Commit
•
bd17453
1
Parent(s):
a1b2e5d
Update README.md (#9)
Browse files- Update README.md (3e62766e899dfbbeb705c51c286d6a22cdb65532)
README.md
CHANGED
@@ -16,7 +16,7 @@ tags:
|
|
16 |
base_model: meta-llama/Meta-Llama-3-70B-Instruct
|
17 |
datasets:
|
18 |
- MaziyarPanahi/truthy-dpo-v0.1-axolotl
|
19 |
-
model_name:
|
20 |
pipeline_tag: text-generation
|
21 |
license_name: llama3
|
22 |
license_link: LICENSE
|
@@ -24,7 +24,7 @@ inference: false
|
|
24 |
model_creator: MaziyarPanahi
|
25 |
quantized_by: MaziyarPanahi
|
26 |
model-index:
|
27 |
-
- name:
|
28 |
results:
|
29 |
- task:
|
30 |
type: text-generation
|
@@ -42,7 +42,7 @@ model-index:
|
|
42 |
name: normalized accuracy
|
43 |
source:
|
44 |
url: >-
|
45 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/
|
46 |
name: Open LLM Leaderboard
|
47 |
- task:
|
48 |
type: text-generation
|
@@ -59,7 +59,7 @@ model-index:
|
|
59 |
name: normalized accuracy
|
60 |
source:
|
61 |
url: >-
|
62 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/
|
63 |
name: Open LLM Leaderboard
|
64 |
- task:
|
65 |
type: text-generation
|
@@ -77,7 +77,7 @@ model-index:
|
|
77 |
name: accuracy
|
78 |
source:
|
79 |
url: >-
|
80 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/
|
81 |
name: Open LLM Leaderboard
|
82 |
- task:
|
83 |
type: text-generation
|
@@ -94,7 +94,7 @@ model-index:
|
|
94 |
value: 63.45
|
95 |
source:
|
96 |
url: >-
|
97 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/
|
98 |
name: Open LLM Leaderboard
|
99 |
- task:
|
100 |
type: text-generation
|
@@ -112,7 +112,7 @@ model-index:
|
|
112 |
name: accuracy
|
113 |
source:
|
114 |
url: >-
|
115 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/
|
116 |
name: Open LLM Leaderboard
|
117 |
- task:
|
118 |
type: text-generation
|
@@ -130,23 +130,23 @@ model-index:
|
|
130 |
name: accuracy
|
131 |
source:
|
132 |
url: >-
|
133 |
-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/
|
134 |
name: Open LLM Leaderboard
|
135 |
---
|
136 |
|
137 |
<img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
138 |
|
139 |
|
140 |
-
# MaziyarPanahi/
|
141 |
|
142 |
This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model.
|
143 |
|
144 |
# ⚡ Quantized GGUF
|
145 |
|
146 |
-
All GGUF models are available here: [MaziyarPanahi/
|
147 |
|
148 |
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
149 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/
|
150 |
|
151 |
| Metric |Value|
|
152 |
|---------------------------------|----:|
|
@@ -178,7 +178,7 @@ This model uses `ChatML` prompt template:
|
|
178 |
|
179 |
# How to use
|
180 |
|
181 |
-
You can use this model by using `MaziyarPanahi/
|
182 |
transformers library.
|
183 |
|
184 |
```python
|
@@ -186,7 +186,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
|
|
186 |
from transformers import pipeline
|
187 |
import torch
|
188 |
|
189 |
-
model_id = "MaziyarPanahi/
|
190 |
|
191 |
model = AutoModelForCausalLM.from_pretrained(
|
192 |
model_id,
|
|
|
16 |
base_model: meta-llama/Meta-Llama-3-70B-Instruct
|
17 |
datasets:
|
18 |
- MaziyarPanahi/truthy-dpo-v0.1-axolotl
|
19 |
+
model_name: calme-2.3-llama3-70b
|
20 |
pipeline_tag: text-generation
|
21 |
license_name: llama3
|
22 |
license_link: LICENSE
|
|
|
24 |
model_creator: MaziyarPanahi
|
25 |
quantized_by: MaziyarPanahi
|
26 |
model-index:
|
27 |
+
- name: calme-2.3-llama3-70b
|
28 |
results:
|
29 |
- task:
|
30 |
type: text-generation
|
|
|
42 |
name: normalized accuracy
|
43 |
source:
|
44 |
url: >-
|
45 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
|
46 |
name: Open LLM Leaderboard
|
47 |
- task:
|
48 |
type: text-generation
|
|
|
59 |
name: normalized accuracy
|
60 |
source:
|
61 |
url: >-
|
62 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
|
63 |
name: Open LLM Leaderboard
|
64 |
- task:
|
65 |
type: text-generation
|
|
|
77 |
name: accuracy
|
78 |
source:
|
79 |
url: >-
|
80 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
|
81 |
name: Open LLM Leaderboard
|
82 |
- task:
|
83 |
type: text-generation
|
|
|
94 |
value: 63.45
|
95 |
source:
|
96 |
url: >-
|
97 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
|
98 |
name: Open LLM Leaderboard
|
99 |
- task:
|
100 |
type: text-generation
|
|
|
112 |
name: accuracy
|
113 |
source:
|
114 |
url: >-
|
115 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
|
116 |
name: Open LLM Leaderboard
|
117 |
- task:
|
118 |
type: text-generation
|
|
|
130 |
name: accuracy
|
131 |
source:
|
132 |
url: >-
|
133 |
+
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
|
134 |
name: Open LLM Leaderboard
|
135 |
---
|
136 |
|
137 |
<img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
138 |
|
139 |
|
140 |
+
# MaziyarPanahi/calme-2.3-llama3-70b
|
141 |
|
142 |
This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model.
|
143 |
|
144 |
# ⚡ Quantized GGUF
|
145 |
|
146 |
+
All GGUF models are available here: [MaziyarPanahi/calme-2.3-llama3-70b-GGUF](https://huggingface.co/MaziyarPanahi/calme-2.3-llama3-70b-GGUF)
|
147 |
|
148 |
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
149 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__calme-2.3-llama3-70b)
|
150 |
|
151 |
| Metric |Value|
|
152 |
|---------------------------------|----:|
|
|
|
178 |
|
179 |
# How to use
|
180 |
|
181 |
+
You can use this model by using `MaziyarPanahi/calme-2.3-llama3-70b` as the model name in Hugging Face's
|
182 |
transformers library.
|
183 |
|
184 |
```python
|
|
|
186 |
from transformers import pipeline
|
187 |
import torch
|
188 |
|
189 |
+
model_id = "MaziyarPanahi/calme-2.3-llama3-70b"
|
190 |
|
191 |
model = AutoModelForCausalLM.from_pretrained(
|
192 |
model_id,
|