
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.39.3",
|
41 |
+
"use_cache": false,
|
42 |
+
"vocab_size": 128256
|
43 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128009
|
7 |
+
],
|
8 |
+
"max_length": 4096,
|
9 |
+
"temperature": 0.6,
|
10 |
+
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.39.3"
|
12 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e11b1074c61984e4f3b1621381476c838bab84dbf19c74c2c4c020bfb1af75b6
|
3 |
+
size 4978378128
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c068efd06c46d3142f93228c33295c1708d24d0f49c02010fd680738fa99dec2
|
3 |
+
size 2839903747
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|